Benchmark Results - ScanNet Benchmark

This table lists the benchmark results for the ScanNet200 3D semantic label scenario.

Method	avg iou	head iou	common iou	tail iou	wall	chair	floor	table	door	couch	cabinet	shelf	desk	office chair	bed	pillow	sink	picture	window	toilet	bookshelf	monitor	curtain	book	coffee table	box	refrigerator	lamp	kitchen cabinet	towel	clothes	tv	nightstand	counter	dresser	stool	cushion	plant	ceiling	bathtub	end table	dining table	keyboard	bag	backpack	toilet paper	printer	tv stand	whiteboard	blanket	shower curtain	trash can	closet	stairs	microwave	stove	shoe	computer tower	bottle	bin	bench	board	washing machine	mirror	copier	basket	sofa chair	file cabinet	fan	laptop	shower	paper	person	paper towel dispenser	oven	blinds	rack	plate	blackboard	piano	suitcase	radiator	recycling bin	wardrobe	soap dispenser	telephone	bucket	clock	stand	light	laundry basket	pipe	clothes dryer	seat	speaker	column	bicycle	ladder	bathroom stall	shower wall	cup	jacket	storage bin	coffee maker	dishwasher	paper towel roll	machine	mat	windowsill	bar	toaster	bulletin board	ironing board	kitchen counter	doorframe	toilet paper dispenser	mini fridge	fire extinguisher	ball	hat	shower curtain rod	water cooler	paper cutter	tray	ledge	mouse	cart	storage container	scale	tissue box	light switch	power outlet	decoration	sign	projector	vacuum cleaner	candle	plunger	stuffed animal	headphones	dish rack	broom	range hood	water bottle	vent	shower floor	water pitcher	mailbox	bowl	paper bag	music stand	projector screen	laundry detergent	object	bathroom vanity	laundry hamper	bathroom stall door	ceiling light	trash bin	dumbbell	stair rail	tube	bathroom cabinet	closet rod	coffee kettle	structure	shower head	keyboard piano	case of water bottles	coat rack	storage organizer	folded chair	fire alarm	power strip	calendar	poster

DITR	0.449 1	0.629 1	0.392 1	0.289 1	0.851 2	0.727 2	0.969 4	0.600 2	0.741 3	0.805 1	0.519 1	0.480 4	0.636 1	0.014 10	0.867 1	0.680 2	0.849 1	0.318 4	0.753 2	0.982 2	0.508 13	0.871 7	0.934 2	0.482 1	0.596 12	0.551 2	0.804 4	0.508 6	0.729 1	0.718 2	0.417 5	0.886 2	0.664 3	0.000 17	0.500 2	0.698 1	0.000 1	0.913 1	0.901 3	0.766 8	0.113 12	0.000 7	0.617 6	0.168 2	0.650 1	0.477 2	0.826 1	0.962 1	0.348 4	0.300 1	0.947 1	0.776 2	0.160 3	0.889 2	0.651 5	0.720 2	0.700 1	0.728 3	0.317 1	0.000 3	0.238 5	0.664 1	0.869 5	0.514 2	0.998 1	0.313 4	0.138 10	0.815 2	0.828 1	0.622 2	0.421 6	0.000 1	0.823 1	0.817 1	0.000 4	0.000 10	0.000 1	0.157 2	0.866 4	0.991 1	0.805 1	0.660 5	0.571 2	0.043 13	0.709 7	0.642 3	0.000 3	0.000 8	0.000 1	0.028 10	0.018 3	0.134 3	0.967 3	0.000 1	0.150 2	0.130 2	0.949 1	0.855 1	0.580 1	0.262 5	0.314 1	0.230 6	0.222 4	0.498 5	0.367 2	0.153 3	0.869 1	0.334 2	0.397 8	0.000 3	0.904 1	0.486 2	1.000 1	0.423 4	0.484 2	0.632 7	0.716 1	0.733 2	0.862 1	0.000 1	0.433 15	0.710 1	0.851 3	0.000 1	0.034 4	0.315 4	0.385 1	0.000 7	0.001 10	0.268 10	0.066 12	0.000 8	0.278 4	0.000 1	0.978 1	0.839 9	0.000 1	0.448 5	0.000 1	0.579 1	0.403 13	0.000 1	0.647 4	0.000 1	0.000 1	0.411 4	0.315 7	0.904 8	0.420 1	0.392 3	0.000 1	0.091 6	0.000 1	0.128 3	0.564 4	0.591 3	0.568 2	0.079 10	0.139 10	1.000 1	0.714 4	0.178 1	0.000 1	0.606 4	0.000 2	0.000 2	0.148 7	0.983 1	0.000 3	0.000 1	0.000 1	0.374 2	0.000 7	0.000 3	0.662 5	0.000 1
Karim Abou Zeid, Kadir Yilmaz, Daan de Geus, Alexander Hermans, David Adrian, Timm Linder, Bastian Leibe: DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation. 3DV 2026
Volt	0.416 2	0.619 2	0.318 4	0.269 3	0.850 4	0.735 1	0.958 5	0.639 1	0.753 2	0.773 3	0.504 3	0.542 2	0.631 2	0.000 14	0.795 7	0.686 1	0.834 2	0.335 3	0.721 4	0.982 2	0.625 2	0.884 2	0.905 5	0.237 13	0.653 4	0.429 5	0.679 15	0.462 11	0.709 3	0.680 3	0.475 1	0.893 1	0.652 5	0.000 17	0.392 9	0.541 12	0.000 1	0.865 4	0.900 5	0.952 1	0.000 17	0.000 7	0.700 2	0.138 4	0.528 3	0.501 1	0.678 4	0.842 6	0.357 3	0.227 2	0.909 3	0.719 4	0.093 8	0.924 1	0.614 8	0.682 6	0.635 3	0.696 8	0.238 8	0.000 3	0.143 13	0.606 4	0.898 2	0.430 4	0.988 2	0.356 1	0.136 12	0.881 1	0.609 4	0.583 3	0.588 1	0.000 1	0.624 3	0.635 11	0.000 4	0.087 2	0.000 1	0.000 6	0.904 2	0.903 2	0.747 2	0.696 2	0.410 8	0.272 7	0.737 4	0.603 4	0.000 3	0.097 1	0.000 1	0.007 17	0.000 4	0.063 11	0.981 1	0.000 1	0.066 5	0.000 10	0.891 2	0.431 9	0.380 8	0.261 6	0.265 4	0.274 4	0.069 10	0.425 9	0.401 1	0.151 4	0.631 2	0.005 16	0.324 13	0.000 3	0.778 2	0.251 4	0.000 15	0.421 5	0.499 1	0.725 3	0.223 4	0.277 7	0.862 1	0.000 1	0.728 1	0.351 14	0.855 2	0.000 1	0.020 6	0.407 1	0.218 4	0.000 7	0.997 1	0.329 8	0.218 4	0.000 8	0.000 11	0.000 1	0.000 5	0.930 1	0.000 1	0.551 1	0.000 1	0.518 2	0.493 8	0.000 1	0.962 1	0.000 1	0.000 1	0.414 3	0.576 1	0.934 2	0.188 3	0.398 2	0.000 1	0.000 9	0.000 1	0.040 18	0.616 2	0.553 5	0.438 7	0.082 8	0.141 7	0.437 12	0.888 1	0.000 12	0.000 1	0.754 1	0.000 2	0.000 2	1.000 1	0.752 6	0.000 3	0.000 1	0.000 1	0.142 9	0.000 7	0.000 3	0.791 3	0.000 1
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
CeCo	0.340 8	0.551 10	0.247 14	0.181 7	0.784 14	0.661 15	0.939 14	0.564 7	0.624 14	0.721 13	0.484 6	0.429 6	0.575 6	0.027 8	0.774 12	0.503 15	0.753 6	0.242 14	0.656 12	0.945 10	0.534 8	0.865 8	0.860 12	0.177 18	0.616 9	0.400 6	0.818 2	0.579 1	0.615 12	0.367 15	0.408 7	0.726 16	0.633 6	0.162 1	0.360 10	0.619 3	0.000 1	0.828 10	0.873 10	0.924 3	0.109 13	0.083 3	0.564 7	0.057 16	0.475 13	0.266 12	0.781 2	0.767 8	0.257 8	0.100 12	0.825 12	0.663 11	0.048 16	0.620 14	0.551 13	0.595 14	0.532 8	0.692 9	0.246 6	0.000 3	0.213 6	0.615 2	0.861 8	0.376 8	0.900 9	0.000 8	0.102 16	0.660 9	0.321 16	0.547 6	0.226 14	0.000 1	0.311 14	0.742 5	0.011 3	0.006 9	0.000 1	0.000 6	0.546 16	0.824 9	0.345 15	0.665 3	0.450 6	0.435 1	0.683 9	0.411 9	0.338 1	0.000 8	0.000 1	0.030 9	0.000 4	0.068 9	0.892 9	0.000 1	0.063 6	0.000 10	0.257 14	0.304 14	0.387 6	0.079 15	0.228 7	0.190 12	0.000 15	0.586 1	0.347 5	0.133 8	0.000 5	0.037 13	0.377 10	0.000 3	0.384 9	0.006 17	0.003 13	0.421 5	0.410 11	0.643 6	0.171 10	0.121 10	0.142 13	0.000 1	0.510 12	0.447 11	0.474 15	0.000 1	0.000 12	0.286 6	0.083 12	0.000 7	0.000 11	0.603 1	0.096 8	0.063 5	0.000 11	0.000 1	0.000 5	0.898 4	0.000 1	0.429 8	0.000 1	0.400 3	0.550 4	0.000 1	0.633 7	0.000 1	0.000 1	0.377 6	0.000 16	0.916 5	0.000 10	0.000 12	0.000 1	0.000 9	0.000 1	0.102 12	0.499 10	0.296 15	0.463 6	0.089 5	0.304 1	0.740 3	0.401 17	0.010 7	0.000 1	0.560 5	0.000 2	0.000 2	0.709 3	0.652 11	0.000 3	0.000 1	0.000 1	0.143 8	0.000 7	0.000 3	0.609 6	0.000 1
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
BFANet ScanNet200	0.360 6	0.553 8	0.293 6	0.193 6	0.827 5	0.689 5	0.970 3	0.528 14	0.661 7	0.753 7	0.436 9	0.378 9	0.469 16	0.042 7	0.810 3	0.654 3	0.760 5	0.266 11	0.659 11	0.973 5	0.574 4	0.849 12	0.897 6	0.382 3	0.546 14	0.372 10	0.698 14	0.491 9	0.617 11	0.526 11	0.436 2	0.764 15	0.476 18	0.101 5	0.409 6	0.585 10	0.000 1	0.835 7	0.901 3	0.810 6	0.102 14	0.000 7	0.688 3	0.096 7	0.483 11	0.264 13	0.612 10	0.591 17	0.358 2	0.161 7	0.863 6	0.707 5	0.128 4	0.814 3	0.669 4	0.629 11	0.563 5	0.651 15	0.258 5	0.000 3	0.194 10	0.494 10	0.806 13	0.394 7	0.953 6	0.000 8	0.233 1	0.757 5	0.508 7	0.556 5	0.476 5	0.000 1	0.573 6	0.741 6	0.000 4	0.000 10	0.000 1	0.000 6	0.000 18	0.852 6	0.678 4	0.616 7	0.460 5	0.338 3	0.710 6	0.534 6	0.000 3	0.025 5	0.000 1	0.043 3	0.000 4	0.056 13	0.493 18	0.000 1	0.000 11	0.109 5	0.785 8	0.590 6	0.298 14	0.282 3	0.143 14	0.262 5	0.053 12	0.526 4	0.337 6	0.215 1	0.000 5	0.135 9	0.510 4	0.000 3	0.596 5	0.043 15	0.511 3	0.321 13	0.459 4	0.772 2	0.124 14	0.060 15	0.266 7	0.000 1	0.574 10	0.568 9	0.653 11	0.000 1	0.093 1	0.298 5	0.239 3	0.000 7	0.516 3	0.129 15	0.284 2	0.000 8	0.431 1	0.000 1	0.000 5	0.848 7	0.000 1	0.492 2	0.000 1	0.376 4	0.522 6	0.000 1	0.469 18	0.000 1	0.000 1	0.330 7	0.151 11	0.875 15	0.000 10	0.254 5	0.000 1	0.000 9	0.000 1	0.088 13	0.661 1	0.481 6	0.255 13	0.105 1	0.139 10	0.666 5	0.641 6	0.000 12	0.000 1	0.614 3	0.000 2	0.000 2	0.000 12	0.921 2	0.000 3	0.000 1	0.000 1	0.497 1	0.000 7	0.000 3	0.000 12	0.000 1
Weiguang Zhao, Rui Zhang, Qiufeng Wang, Guangliang Cheng, Kaizhu Huang: BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis. CVPR 2025
GSTran	0.334 11	0.533 13	0.250 13	0.179 9	0.799 12	0.684 8	0.940 11	0.554 10	0.633 12	0.741 11	0.405 12	0.337 13	0.560 10	0.060 5	0.794 9	0.517 14	0.732 12	0.274 6	0.647 13	0.948 8	0.459 17	0.849 12	0.864 10	0.306 9	0.648 6	0.282 15	0.717 12	0.496 7	0.624 10	0.533 9	0.363 10	0.821 5	0.573 15	0.009 15	0.411 4	0.593 9	0.000 1	0.841 6	0.873 10	0.704 15	0.242 5	0.000 7	0.495 12	0.041 17	0.487 9	0.304 9	0.439 14	0.613 14	0.133 18	0.055 17	0.853 9	0.634 13	0.075 13	0.791 6	0.601 10	0.574 17	0.483 14	0.669 12	0.217 11	0.000 3	0.198 8	0.518 7	0.782 15	0.345 12	0.914 7	0.273 6	0.193 3	0.598 15	0.440 10	0.499 9	0.570 2	0.000 1	0.381 12	0.775 4	0.000 4	0.063 6	0.000 1	0.000 6	0.712 9	0.752 14	0.507 13	0.512 17	0.158 17	0.036 14	0.773 2	0.361 12	0.000 3	0.000 8	0.000 1	0.032 7	0.000 4	0.032 16	0.651 16	0.000 1	0.000 11	0.000 10	0.831 6	0.595 4	0.273 17	0.229 8	0.200 10	0.191 11	0.000 15	0.425 9	0.233 13	0.125 12	0.000 5	0.279 5	0.213 16	0.003 1	0.608 4	0.044 13	0.138 9	0.321 13	0.408 12	0.593 11	0.198 6	0.205 9	0.139 14	0.000 1	0.614 8	0.609 7	0.838 5	0.000 1	0.014 7	0.260 7	0.080 13	0.010 5	0.000 11	0.136 14	0.136 5	0.047 6	0.000 11	0.000 1	0.787 3	0.797 11	0.000 1	0.354 15	0.000 1	0.372 5	0.357 15	0.000 1	0.507 17	0.000 1	0.000 1	0.121 12	0.423 4	0.903 9	0.028 5	0.089 8	0.000 1	0.252 4	0.000 1	0.072 17	0.465 13	0.340 13	0.189 17	0.020 17	0.011 17	0.320 17	0.606 8	0.060 3	0.000 1	0.496 10	0.000 2	0.000 2	0.070 10	0.618 14	0.000 3	0.000 1	0.000 1	0.139 12	0.047 4	0.000 3	0.558 9	0.000 1

IMFSegNet	0.334 10	0.532 14	0.251 12	0.179 8	0.799 12	0.683 9	0.940 11	0.555 9	0.631 13	0.740 12	0.406 11	0.336 14	0.560 10	0.062 4	0.795 7	0.518 13	0.733 11	0.274 6	0.646 14	0.947 9	0.458 18	0.848 14	0.862 11	0.305 10	0.649 5	0.284 14	0.713 13	0.495 8	0.626 9	0.527 10	0.363 10	0.820 6	0.574 14	0.010 14	0.411 4	0.597 7	0.000 1	0.842 5	0.873 10	0.704 15	0.246 4	0.000 7	0.495 12	0.041 17	0.486 10	0.305 8	0.444 13	0.604 16	0.134 17	0.055 17	0.852 10	0.633 14	0.076 10	0.792 5	0.612 9	0.573 18	0.484 13	0.668 13	0.216 13	0.000 3	0.197 9	0.518 7	0.784 14	0.344 13	0.908 8	0.283 5	0.190 4	0.599 14	0.439 11	0.496 11	0.569 3	0.000 1	0.392 10	0.776 3	0.000 4	0.064 5	0.000 1	0.000 6	0.710 10	0.756 13	0.508 12	0.512 17	0.159 16	0.034 15	0.773 2	0.363 11	0.000 3	0.000 8	0.000 1	0.032 7	0.000 4	0.029 17	0.648 17	0.000 1	0.000 11	0.000 10	0.830 7	0.595 4	0.274 16	0.228 9	0.206 9	0.188 13	0.000 15	0.425 9	0.237 12	0.123 13	0.000 5	0.277 6	0.214 15	0.003 1	0.610 3	0.044 13	0.124 10	0.320 15	0.408 12	0.594 10	0.196 8	0.213 8	0.139 14	0.000 1	0.615 7	0.618 6	0.839 4	0.000 1	0.014 7	0.260 7	0.080 13	0.025 2	0.000 11	0.139 13	0.135 6	0.035 7	0.000 11	0.000 1	0.793 2	0.799 10	0.000 1	0.357 14	0.000 1	0.369 6	0.359 14	0.000 1	0.512 16	0.000 1	0.000 1	0.120 13	0.424 3	0.903 9	0.027 6	0.091 7	0.000 1	0.245 5	0.000 1	0.073 16	0.457 15	0.340 13	0.191 16	0.021 16	0.009 18	0.322 16	0.608 7	0.060 3	0.000 1	0.494 11	0.000 2	0.000 2	0.068 11	0.624 12	0.000 3	0.000 1	0.000 1	0.139 12	0.047 4	0.000 3	0.561 8	0.000 1

PonderV2 ScanNet200	0.346 7	0.552 9	0.270 9	0.175 10	0.810 8	0.682 10	0.950 6	0.560 8	0.641 11	0.761 4	0.398 14	0.357 11	0.570 9	0.113 2	0.804 5	0.603 7	0.750 8	0.283 5	0.681 8	0.952 6	0.548 6	0.874 5	0.852 14	0.290 12	0.700 2	0.356 12	0.792 5	0.445 13	0.545 14	0.436 13	0.351 13	0.787 11	0.611 9	0.050 8	0.290 15	0.519 13	0.000 1	0.825 11	0.888 6	0.842 4	0.259 3	0.100 2	0.558 8	0.070 13	0.497 8	0.247 15	0.457 12	0.889 3	0.248 10	0.106 11	0.817 14	0.691 7	0.094 7	0.729 7	0.636 6	0.620 13	0.503 12	0.660 14	0.243 7	0.000 3	0.212 7	0.590 6	0.860 9	0.400 6	0.881 10	0.000 8	0.202 2	0.622 11	0.408 12	0.499 9	0.261 11	0.000 1	0.385 11	0.636 10	0.000 4	0.000 10	0.000 1	0.000 6	0.433 17	0.843 7	0.660 7	0.574 13	0.481 4	0.336 4	0.677 10	0.486 7	0.000 3	0.030 4	0.000 1	0.034 6	0.000 4	0.080 8	0.869 11	0.000 1	0.000 11	0.000 10	0.540 11	0.727 3	0.232 18	0.115 12	0.186 11	0.193 10	0.000 15	0.403 12	0.326 7	0.103 15	0.000 5	0.290 4	0.392 9	0.000 3	0.346 11	0.062 11	0.424 5	0.375 8	0.431 7	0.667 5	0.115 15	0.082 13	0.239 8	0.000 1	0.504 13	0.606 8	0.584 13	0.000 1	0.002 10	0.186 11	0.104 11	0.000 7	0.394 6	0.384 6	0.083 9	0.000 8	0.007 9	0.000 1	0.000 5	0.880 5	0.000 1	0.377 11	0.000 1	0.263 7	0.565 3	0.000 1	0.608 10	0.000 1	0.000 1	0.304 8	0.009 12	0.924 3	0.000 10	0.000 12	0.000 1	0.000 9	0.000 1	0.128 3	0.584 3	0.475 8	0.412 9	0.076 12	0.269 3	0.621 6	0.509 10	0.010 7	0.000 1	0.491 12	0.063 1	0.000 2	0.472 5	0.880 4	0.000 3	0.000 1	0.000 1	0.179 5	0.125 2	0.000 3	0.441 11	0.000 1
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
ALS-MinkowskiNet	0.414 3	0.610 3	0.322 3	0.271 2	0.852 1	0.710 3	0.973 1	0.572 5	0.719 4	0.795 2	0.477 7	0.506 3	0.601 4	0.000 14	0.804 5	0.646 4	0.804 3	0.344 2	0.777 1	0.984 1	0.671 1	0.879 3	0.936 1	0.342 5	0.632 8	0.449 4	0.817 3	0.475 10	0.723 2	0.798 1	0.376 9	0.832 3	0.693 1	0.031 9	0.564 1	0.510 14	0.000 1	0.893 3	0.905 1	0.672 17	0.314 1	0.000 7	0.718 1	0.153 3	0.542 2	0.397 4	0.726 3	0.752 9	0.252 9	0.226 3	0.916 2	0.800 1	0.047 17	0.807 4	0.769 1	0.709 3	0.630 4	0.769 1	0.217 11	0.000 3	0.285 1	0.598 5	0.846 11	0.535 1	0.956 5	0.000 8	0.137 11	0.784 3	0.464 8	0.463 14	0.230 13	0.000 1	0.598 4	0.662 9	0.000 4	0.087 2	0.000 1	0.135 3	0.900 3	0.780 12	0.703 3	0.741 1	0.571 2	0.149 10	0.697 8	0.646 2	0.000 3	0.076 3	0.000 1	0.025 11	0.000 4	0.106 6	0.981 1	0.000 1	0.043 8	0.113 4	0.888 3	0.248 16	0.404 4	0.252 7	0.314 1	0.220 8	0.245 2	0.466 7	0.366 3	0.159 2	0.000 5	0.149 8	0.690 2	0.000 3	0.531 6	0.253 3	0.285 6	0.460 1	0.440 6	0.813 1	0.230 3	0.283 6	0.159 12	0.000 1	0.728 1	0.666 5	0.958 1	0.000 1	0.021 5	0.252 9	0.118 6	0.000 7	0.445 4	0.223 11	0.285 1	0.194 3	0.390 2	0.000 1	0.475 4	0.842 8	0.000 1	0.455 4	0.000 1	0.250 8	0.458 9	0.000 1	0.865 2	0.000 1	0.000 1	0.635 1	0.359 6	0.972 1	0.087 4	0.447 1	0.000 1	0.000 9	0.000 1	0.129 2	0.532 7	0.446 9	0.503 5	0.071 14	0.135 13	0.699 4	0.717 3	0.097 2	0.000 1	0.665 2	0.000 2	0.000 2	1.000 1	0.752 6	0.000 3	0.000 1	0.000 1	0.142 9	0.200 1	0.259 1	1.000 1	0.000 1
Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum: ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding. CVPR 2025
L3DETR-ScanNet_200	0.336 9	0.533 12	0.279 7	0.155 11	0.801 10	0.689 5	0.946 7	0.539 12	0.660 8	0.759 5	0.380 15	0.333 15	0.583 5	0.000 14	0.788 11	0.529 11	0.740 9	0.261 13	0.679 10	0.940 13	0.525 11	0.860 9	0.883 8	0.226 14	0.613 10	0.397 7	0.720 11	0.512 5	0.565 13	0.620 4	0.417 5	0.775 14	0.629 7	0.158 2	0.298 13	0.579 11	0.000 1	0.835 7	0.883 7	0.927 2	0.114 11	0.079 4	0.511 11	0.073 12	0.508 6	0.312 7	0.629 7	0.861 5	0.192 15	0.098 14	0.908 4	0.636 12	0.032 18	0.563 18	0.514 16	0.664 7	0.505 11	0.697 7	0.225 10	0.000 3	0.264 2	0.411 13	0.860 9	0.321 14	0.960 4	0.058 7	0.109 14	0.776 4	0.526 6	0.557 4	0.303 10	0.000 1	0.339 13	0.712 7	0.000 4	0.014 8	0.000 1	0.000 6	0.638 13	0.856 5	0.641 8	0.579 12	0.107 18	0.119 12	0.661 12	0.416 8	0.000 3	0.000 8	0.000 1	0.007 17	0.000 4	0.067 10	0.910 6	0.000 1	0.000 11	0.000 10	0.463 12	0.448 8	0.294 15	0.324 1	0.293 3	0.211 9	0.108 8	0.448 8	0.068 18	0.141 7	0.000 5	0.330 3	0.699 1	0.000 3	0.256 12	0.192 7	0.000 15	0.355 9	0.418 8	0.209 18	0.146 13	0.679 3	0.101 18	0.000 1	0.503 14	0.687 2	0.671 9	0.000 1	0.000 12	0.174 12	0.117 7	0.000 7	0.122 8	0.515 2	0.104 7	0.259 2	0.312 3	0.000 1	0.000 5	0.765 13	0.000 1	0.369 13	0.000 1	0.183 9	0.422 12	0.000 1	0.646 5	0.000 1	0.000 1	0.565 2	0.001 15	0.125 18	0.010 8	0.002 11	0.000 1	0.487 1	0.000 1	0.075 14	0.548 5	0.420 10	0.233 15	0.082 8	0.138 12	0.430 13	0.427 14	0.000 12	0.000 1	0.549 7	0.000 2	0.000 2	0.074 9	0.409 17	0.000 3	0.000 1	0.000 1	0.152 7	0.051 3	0.000 3	0.598 7	0.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
PTv3 ScanNet200	0.393 4	0.592 4	0.330 2	0.216 4	0.851 2	0.687 7	0.971 2	0.586 3	0.755 1	0.752 8	0.505 2	0.404 8	0.575 6	0.000 14	0.848 2	0.616 5	0.761 4	0.349 1	0.738 3	0.978 4	0.546 7	0.860 9	0.926 3	0.346 4	0.654 3	0.384 8	0.828 1	0.523 4	0.699 4	0.583 7	0.387 8	0.822 4	0.688 2	0.118 4	0.474 3	0.603 5	0.000 1	0.832 9	0.903 2	0.753 10	0.140 10	0.000 7	0.650 4	0.109 6	0.520 4	0.457 3	0.497 11	0.871 4	0.281 5	0.192 6	0.887 5	0.748 3	0.168 2	0.727 8	0.733 2	0.740 1	0.644 2	0.714 5	0.190 14	0.000 3	0.256 3	0.449 11	0.914 1	0.514 2	0.759 16	0.337 2	0.172 6	0.692 8	0.617 3	0.636 1	0.325 8	0.000 1	0.641 2	0.782 2	0.000 4	0.065 4	0.000 1	0.000 6	0.842 5	0.903 2	0.661 5	0.662 4	0.612 1	0.405 2	0.731 5	0.566 5	0.000 3	0.000 8	0.000 1	0.017 15	0.301 1	0.088 7	0.941 4	0.000 1	0.077 4	0.000 10	0.717 9	0.790 2	0.310 13	0.026 18	0.264 5	0.349 1	0.220 5	0.397 13	0.366 3	0.115 14	0.000 5	0.337 1	0.463 6	0.000 3	0.531 6	0.218 5	0.593 2	0.455 2	0.469 3	0.708 4	0.210 5	0.592 4	0.108 17	0.000 1	0.728 1	0.682 3	0.671 9	0.000 1	0.000 12	0.407 1	0.136 5	0.022 3	0.575 2	0.436 4	0.259 3	0.428 1	0.048 6	0.000 1	0.000 5	0.879 6	0.000 1	0.480 3	0.000 1	0.133 10	0.597 2	0.000 1	0.690 3	0.000 1	0.000 1	0.009 17	0.000 16	0.921 4	0.000 10	0.151 6	0.000 1	0.000 9	0.000 1	0.109 8	0.494 12	0.622 2	0.394 10	0.073 13	0.141 7	0.798 2	0.528 9	0.026 5	0.000 1	0.551 6	0.000 2	0.000 2	0.134 8	0.717 9	0.000 3	0.000 1	0.000 1	0.188 4	0.000 7	0.000 3	0.791 3	0.000 1
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
OA-CNN-L_ScanNet200	0.333 12	0.558 6	0.269 10	0.124 14	0.821 6	0.703 4	0.946 7	0.569 6	0.662 5	0.748 10	0.487 4	0.455 5	0.572 8	0.000 14	0.789 10	0.534 10	0.736 10	0.271 9	0.713 5	0.949 7	0.498 15	0.877 4	0.860 12	0.332 7	0.706 1	0.474 3	0.788 7	0.406 14	0.637 7	0.495 12	0.355 12	0.805 8	0.592 13	0.015 13	0.396 8	0.602 6	0.000 1	0.799 12	0.876 8	0.713 14	0.276 2	0.000 7	0.493 14	0.080 10	0.448 15	0.363 6	0.661 5	0.833 7	0.262 7	0.125 8	0.823 13	0.665 10	0.076 10	0.720 9	0.557 11	0.637 10	0.517 10	0.672 11	0.227 9	0.000 3	0.158 12	0.496 9	0.843 12	0.352 11	0.835 14	0.000 8	0.103 15	0.711 6	0.527 5	0.526 7	0.320 9	0.000 1	0.568 7	0.625 12	0.067 1	0.000 10	0.000 1	0.001 5	0.806 7	0.836 8	0.621 11	0.591 9	0.373 9	0.314 5	0.668 11	0.398 10	0.003 2	0.000 8	0.000 1	0.016 16	0.024 2	0.043 14	0.906 7	0.000 1	0.052 7	0.000 10	0.384 13	0.330 13	0.342 9	0.100 13	0.223 8	0.183 14	0.112 7	0.476 6	0.313 8	0.130 10	0.196 4	0.112 12	0.370 11	0.000 3	0.234 13	0.071 10	0.160 7	0.403 7	0.398 14	0.492 15	0.197 7	0.076 14	0.272 6	0.000 1	0.200 17	0.560 10	0.735 8	0.000 1	0.000 12	0.000 13	0.110 9	0.002 6	0.021 9	0.412 5	0.000 13	0.000 8	0.000 11	0.000 1	0.000 5	0.794 12	0.000 1	0.445 6	0.000 1	0.022 11	0.509 7	0.000 1	0.517 14	0.000 1	0.000 1	0.001 18	0.245 8	0.915 6	0.024 7	0.089 8	0.000 1	0.262 3	0.000 1	0.103 11	0.524 8	0.392 12	0.515 4	0.013 18	0.251 4	0.411 14	0.662 5	0.001 11	0.000 1	0.473 13	0.000 2	0.000 2	0.150 6	0.699 10	0.000 3	0.000 1	0.000 1	0.166 6	0.000 7	0.024 2	0.000 12	0.000 1

AWCS	0.305 15	0.508 15	0.225 15	0.142 12	0.782 15	0.634 18	0.937 15	0.489 16	0.578 15	0.721 13	0.364 16	0.355 12	0.515 13	0.023 9	0.764 15	0.523 12	0.707 15	0.264 12	0.633 15	0.922 15	0.507 14	0.886 1	0.804 16	0.179 16	0.436 17	0.300 13	0.656 17	0.529 3	0.501 16	0.394 14	0.296 17	0.820 6	0.603 10	0.131 3	0.179 18	0.619 3	0.000 1	0.707 17	0.865 14	0.773 7	0.171 7	0.010 6	0.484 15	0.063 14	0.463 14	0.254 14	0.332 17	0.649 12	0.220 12	0.100 12	0.729 16	0.613 16	0.071 14	0.582 15	0.628 7	0.702 4	0.424 16	0.749 2	0.137 16	0.000 3	0.142 14	0.360 14	0.863 7	0.305 15	0.877 11	0.000 8	0.173 5	0.606 13	0.337 15	0.478 13	0.154 16	0.000 1	0.253 15	0.664 8	0.000 4	0.000 10	0.000 1	0.000 6	0.626 14	0.782 11	0.302 17	0.602 8	0.185 14	0.282 6	0.651 14	0.317 14	0.000 3	0.000 8	0.000 1	0.022 13	0.000 4	0.154 2	0.876 10	0.000 1	0.014 10	0.063 9	0.029 18	0.553 7	0.467 3	0.084 14	0.124 15	0.157 17	0.049 13	0.373 14	0.252 10	0.097 16	0.000 5	0.219 7	0.542 3	0.000 3	0.392 8	0.172 9	0.000 15	0.339 10	0.417 9	0.533 14	0.093 16	0.115 11	0.195 10	0.000 1	0.516 11	0.288 16	0.741 7	0.000 1	0.001 11	0.233 10	0.056 15	0.000 7	0.159 7	0.334 7	0.077 10	0.000 8	0.000 11	0.000 1	0.000 5	0.749 14	0.000 1	0.411 9	0.000 1	0.008 12	0.452 11	0.000 1	0.595 11	0.000 1	0.000 1	0.220 11	0.006 13	0.894 13	0.006 9	0.000 12	0.000 1	0.000 9	0.000 1	0.112 6	0.504 9	0.404 11	0.551 3	0.093 4	0.129 15	0.484 10	0.381 18	0.000 12	0.000 1	0.396 15	0.000 2	0.000 2	0.620 4	0.402 18	0.000 3	0.000 1	0.000 1	0.142 9	0.000 7	0.000 3	0.512 10	0.000 1
: Long-Tailed 3D Semantic Segmentation with Adaptive Weight Constraint and Sampling. ICRA 2024
PPT-SpUNet-F.T.	0.332 13	0.556 7	0.270 8	0.123 15	0.816 7	0.682 10	0.946 7	0.549 11	0.657 9	0.756 6	0.459 8	0.376 10	0.550 12	0.001 12	0.807 4	0.616 5	0.727 13	0.267 10	0.691 6	0.942 12	0.530 10	0.872 6	0.874 9	0.330 8	0.542 15	0.374 9	0.792 5	0.400 15	0.673 5	0.572 8	0.433 3	0.793 10	0.623 8	0.008 16	0.351 11	0.594 8	0.000 1	0.783 14	0.876 8	0.833 5	0.213 6	0.000 7	0.537 9	0.091 8	0.519 5	0.304 9	0.620 9	0.942 2	0.264 6	0.124 9	0.855 8	0.695 6	0.086 9	0.646 11	0.506 17	0.658 8	0.535 7	0.715 4	0.314 2	0.000 3	0.241 4	0.608 3	0.897 3	0.359 9	0.858 12	0.000 8	0.076 18	0.611 12	0.392 13	0.509 8	0.378 7	0.000 1	0.579 5	0.565 16	0.000 4	0.000 10	0.000 1	0.000 6	0.755 8	0.806 10	0.661 5	0.572 14	0.350 10	0.181 8	0.660 13	0.300 15	0.000 3	0.000 8	0.000 1	0.023 12	0.000 4	0.042 15	0.930 5	0.000 1	0.000 11	0.077 7	0.584 10	0.392 11	0.339 10	0.185 11	0.171 13	0.308 2	0.006 14	0.563 3	0.256 9	0.150 5	0.000 5	0.002 17	0.345 12	0.000 3	0.045 15	0.197 6	0.063 11	0.323 12	0.453 5	0.600 9	0.163 12	0.037 16	0.349 5	0.000 1	0.672 4	0.679 4	0.753 6	0.000 1	0.000 12	0.000 13	0.117 7	0.000 7	0.000 11	0.291 9	0.000 13	0.000 8	0.039 7	0.000 1	0.000 5	0.899 3	0.000 1	0.374 12	0.000 1	0.000 13	0.545 5	0.000 1	0.634 6	0.000 1	0.000 1	0.074 14	0.223 9	0.914 7	0.000 10	0.021 10	0.000 1	0.000 9	0.000 1	0.112 6	0.498 11	0.649 1	0.383 11	0.095 2	0.135 13	0.449 11	0.432 13	0.008 9	0.000 1	0.518 8	0.000 2	0.000 2	0.000 12	0.796 5	0.000 3	0.000 1	0.000 1	0.138 14	0.000 7	0.000 3	0.000 12	0.000 1
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormer ScanNet200	0.326 14	0.539 11	0.265 11	0.131 13	0.806 9	0.670 13	0.943 10	0.535 13	0.662 5	0.705 17	0.423 10	0.407 7	0.505 14	0.003 11	0.765 14	0.582 8	0.686 16	0.227 17	0.680 9	0.943 11	0.601 3	0.854 11	0.892 7	0.335 6	0.417 18	0.357 11	0.724 10	0.453 12	0.632 8	0.596 6	0.432 4	0.783 12	0.512 17	0.021 12	0.244 16	0.637 2	0.000 1	0.787 13	0.873 10	0.743 12	0.000 17	0.000 7	0.534 10	0.110 5	0.499 7	0.289 11	0.626 8	0.620 13	0.168 16	0.204 5	0.849 11	0.679 9	0.117 5	0.633 12	0.684 3	0.650 9	0.552 6	0.684 10	0.312 3	0.000 3	0.175 11	0.429 12	0.865 6	0.413 5	0.837 13	0.000 8	0.145 8	0.626 10	0.451 9	0.487 12	0.513 4	0.000 1	0.529 8	0.613 13	0.000 4	0.033 7	0.000 1	0.000 6	0.828 6	0.871 4	0.622 10	0.587 10	0.411 7	0.137 11	0.645 15	0.343 13	0.000 3	0.000 8	0.000 1	0.022 13	0.000 4	0.026 18	0.829 12	0.000 1	0.022 9	0.089 6	0.842 5	0.253 15	0.318 12	0.296 2	0.178 12	0.291 3	0.224 3	0.584 2	0.200 15	0.132 9	0.000 5	0.128 11	0.227 14	0.000 3	0.230 14	0.047 12	0.149 8	0.331 11	0.412 10	0.618 8	0.164 11	0.102 12	0.522 4	0.000 1	0.655 5	0.378 12	0.469 16	0.000 1	0.000 12	0.000 13	0.105 10	0.000 7	0.000 11	0.483 3	0.000 13	0.000 8	0.028 8	0.000 1	0.000 5	0.906 2	0.000 1	0.339 16	0.000 1	0.000 13	0.457 10	0.000 1	0.612 9	0.000 1	0.000 1	0.408 5	0.000 16	0.900 11	0.000 10	0.000 12	0.000 1	0.029 8	0.000 1	0.074 15	0.455 16	0.479 7	0.427 8	0.079 10	0.140 9	0.496 8	0.414 15	0.022 6	0.000 1	0.471 14	0.000 2	0.000 2	0.000 12	0.722 8	0.000 3	0.000 1	0.000 1	0.138 14	0.000 7	0.000 3	0.000 12	0.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
ODIN - Sem200	0.368 5	0.562 5	0.297 5	0.207 5	0.800 11	0.669 14	0.940 11	0.575 4	0.654 10	0.749 9	0.487 4	0.589 1	0.609 3	0.001 12	0.769 13	0.561 9	0.752 7	0.274 6	0.682 7	0.926 14	0.554 5	0.833 15	0.921 4	0.389 2	0.599 11	0.591 1	0.787 8	0.550 2	0.657 6	0.610 5	0.334 14	0.803 9	0.661 4	0.090 6	0.408 7	0.373 16	0.000 1	0.912 2	0.796 18	0.501 18	0.169 8	0.000 7	0.641 5	0.196 1	0.380 18	0.397 4	0.641 6	0.740 10	0.862 1	0.213 4	0.857 7	0.685 8	0.216 1	0.578 17	0.557 11	0.685 5	0.523 9	0.581 17	0.312 3	0.000 3	0.065 16	0.000 18	0.871 4	0.359 9	0.988 2	0.321 3	0.090 17	0.704 7	0.631 2	0.393 16	0.246 12	0.000 1	0.482 9	0.565 16	0.000 4	0.000 10	0.000 1	0.181 1	0.913 1	0.468 17	0.632 9	0.642 6	0.259 12	0.000 18	0.832 1	0.663 1	0.000 3	0.081 2	0.000 1	0.048 2	0.000 4	0.376 1	0.898 8	0.000 1	0.157 1	0.000 10	0.870 4	0.000 18	0.400 5	0.265 4	0.242 6	0.227 7	0.539 1	0.370 15	0.214 14	0.129 11	0.000 5	0.131 10	0.054 18	0.000 3	0.358 10	0.491 1	0.462 4	0.434 3	0.346 16	0.454 16	0.316 2	0.814 1	0.828 3	0.000 1	0.000 18	0.220 18	0.612 12	0.000 1	0.000 12	0.373 3	0.378 2	0.000 7	0.429 5	0.152 12	0.077 10	0.166 4	0.202 5	0.000 1	0.000 5	0.441 15	0.000 1	0.440 7	0.000 1	0.000 13	0.655 1	0.000 1	0.626 8	0.000 1	0.000 1	0.228 10	0.487 2	0.784 17	0.000 10	0.301 4	0.000 1	0.426 2	0.000 1	0.108 9	0.460 14	0.590 4	0.775 1	0.088 6	0.119 16	0.485 9	0.791 2	0.000 12	0.000 1	0.256 18	0.000 2	0.000 2	0.000 12	0.885 3	0.303 1	0.000 1	0.000 1	0.127 17	0.000 7	0.000 3	0.894 2	0.000 1
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024
LGround	0.272 16	0.485 16	0.184 16	0.106 16	0.778 16	0.676 12	0.932 16	0.479 18	0.572 16	0.718 15	0.399 13	0.265 16	0.453 17	0.085 3	0.745 16	0.446 16	0.726 14	0.232 16	0.622 16	0.901 16	0.512 12	0.826 16	0.786 17	0.178 17	0.549 13	0.277 16	0.659 16	0.381 16	0.518 15	0.295 18	0.323 15	0.777 13	0.599 11	0.028 10	0.321 12	0.363 17	0.000 1	0.708 16	0.858 15	0.746 11	0.063 15	0.022 5	0.457 16	0.077 11	0.476 12	0.243 16	0.402 15	0.397 18	0.233 11	0.077 16	0.720 18	0.610 17	0.103 6	0.629 13	0.437 18	0.626 12	0.446 15	0.702 6	0.190 14	0.005 1	0.058 17	0.322 15	0.702 17	0.244 16	0.768 15	0.000 8	0.134 13	0.552 16	0.279 17	0.395 15	0.147 17	0.000 1	0.207 16	0.612 14	0.000 4	0.000 10	0.000 1	0.000 6	0.658 12	0.566 15	0.323 16	0.525 16	0.229 13	0.179 9	0.467 18	0.154 17	0.000 3	0.002 6	0.000 1	0.051 1	0.000 4	0.127 4	0.703 13	0.000 1	0.000 11	0.216 1	0.112 17	0.358 12	0.547 2	0.187 10	0.092 17	0.156 18	0.055 11	0.296 16	0.252 10	0.143 6	0.000 5	0.014 14	0.398 7	0.000 3	0.028 17	0.173 8	0.000 15	0.265 17	0.348 15	0.415 17	0.179 9	0.019 17	0.218 9	0.000 1	0.597 9	0.274 17	0.565 14	0.000 1	0.012 9	0.000 13	0.039 17	0.022 3	0.000 11	0.117 16	0.000 13	0.000 8	0.000 11	0.000 1	0.000 5	0.324 17	0.000 1	0.384 10	0.000 1	0.000 13	0.251 18	0.000 1	0.566 12	0.000 1	0.000 1	0.066 15	0.404 5	0.886 14	0.199 2	0.000 12	0.000 1	0.059 7	0.000 1	0.136 1	0.540 6	0.127 18	0.295 12	0.085 7	0.143 6	0.514 7	0.413 16	0.000 12	0.000 1	0.498 9	0.000 2	0.000 2	0.000 12	0.623 13	0.000 3	0.000 1	0.000 1	0.132 16	0.000 7	0.000 3	0.000 12	0.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrain	0.249 18	0.455 18	0.171 17	0.079 18	0.766 18	0.659 16	0.930 18	0.494 15	0.542 18	0.700 18	0.314 18	0.215 18	0.430 18	0.121 1	0.697 18	0.441 17	0.683 17	0.235 15	0.609 18	0.895 17	0.476 16	0.816 17	0.770 18	0.186 15	0.634 7	0.216 18	0.734 9	0.340 17	0.471 17	0.307 17	0.293 18	0.591 18	0.542 16	0.076 7	0.205 17	0.464 15	0.000 1	0.484 18	0.832 17	0.766 8	0.052 16	0.000 7	0.413 17	0.059 15	0.418 16	0.222 17	0.318 18	0.609 15	0.206 14	0.112 10	0.743 15	0.625 15	0.076 10	0.579 16	0.548 14	0.590 15	0.371 17	0.552 18	0.081 17	0.003 2	0.142 14	0.201 17	0.638 18	0.233 17	0.686 18	0.000 8	0.142 9	0.444 18	0.375 14	0.247 18	0.198 15	0.000 1	0.128 18	0.454 18	0.019 2	0.097 1	0.000 1	0.000 6	0.553 15	0.557 16	0.373 14	0.545 15	0.164 15	0.014 17	0.547 17	0.174 16	0.000 3	0.002 6	0.000 1	0.037 4	0.000 4	0.063 11	0.664 15	0.000 1	0.000 11	0.130 2	0.170 15	0.152 17	0.335 11	0.079 15	0.110 16	0.175 15	0.098 9	0.175 18	0.166 16	0.045 18	0.207 3	0.014 14	0.465 5	0.000 3	0.001 18	0.001 18	0.046 12	0.299 16	0.327 17	0.537 13	0.033 17	0.012 18	0.186 11	0.000 1	0.205 16	0.377 13	0.463 17	0.000 1	0.058 3	0.000 13	0.055 16	0.041 1	0.000 11	0.105 17	0.000 13	0.000 8	0.000 11	0.000 1	0.000 5	0.398 16	0.000 1	0.308 18	0.000 1	0.000 13	0.319 16	0.000 1	0.543 13	0.000 1	0.000 1	0.062 16	0.004 14	0.862 16	0.000 10	0.000 12	0.000 1	0.000 9	0.000 1	0.123 5	0.316 17	0.225 16	0.250 14	0.094 3	0.180 5	0.332 15	0.441 12	0.000 12	0.000 1	0.310 17	0.000 2	0.000 2	0.000 12	0.592 15	0.000 3	0.000 1	0.000 1	0.203 3	0.000 7	0.000 3	0.000 12	0.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34D	0.253 17	0.463 17	0.154 18	0.102 17	0.771 17	0.650 17	0.932 16	0.483 17	0.571 17	0.710 16	0.331 17	0.250 17	0.492 15	0.044 6	0.703 17	0.419 18	0.606 18	0.227 17	0.621 17	0.865 18	0.531 9	0.771 18	0.813 15	0.291 11	0.484 16	0.242 17	0.612 18	0.282 18	0.440 18	0.351 16	0.299 16	0.622 17	0.593 12	0.027 11	0.293 14	0.310 18	0.000 1	0.757 15	0.858 15	0.737 13	0.150 9	0.164 1	0.368 18	0.084 9	0.381 17	0.142 18	0.357 16	0.720 11	0.214 13	0.092 15	0.724 17	0.596 18	0.056 15	0.655 10	0.525 15	0.581 16	0.352 18	0.594 16	0.056 18	0.000 3	0.014 18	0.224 16	0.772 16	0.205 18	0.720 17	0.000 8	0.159 7	0.531 17	0.163 18	0.294 17	0.136 18	0.000 1	0.169 17	0.589 15	0.000 4	0.000 10	0.000 1	0.002 4	0.663 11	0.466 18	0.265 18	0.582 11	0.337 11	0.016 16	0.559 16	0.084 18	0.000 3	0.000 8	0.000 1	0.036 5	0.000 4	0.125 5	0.670 14	0.000 1	0.102 3	0.071 8	0.164 16	0.406 10	0.386 7	0.046 17	0.068 18	0.159 16	0.117 6	0.284 17	0.111 17	0.094 17	0.000 5	0.000 18	0.197 17	0.000 3	0.044 16	0.013 16	0.002 14	0.228 18	0.307 18	0.588 12	0.025 18	0.545 5	0.134 16	0.000 1	0.655 5	0.302 15	0.282 18	0.000 1	0.060 2	0.000 13	0.035 18	0.000 7	0.000 11	0.097 18	0.000 13	0.000 8	0.005 10	0.000 1	0.000 5	0.096 18	0.000 1	0.334 17	0.000 1	0.000 13	0.274 17	0.000 1	0.513 15	0.000 1	0.000 1	0.280 9	0.194 10	0.897 12	0.000 10	0.000 12	0.000 1	0.000 9	0.000 1	0.108 9	0.279 18	0.189 17	0.141 18	0.059 15	0.272 2	0.307 18	0.445 11	0.003 10	0.000 1	0.353 16	0.000 2	0.026 1	0.000 12	0.581 16	0.001 2	0.000 1	0.000 1	0.093 18	0.002 6	0.000 3	0.000 12	0.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019

This table lists the benchmark results for the ScanNet200 3D semantic instance scenario.

Method	avg ap 25%	head ap 25%	common ap 25%	tail ap 25%	chair	table	door	couch	cabinet	shelf	desk	office chair	bed	pillow	sink	picture	window	toilet	bookshelf	monitor	curtain	book	coffee table	box	refrigerator	lamp	kitchen cabinet	towel	clothes	tv	nightstand	counter	dresser	stool	cushion	plant	ceiling	bathtub	end table	dining table	keyboard	bag	backpack	toilet paper	printer	tv stand	whiteboard	blanket	shower curtain	trash can	closet	stairs	microwave	stove	shoe	computer tower	bottle	bin	bench	board	washing machine	mirror	copier	basket	sofa chair	file cabinet	fan	laptop	shower	paper	person	paper towel dispenser	oven	blinds	rack	plate	blackboard	piano	suitcase	radiator	recycling bin	wardrobe	soap dispenser	telephone	bucket	clock	stand	light	laundry basket	pipe	clothes dryer	seat	speaker	column	bicycle	ladder	bathroom stall	shower wall	cup	jacket	storage bin	coffee maker	dishwasher	paper towel roll	machine	mat	windowsill	bar	toaster	bulletin board	ironing board	kitchen counter	doorframe	toilet paper dispenser	mini fridge	fire extinguisher	ball	hat	shower curtain rod	water cooler	paper cutter	tray	ledge	mouse	cart	storage container	scale	tissue box	light switch	power outlet	decoration	sign	projector	vacuum cleaner	candle	plunger	stuffed animal	headphones	dish rack	broom	range hood	water bottle	vent	shower floor	water pitcher	mailbox	bowl	paper bag	music stand	projector screen	laundry detergent	object	bathroom vanity	laundry hamper	bathroom stall door	ceiling light	trash bin	dumbbell	stair rail	tube	bathroom cabinet	closet rod	coffee kettle	structure	shower head	keyboard piano	case of water bottles	coat rack	storage organizer	folded chair	fire alarm	power strip	calendar	poster

DINO3D-Scannet200	0.511 4	0.685 4	0.484 1	0.331 3	0.892 3	0.821 2	0.890 3	0.907 6	0.629 2	0.468 2	0.905 1	0.001 8	1.000 1	0.816 1	0.968 2	0.863 4	0.811 5	0.944 9	0.596 10	0.960 6	0.778 4	0.532 3	0.719 10	0.481 1	0.851 9	0.803 1	0.873 1	0.850 1	0.421 1	0.806 5	0.856 7	0.111 6	0.761 3	0.677 1	0.000 5	0.944 1	0.861 5	1.000 1	0.220 2	0.708 4	0.856 6	0.220 1	0.864 1	0.579 1	1.000 1	0.764 11	0.655 4	0.327 5	1.000 1	0.911 4	0.244 1	0.667 10	0.923 1	0.857 1	0.702 1	0.889 4	0.496 2	0.048 2	0.355 11	0.494 2	0.794 5	0.798 3	1.000 1	0.042 5	0.264 8	0.817 7	0.683 2	0.675 1	0.167 5	0.000 6	0.700 1	0.824 4	0.417 7	0.000 6	0.000 5	0.764 1	0.000 8	0.500 3	0.699 3	0.789 7	0.079 9	0.472 2	0.845 4	0.930 1	0.000 4	0.667 1	0.000 5	0.412 3	0.000 2	0.163 6	1.000 1	0.000 6	0.419 1	0.500 2	1.000 1	0.777 2	0.576 3	0.867 4	0.378 2	0.334 5	0.028 3	0.764 4	0.542 2	0.559 1	0.000 5	0.800 1	0.528 5	0.000 4	0.346 6	0.714 1	0.125 5	0.756 5	0.754 6	0.866 5	0.750 1	0.600 3	0.500 1	0.500 1	1.000 1	0.667 1	1.000 1	0.000 1	0.298 1	0.000 5	0.250 6	0.194 2	0.000 8	0.850 4	0.000 5	0.250 5	0.595 1	0.000 3	0.063 1	0.860 5	0.000 1	0.714 2	0.000 1	0.944 1	0.750 1	0.000 1	0.974 2	0.000 1	0.000 1	0.857 4	0.655 4	0.719 10	0.250 3	0.014 7	0.000 1	1.000 1	0.000 1	0.142 4	0.744 3	0.200 8	0.746 3	0.436 3	0.221 7	0.798 1	0.500 8	0.011 5	0.000 1	0.385 8	0.000 1	0.000 2	0.000 6	0.792 7	0.663 1	0.000 6	0.000 2	0.200 5	0.000 5	0.000 4	1.000 1	0.000 2
Jinyuan Qu, Hongyang Li, Xingyu Chen, Shilong Liu, Yukai Shi, Tianhe Ren, Ruitao Jing and Lei Zhang: SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features. AAAI 2026
Volt-SPFormer	0.527 2	0.731 3	0.475 4	0.342 2	0.826 6	0.803 3	0.942 1	0.950 2	0.594 4	0.321 5	0.867 5	0.008 6	0.994 5	0.767 3	0.926 6	0.874 3	0.815 4	1.000 1	0.810 2	0.973 3	0.856 3	0.510 5	0.825 2	0.346 5	0.923 4	0.799 2	0.843 3	0.812 4	0.262 5	0.923 1	0.921 3	0.279 2	0.901 1	0.500 7	0.000 5	0.801 4	0.937 1	1.000 1	0.329 1	0.000 8	0.903 2	0.076 6	0.789 3	0.565 3	0.907 2	1.000 1	0.614 6	0.413 3	1.000 1	0.937 1	0.214 2	0.629 11	0.878 3	0.725 8	0.579 5	0.880 5	0.433 3	0.020 7	0.400 7	0.547 1	1.000 1	0.843 2	1.000 1	0.125 3	0.343 4	0.855 5	0.750 1	0.449 5	1.000 1	0.057 3	0.700 1	0.802 5	0.500 4	0.850 2	0.011 3	0.047 6	1.000 1	1.000 1	0.715 2	0.875 1	0.255 4	0.099 7	0.857 2	0.738 5	0.000 4	0.056 7	0.025 2	0.372 4	0.250 1	0.279 4	0.667 4	0.002 5	0.000 8	0.250 7	0.500 5	1.000 1	0.391 9	0.737 7	0.309 5	0.397 2	0.000 8	0.817 3	0.542 2	0.557 2	1.000 1	0.400 3	0.681 3	0.000 4	0.500 4	0.519 6	0.500 1	0.773 4	0.818 4	0.884 4	0.656 5	0.510 4	0.500 1	0.000 2	1.000 1	0.472 4	1.000 1	0.000 1	0.027 8	0.000 5	0.331 5	0.000 4	1.000 1	1.000 1	0.000 5	0.500 1	0.304 3	0.000 3	0.000 3	1.000 1	0.000 1	0.714 2	0.000 1	0.677 2	0.750 1	0.000 1	0.944 4	0.000 1	0.000 1	1.000 1	0.764 2	0.833 7	0.250 3	0.278 4	0.000 1	1.000 1	0.000 1	0.103 5	0.753 2	0.600 1	0.508 10	0.638 1	0.167 9	0.458 7	0.741 1	0.019 4	0.000 1	0.850 2	0.000 1	0.000 2	1.000 1	1.000 1	0.000 4	0.028 5	0.000 2	0.200 5	0.000 5	0.250 1	1.000 1	0.000 2
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
CompetitorFormer-200	0.469 5	0.676 5	0.401 6	0.296 5	0.901 2	0.729 7	0.885 5	0.829 9	0.380 8	0.320 6	0.873 4	0.400 1	0.998 3	0.711 4	0.980 1	0.847 5	0.854 1	1.000 1	0.696 6	0.989 2	0.759 6	0.556 2	0.806 4	0.240 6	0.918 5	0.650 5	0.818 6	0.629 6	0.224 6	0.839 2	0.933 1	0.247 3	0.711 4	0.540 5	0.021 4	0.543 10	0.900 4	0.903 10	0.118 5	0.125 6	0.916 1	0.057 8	0.692 5	0.410 9	0.747 4	1.000 1	0.664 3	0.424 2	0.933 9	0.839 7	0.207 3	0.703 9	0.748 8	0.700 9	0.610 3	0.869 6	0.270 7	0.068 1	0.878 1	0.244 7	0.794 5	0.698 6	1.000 1	0.000 6	0.325 6	0.770 10	0.482 4	0.452 4	0.025 11	0.015 5	0.293 6	0.829 3	0.663 3	1.000 1	0.013 2	0.385 3	0.250 7	0.500 3	0.491 8	0.850 4	0.214 8	0.131 6	0.878 1	0.617 6	0.000 4	0.085 6	0.009 4	0.278 7	0.000 2	0.295 3	1.000 1	0.000 6	0.160 4	0.500 2	0.500 5	0.342 9	0.534 4	0.901 2	0.474 1	0.222 7	0.011 6	0.724 5	0.542 2	0.125 4	0.083 4	0.336 7	0.500 6	0.083 3	0.565 3	0.587 4	0.500 1	0.827 3	0.829 3	0.750 6	0.508 6	0.018 8	0.500 1	0.000 2	1.000 1	0.667 1	1.000 1	0.000 1	0.173 2	0.286 2	0.500 1	0.000 4	0.125 7	0.489 6	0.000 5	0.500 1	0.269 4	0.000 3	0.050 2	0.834 6	0.000 1	0.581 7	0.000 1	0.677 2	0.467 10	0.000 1	0.886 6	0.000 1	0.000 1	0.820 6	0.144 9	1.000 1	1.000 1	0.103 5	0.000 1	1.000 1	0.000 1	0.175 2	0.410 8	0.330 7	0.701 5	0.257 4	0.292 5	0.285 10	0.574 7	0.157 1	0.000 1	0.863 1	0.000 1	0.056 1	0.250 5	1.000 1	0.000 4	0.109 2	0.000 2	0.400 2	0.025 4	0.000 4	1.000 1	0.000 2

ACGP-ScanNet200	0.544 1	0.737 2	0.483 2	0.381 1	0.801 9	0.859 1	0.921 2	0.912 5	0.536 6	0.483 1	0.846 7	0.036 4	0.996 4	0.699 5	0.955 3	0.929 1	0.842 2	1.000 1	0.834 1	0.993 1	0.858 2	0.517 4	0.838 1	0.396 4	0.968 2	0.682 4	0.860 2	0.840 2	0.292 4	0.800 6	0.825 8	0.213 4	0.573 6	0.552 4	0.000 5	0.738 5	0.918 2	1.000 1	0.064 9	1.000 1	0.897 3	0.184 2	0.747 4	0.424 7	0.835 3	1.000 1	0.718 2	0.388 4	1.000 1	0.915 3	0.140 6	0.721 8	0.851 4	0.778 2	0.666 2	0.902 3	0.405 4	0.035 4	0.511 6	0.307 6	0.903 3	0.680 7	1.000 1	0.708 2	0.403 2	0.931 3	0.658 3	0.510 3	1.000 1	0.089 1	0.671 3	0.765 6	1.000 1	0.528 3	0.006 4	0.204 4	1.000 1	0.500 3	0.759 1	0.854 3	0.590 1	0.461 3	0.850 3	0.767 4	0.042 2	0.086 5	0.000 5	0.462 2	0.000 2	0.349 1	1.000 1	0.007 4	0.341 2	0.444 6	1.000 1	0.759 3	0.371 10	0.867 3	0.367 4	0.462 1	0.000 8	0.903 2	0.443 7	0.500 3	0.250 3	0.600 2	0.809 2	0.500 1	0.944 1	0.540 5	0.000 6	0.944 1	0.905 1	0.944 3	0.677 3	0.637 2	0.500 1	0.000 2	1.000 1	0.507 3	1.000 1	0.000 1	0.140 3	0.000 5	0.500 1	0.000 4	1.000 1	1.000 1	0.143 4	0.146 7	0.396 2	0.000 3	0.000 3	1.000 1	0.000 1	0.782 1	0.000 1	0.638 4	0.677 6	0.000 1	0.974 2	0.000 1	0.000 1	0.959 3	0.903 1	0.884 6	1.000 1	0.472 2	0.000 1	0.250 7	0.000 1	0.185 1	0.718 4	0.391 6	0.604 6	0.189 5	0.206 8	0.500 5	0.637 4	0.064 3	0.000 1	0.667 4	0.000 1	0.000 2	1.000 1	1.000 1	0.050 3	0.000 6	0.000 2	0.317 4	0.144 2	0.024 3	1.000 1	0.008 1
Rongkun Yang, Ye Zhang, Longguang Wang, Zhiheng Fu, Lian Xu, Yulan Guo: Beyond Context Bias: Adaptive Instance Placement for Robust 3D Instance Segmentation.
AQ3D-ScanNet200	0.527 3	0.743 1	0.477 3	0.324 4	0.930 1	0.784 4	0.886 4	0.947 3	0.631 1	0.410 4	0.893 2	0.328 2	0.955 7	0.795 2	0.926 5	0.925 2	0.816 3	1.000 1	0.754 4	0.960 5	0.858 1	0.556 1	0.805 5	0.396 3	0.929 3	0.707 3	0.839 4	0.835 3	0.360 2	0.764 9	0.896 5	0.087 8	0.778 2	0.576 3	0.160 3	0.879 2	0.901 3	1.000 1	0.089 8	0.023 7	0.895 4	0.161 3	0.862 2	0.549 6	0.667 6	1.000 1	0.546 7	0.435 1	1.000 1	0.935 2	0.113 7	1.000 1	0.831 6	0.778 2	0.602 4	0.938 1	0.279 6	0.025 5	0.567 4	0.458 3	1.000 1	0.750 4	1.000 1	0.833 1	0.392 3	0.991 1	0.479 5	0.434 6	1.000 1	0.071 2	0.428 5	0.868 2	1.000 1	0.333 5	0.281 1	0.000 7	0.533 6	1.000 1	0.671 4	0.838 5	0.534 2	0.664 1	0.819 6	0.768 3	0.083 1	0.009 8	0.000 5	0.465 1	0.000 2	0.337 2	0.667 4	0.030 2	0.172 3	0.250 7	1.000 1	0.738 4	0.513 6	0.712 8	0.368 3	0.366 4	0.016 5	0.489 9	0.600 1	0.083 6	0.563 2	0.400 3	0.923 1	0.500 1	0.736 2	0.607 3	0.500 1	0.837 2	0.843 2	1.000 1	0.658 4	0.318 6	0.500 1	0.000 2	1.000 1	0.333 9	1.000 1	0.000 1	0.105 5	0.000 5	0.500 1	0.000 4	1.000 1	1.000 1	0.000 5	0.141 8	0.026 8	0.000 3	0.000 3	1.000 1	0.000 1	0.714 2	0.000 1	0.621 5	0.750 1	0.000 1	1.000 1	0.000 1	0.000 1	0.714 8	0.667 3	1.000 1	0.167 5	0.667 1	0.000 1	1.000 1	0.000 1	0.088 8	0.873 1	0.517 3	0.556 7	0.073 7	0.434 3	0.458 7	0.707 3	0.083 2	0.000 1	0.803 3	0.000 1	0.000 2	1.000 1	1.000 1	0.000 4	0.056 3	0.000 2	0.200 5	0.143 3	0.000 4	0.250 7	0.000 2

Mask3D Scannet200	0.445 7	0.653 6	0.392 7	0.254 7	0.844 5	0.746 6	0.818 7	0.888 8	0.556 5	0.262 7	0.890 3	0.025 5	1.000 1	0.608 7	0.930 4	0.694 8	0.721 6	0.930 11	0.686 8	0.966 4	0.615 10	0.440 6	0.725 8	0.201 7	0.890 7	0.414 10	0.827 5	0.552 7	0.158 11	0.806 4	0.924 2	0.042 9	0.512 8	0.412 11	0.226 1	0.604 8	0.830 6	1.000 1	0.125 4	0.792 2	0.815 7	0.097 5	0.648 6	0.551 5	0.354 10	1.000 1	0.630 5	0.241 7	1.000 1	0.853 5	0.204 4	0.974 5	0.841 5	0.778 2	0.358 8	0.927 2	0.300 5	0.045 3	0.640 2	0.363 4	0.745 7	0.710 5	1.000 1	0.000 6	0.330 5	0.943 2	0.315 8	0.600 2	1.000 1	0.027 4	0.080 11	0.556 11	0.500 4	0.409 4	0.000 5	0.194 5	1.000 1	0.500 3	0.493 7	0.761 8	0.053 10	0.042 8	0.780 8	0.454 7	0.009 3	0.333 3	0.050 1	0.321 5	0.000 2	0.084 7	0.552 8	0.008 3	0.027 6	0.750 1	0.500 5	0.442 7	0.657 1	0.765 6	0.120 8	0.183 9	0.021 4	1.000 1	0.510 6	0.016 7	0.000 5	0.400 3	0.619 4	0.000 4	0.396 5	0.290 7	0.000 6	0.741 6	0.699 7	1.000 1	0.260 7	0.017 9	0.125 11	0.000 2	0.792 9	0.399 8	1.000 1	0.000 1	0.049 7	0.265 3	0.063 9	0.000 4	1.000 1	0.335 7	0.381 1	0.500 1	0.250 5	0.004 2	0.000 3	0.727 7	0.000 1	0.538 8	0.000 1	0.188 6	0.677 6	0.000 1	0.930 5	0.000 1	0.000 1	0.966 2	0.391 5	0.908 5	0.000 6	0.028 6	0.000 1	1.000 1	0.000 1	0.152 3	0.451 6	0.458 4	0.971 1	0.573 2	0.606 1	0.167 11	0.625 5	0.004 6	0.000 1	0.058 11	0.000 1	0.000 2	1.000 1	1.000 1	0.000 4	0.056 3	0.000 2	0.200 5	0.309 1	0.000 4	1.000 1	0.000 2
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TD3D Scannet200	0.379 8	0.603 8	0.306 8	0.190 8	0.885 4	0.755 5	0.800 8	0.958 1	0.390 7	0.260 8	0.866 6	0.232 3	0.979 6	0.523 9	0.869 9	0.559 11	0.689 7	1.000 1	0.795 3	0.905 7	0.748 7	0.173 11	0.825 3	0.173 8	0.970 1	0.457 7	0.615 8	0.456 8	0.200 7	0.621 10	0.906 4	0.553 1	0.517 7	0.510 6	0.220 2	0.715 6	0.706 8	1.000 1	0.113 6	0.792 2	0.717 8	0.073 7	0.635 7	0.557 4	0.638 7	1.000 1	0.205 11	0.146 9	1.000 1	0.769 11	0.186 5	1.000 1	0.710 11	0.778 2	0.415 7	0.834 10	0.226 8	0.021 6	0.590 3	0.356 5	0.817 4	0.477 11	1.000 1	0.000 6	0.635 1	0.843 6	0.427 6	0.270 10	0.125 7	0.000 6	0.102 9	1.000 1	0.125 8	0.000 6	0.000 5	0.000 7	0.000 8	0.125 10	0.370 9	0.622 11	0.221 5	0.196 5	0.836 5	0.288 8	0.000 4	0.093 4	0.020 3	0.294 6	0.000 2	0.075 8	0.667 4	0.038 1	0.111 5	0.250 7	0.000 10	0.526 6	0.495 7	0.908 1	0.111 9	0.259 6	0.003 7	0.667 6	0.045 11	0.000 8	0.000 5	0.400 3	0.274 9	0.000 4	0.274 7	0.226 8	0.000 6	0.520 7	0.302 11	0.731 7	0.103 9	0.458 5	0.500 1	0.000 2	1.000 1	0.472 4	0.792 9	0.000 1	0.088 6	0.061 4	0.250 6	0.009 3	0.250 6	0.333 8	0.181 3	0.396 4	0.051 7	0.012 1	0.000 3	0.458 10	0.000 1	0.424 11	0.000 1	0.101 7	0.390 11	0.000 1	0.833 7	0.000 1	0.000 1	0.857 4	0.222 8	1.000 1	0.000 6	0.003 8	0.000 1	0.000 8	0.000 1	0.102 6	0.275 11	0.400 5	0.735 4	0.061 9	0.433 4	0.533 4	0.625 5	0.000 7	0.000 1	0.259 10	0.000 1	0.000 2	0.000 6	0.500 8	0.000 4	0.000 6	1.000 1	0.600 1	0.000 5	0.250 1	0.000 8	0.000 2
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
ODIN - Ins200	0.451 6	0.637 7	0.407 5	0.277 6	0.742 11	0.699 8	0.855 6	0.826 11	0.626 3	0.441 3	0.742 8	0.003 7	0.941 8	0.637 6	0.910 7	0.616 10	0.679 8	0.944 9	0.695 7	0.877 8	0.763 5	0.357 7	0.723 9	0.475 2	0.779 10	0.494 6	0.782 7	0.795 5	0.334 3	0.824 3	0.867 6	0.108 7	0.701 5	0.638 2	0.000 5	0.873 3	0.749 7	0.667 11	0.203 3	0.500 5	0.886 5	0.116 4	0.583 10	0.571 2	0.688 5	1.000 1	0.760 1	0.162 8	1.000 1	0.852 6	0.078 8	0.833 6	0.887 2	0.778 2	0.577 6	0.859 9	0.550 1	0.000 8	0.542 5	0.028 10	0.667 8	0.874 1	1.000 1	0.125 3	0.232 9	0.870 4	0.406 7	0.337 8	0.167 5	0.000 6	0.671 3	0.742 7	0.500 4	0.000 6	0.000 5	0.528 2	1.000 1	0.417 9	0.597 5	0.872 2	0.275 3	0.000 9	0.800 7	0.850 2	0.000 4	0.528 2	0.000 5	0.215 8	0.000 2	0.238 5	0.667 4	0.000 6	0.019 7	0.250 7	1.000 1	0.429 8	0.599 2	0.778 5	0.221 6	0.370 3	0.284 1	0.278 11	0.400 8	0.125 4	0.000 5	0.200 8	0.404 7	0.000 4	0.250 8	0.714 1	0.500 1	0.504 8	0.769 5	0.677 8	0.750 1	0.963 1	0.500 1	0.000 2	0.500 10	0.333 9	1.000 1	0.000 1	0.000 9	0.438 1	0.500 1	0.000 4	1.000 1	0.333 8	0.226 2	0.250 5	0.250 5	0.000 3	0.000 3	0.668 8	0.000 1	0.494 10	0.000 1	0.000 8	0.750 1	0.000 1	0.833 7	0.000 1	0.000 1	0.777 7	0.333 6	0.944 4	0.000 6	0.333 3	0.000 1	1.000 1	0.000 1	0.089 7	0.407 9	0.600 1	0.823 2	0.080 6	0.264 6	0.469 6	0.717 2	0.000 7	0.000 1	0.500 6	0.000 1	0.000 2	0.000 6	1.000 1	0.125 2	0.333 1	0.000 2	0.200 5	0.000 5	0.000 4	1.000 1	0.000 2

Minkowski 34D Inst.	0.280 10	0.488 10	0.192 11	0.124 10	0.804 8	0.518 10	0.772 11	0.904 7	0.337 11	0.191 10	0.443 10	0.000 9	0.861 10	0.502 10	0.868 10	0.669 9	0.587 10	0.997 7	0.467 11	0.828 11	0.732 8	0.342 9	0.745 7	0.119 11	0.918 5	0.404 11	0.419 10	0.398 9	0.172 9	0.618 11	0.743 10	0.167 5	0.077 11	0.500 7	0.000 5	0.568 9	0.506 11	1.000 1	0.044 10	0.000 8	0.502 10	0.010 10	0.593 9	0.284 11	0.305 11	0.903 10	0.213 10	0.142 10	0.981 8	0.790 10	0.000 10	1.000 1	0.715 10	0.538 11	0.346 10	0.830 11	0.067 9	0.000 8	0.400 7	0.074 9	0.333 10	0.551 8	1.000 1	0.000 6	0.292 7	0.777 9	0.118 11	0.317 9	0.100 9	0.000 6	0.191 8	0.648 9	0.000 9	0.000 6	0.000 5	0.000 7	0.000 8	0.500 3	0.213 11	0.825 6	0.021 11	0.333 4	0.648 11	0.098 10	0.000 4	0.000 9	0.000 5	0.077 9	0.000 2	0.000 11	0.150 11	0.000 6	0.000 8	0.000 11	0.225 8	0.281 10	0.447 8	0.000 11	0.090 10	0.148 10	0.000 8	0.479 10	0.542 2	0.000 8	0.000 5	0.200 8	0.131 11	0.000 4	0.250 8	0.000 10	0.000 6	0.159 11	0.396 10	0.677 8	0.021 10	0.000 10	0.500 1	0.000 2	1.000 1	0.442 7	0.125 11	0.000 1	0.000 9	0.000 5	0.000 10	0.333 1	0.000 8	0.528 5	0.000 5	0.000 9	0.000 9	0.000 3	0.000 3	0.200 11	0.000 1	0.516 9	0.000 1	0.000 8	0.500 8	0.000 1	0.833 7	0.000 1	0.000 1	0.286 10	0.083 10	0.750 8	0.000 6	0.000 9	0.000 1	0.000 8	0.000 1	0.059 11	0.445 7	0.200 8	0.535 9	0.070 8	0.167 9	0.385 9	0.375 9	0.000 7	0.000 1	0.333 9	0.000 1	0.000 2	0.000 6	0.500 8	0.000 4	0.000 6	0.000 2	0.200 5	0.000 5	0.000 4	0.000 8	0.000 2
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.	0.275 11	0.466 11	0.218 10	0.110 11	0.783 10	0.383 11	0.783 10	0.829 10	0.367 10	0.168 11	0.305 11	0.000 9	0.661 11	0.413 11	0.869 8	0.719 6	0.546 11	0.997 7	0.685 9	0.841 10	0.555 11	0.277 10	0.768 6	0.132 9	0.779 10	0.448 9	0.364 11	0.212 11	0.161 10	0.768 7	0.692 11	0.000 10	0.395 9	0.500 7	0.000 5	0.450 11	0.591 9	1.000 1	0.020 11	0.000 8	0.423 11	0.007 11	0.625 8	0.420 8	0.505 9	1.000 1	0.353 8	0.119 11	0.571 10	0.819 8	0.014 9	1.000 1	0.774 7	0.689 10	0.311 11	0.866 7	0.067 9	0.000 8	0.400 7	0.000 11	0.278 11	0.501 9	1.000 1	0.000 6	0.162 11	0.584 11	0.286 9	0.206 11	0.125 7	0.000 6	0.084 10	0.649 8	0.000 9	0.000 6	0.000 5	0.000 7	0.000 8	0.125 10	0.312 10	0.727 9	0.221 6	0.000 9	0.667 10	0.114 9	0.000 4	0.000 9	0.000 5	0.065 11	0.000 2	0.004 10	0.278 9	0.000 6	0.000 8	0.500 2	0.000 10	0.571 5	0.000 11	0.250 10	0.019 11	0.145 11	0.000 8	0.667 6	0.200 10	0.000 8	0.000 5	0.200 8	0.258 10	0.000 4	0.000 10	0.000 10	0.000 6	0.369 10	0.429 9	0.613 10	0.000 11	0.000 10	0.500 1	0.000 2	0.500 10	0.333 9	0.500 10	0.000 1	0.106 4	0.000 5	0.000 10	0.000 4	0.000 8	0.333 8	0.000 5	0.000 9	0.000 9	0.000 3	0.000 3	0.918 4	0.000 1	0.638 5	0.000 1	0.000 8	0.750 1	0.000 1	0.833 7	0.000 1	0.000 1	0.143 11	0.000 11	0.750 8	0.000 6	0.000 9	0.000 1	0.000 8	0.000 1	0.063 10	0.377 10	0.200 8	0.222 11	0.055 10	0.500 2	0.677 3	0.250 10	0.000 7	0.000 1	0.500 6	0.000 1	0.000 2	0.000 6	0.500 8	0.000 4	0.000 6	0.000 2	0.115 11	0.000 5	0.000 4	0.000 8	0.000 2
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.	0.314 9	0.529 9	0.225 9	0.155 9	0.810 7	0.625 9	0.798 9	0.940 4	0.372 9	0.217 9	0.484 9	0.000 9	0.927 9	0.528 8	0.826 11	0.694 7	0.605 9	1.000 1	0.731 5	0.846 9	0.716 9	0.350 8	0.589 11	0.123 10	0.857 8	0.457 8	0.578 9	0.376 10	0.183 8	0.765 8	0.800 9	0.000 10	0.278 10	0.500 7	0.000 5	0.659 7	0.569 10	1.000 1	0.093 7	0.000 8	0.539 9	0.010 9	0.578 11	0.378 10	0.571 8	1.000 1	0.337 9	0.252 6	0.530 11	0.814 9	0.000 10	0.744 7	0.743 9	0.746 7	0.346 9	0.863 8	0.067 9	0.000 8	0.400 7	0.167 8	0.667 8	0.488 10	1.000 1	0.000 6	0.208 10	0.783 8	0.166 10	0.375 7	0.071 10	0.000 6	0.200 7	0.607 10	0.000 9	0.000 6	0.000 5	0.000 7	1.000 1	0.500 3	0.517 6	0.716 10	0.221 6	0.000 9	0.706 9	0.085 11	0.000 4	0.000 9	0.000 5	0.077 10	0.000 2	0.063 9	0.278 9	0.000 6	0.000 8	0.500 2	0.083 9	0.181 11	0.515 5	0.286 9	0.144 7	0.219 8	0.042 2	0.582 8	0.400 8	0.000 8	0.000 5	0.000 11	0.305 8	0.000 4	0.000 10	0.036 9	0.000 6	0.413 9	0.500 8	0.533 11	0.250 8	0.200 7	0.500 1	0.000 2	1.000 1	0.472 4	1.000 1	0.000 1	0.000 9	0.000 5	0.250 6	0.000 4	0.000 8	0.333 8	0.000 5	0.000 9	0.000 9	0.000 3	0.000 3	0.600 9	0.000 1	0.594 6	0.000 1	0.000 8	0.500 8	0.000 1	0.647 11	0.000 1	0.000 1	0.429 9	0.333 6	0.500 11	0.000 6	0.000 9	0.000 1	0.000 8	0.000 1	0.069 9	0.696 5	0.050 11	0.556 7	0.031 11	0.042 11	0.750 2	0.250 10	0.000 7	0.000 1	0.630 5	0.000 1	0.000 2	0.000 6	0.500 8	0.000 4	0.000 6	0.000 2	0.400 2	0.000 5	0.000 4	0.000 8	0.000 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.

ScanNet Benchmark

This table lists the benchmark results for the 3D semantic label scenario.

Method	avg iou	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	floor	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	wall	window

Volt ScanNet	0.805 1	0.932 5	0.846 3	0.801 49	0.775 10	0.862 11	0.604 1	0.955 1	0.779 1	0.722 4	0.980 1	0.635 1	0.352 12	0.799 3	0.941 4	0.887 1	0.807 20	0.748 2	0.973 3	0.911 1	0.798 6
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
PTv3-PPT-ALC	0.798 2	0.911 12	0.812 24	0.854 8	0.770 13	0.856 16	0.555 18	0.943 2	0.660 27	0.735 2	0.979 2	0.606 8	0.492 1	0.792 5	0.934 5	0.841 3	0.819 6	0.716 10	0.947 11	0.906 2	0.822 1
Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum: ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding. CVPR 2025
DITR ScanNet	0.797 3	0.727 78	0.869 1	0.882 1	0.785 6	0.868 7	0.578 6	0.943 2	0.744 2	0.727 3	0.979 2	0.627 3	0.364 9	0.824 1	0.949 2	0.779 16	0.844 1	0.757 1	0.982 1	0.905 3	0.802 3
Karim Abou Zeid, Kadir Yilmaz, Daan de Geus, Alexander Hermans, David Adrian, Timm Linder, Bastian Leibe: DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation. 3DV 2026
PTv3 ScanNet	0.794 4	0.941 3	0.813 23	0.851 11	0.782 7	0.890 2	0.597 2	0.916 7	0.696 12	0.713 6	0.979 2	0.635 1	0.384 3	0.793 4	0.907 11	0.821 6	0.790 38	0.696 15	0.967 5	0.903 4	0.805 2
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
PonderV2	0.785 5	0.978 1	0.800 32	0.833 30	0.788 4	0.853 21	0.545 22	0.910 10	0.713 4	0.705 7	0.979 2	0.596 10	0.390 2	0.769 16	0.832 46	0.821 6	0.792 37	0.730 3	0.975 2	0.897 7	0.785 8
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
Mix3D	0.781 6	0.964 2	0.855 2	0.843 20	0.781 8	0.858 14	0.575 9	0.831 41	0.685 18	0.714 5	0.979 2	0.594 11	0.310 32	0.801 2	0.892 20	0.841 3	0.819 6	0.723 7	0.940 16	0.887 9	0.725 30
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3D	0.779 7	0.861 25	0.818 18	0.836 27	0.790 3	0.875 4	0.576 8	0.905 11	0.704 8	0.739 1	0.969 13	0.611 4	0.349 13	0.756 26	0.958 1	0.702 53	0.805 21	0.708 11	0.916 40	0.898 6	0.801 4

TTT-KD	0.773 8	0.646 99	0.818 18	0.809 42	0.774 11	0.878 3	0.581 4	0.943 2	0.687 16	0.704 8	0.978 7	0.607 7	0.336 21	0.775 12	0.912 9	0.838 5	0.823 4	0.694 16	0.967 5	0.899 5	0.794 7
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ResLFE_HDS	0.772 9	0.939 4	0.824 8	0.854 8	0.771 12	0.840 36	0.564 14	0.900 13	0.686 17	0.677 15	0.961 19	0.537 37	0.348 14	0.769 16	0.903 13	0.785 14	0.815 9	0.676 27	0.939 17	0.880 14	0.772 12

OctFormer	0.766 10	0.925 8	0.808 28	0.849 13	0.786 5	0.846 31	0.566 13	0.876 20	0.690 14	0.674 18	0.960 20	0.576 23	0.226 75	0.753 28	0.904 12	0.777 17	0.815 9	0.722 8	0.923 32	0.877 18	0.776 11
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
PPT-SpUNet-Joint	0.766 10	0.932 5	0.794 38	0.829 32	0.751 27	0.854 19	0.540 26	0.903 12	0.630 40	0.672 19	0.963 17	0.565 27	0.357 10	0.788 6	0.900 15	0.737 32	0.802 22	0.685 21	0.950 9	0.887 9	0.780 9
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OccuSeg+Semantic	0.764 12	0.758 63	0.796 36	0.839 24	0.746 31	0.907 1	0.562 15	0.850 32	0.680 20	0.672 19	0.978 7	0.610 5	0.335 23	0.777 10	0.819 50	0.847 2	0.830 3	0.691 18	0.972 4	0.885 11	0.727 28

CU-Hybrid Net	0.764 12	0.924 9	0.819 15	0.840 23	0.757 22	0.853 21	0.580 5	0.848 33	0.709 6	0.643 29	0.958 25	0.587 17	0.295 40	0.753 28	0.884 24	0.758 24	0.815 9	0.725 6	0.927 28	0.867 29	0.743 21

O-CNN	0.762 14	0.924 9	0.823 9	0.844 19	0.770 13	0.852 23	0.577 7	0.847 35	0.711 5	0.640 33	0.958 25	0.592 12	0.217 81	0.762 21	0.888 21	0.758 24	0.813 13	0.726 5	0.932 26	0.868 28	0.744 20
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
DiffSegNet	0.758 15	0.725 80	0.789 43	0.843 20	0.762 18	0.856 16	0.562 15	0.920 5	0.657 30	0.658 23	0.958 25	0.589 15	0.337 20	0.782 7	0.879 25	0.787 12	0.779 43	0.678 23	0.926 30	0.880 14	0.799 5

DTC	0.757 16	0.843 31	0.820 13	0.847 16	0.791 2	0.862 11	0.511 40	0.870 24	0.707 7	0.652 25	0.954 42	0.604 9	0.279 51	0.760 22	0.942 3	0.734 33	0.766 52	0.701 14	0.884 63	0.874 24	0.736 22

OA-CNN-L_ScanNet20	0.756 17	0.783 49	0.826 7	0.858 6	0.776 9	0.837 41	0.548 21	0.896 16	0.649 32	0.675 17	0.962 18	0.586 18	0.335 23	0.771 15	0.802 55	0.770 20	0.787 40	0.691 18	0.936 21	0.880 14	0.761 15

LSK3DNet	0.755 18	0.899 18	0.823 9	0.843 20	0.764 17	0.838 39	0.584 3	0.845 36	0.717 3	0.638 35	0.956 32	0.580 22	0.229 74	0.640 51	0.900 15	0.750 27	0.813 13	0.729 4	0.920 36	0.872 26	0.757 16
Tuo Feng, Wenguan Wang, Fan Ma, Yi Yang: LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels. CVPR 2024
ConDaFormer	0.755 18	0.927 7	0.822 11	0.836 27	0.801 1	0.849 26	0.516 37	0.864 29	0.651 31	0.680 14	0.958 25	0.584 20	0.282 48	0.759 24	0.855 36	0.728 35	0.802 22	0.678 23	0.880 68	0.873 25	0.756 18
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
PNE	0.755 18	0.786 47	0.835 6	0.834 29	0.758 20	0.849 26	0.570 11	0.836 40	0.648 33	0.668 21	0.978 7	0.581 21	0.367 7	0.683 41	0.856 34	0.804 9	0.801 26	0.678 23	0.961 7	0.889 8	0.716 37
P. Hermosilla: Point Neighborhood Embeddings.
PointTransformerV2	0.752 21	0.742 70	0.809 27	0.872 2	0.758 20	0.860 13	0.552 19	0.891 18	0.610 47	0.687 9	0.960 20	0.559 31	0.304 35	0.766 19	0.926 7	0.767 21	0.797 30	0.644 40	0.942 14	0.876 21	0.722 33
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net	0.752 21	0.906 16	0.793 40	0.802 48	0.689 48	0.825 54	0.556 17	0.867 25	0.681 19	0.602 52	0.960 20	0.555 33	0.365 8	0.779 9	0.859 31	0.747 28	0.795 34	0.717 9	0.917 39	0.856 37	0.764 14
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
PointConvFormer	0.749 23	0.793 45	0.790 41	0.807 44	0.750 29	0.856 16	0.524 33	0.881 19	0.588 60	0.642 32	0.977 11	0.591 13	0.274 54	0.781 8	0.929 6	0.804 9	0.796 31	0.642 41	0.947 11	0.885 11	0.715 38
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNet	0.749 23	0.909 14	0.818 18	0.811 40	0.752 25	0.839 38	0.485 55	0.842 37	0.673 22	0.644 28	0.957 30	0.528 44	0.305 34	0.773 13	0.859 31	0.788 11	0.818 8	0.693 17	0.916 40	0.856 37	0.723 32
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP	0.748 25	0.623 102	0.804 30	0.859 5	0.745 32	0.824 56	0.501 44	0.912 9	0.690 14	0.685 11	0.956 32	0.567 26	0.320 29	0.768 18	0.918 8	0.720 40	0.802 22	0.676 27	0.921 34	0.881 13	0.779 10

StratifiedFormer	0.747 26	0.901 17	0.803 31	0.845 18	0.757 22	0.846 31	0.512 39	0.825 44	0.696 12	0.645 27	0.956 32	0.576 23	0.262 65	0.744 34	0.861 30	0.742 30	0.770 50	0.705 12	0.899 52	0.860 34	0.734 23
Xin Lai, Jianhui Liu, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
VMNet	0.746 27	0.870 23	0.838 4	0.858 6	0.729 37	0.850 25	0.501 44	0.874 21	0.587 61	0.658 23	0.956 32	0.564 28	0.299 37	0.765 20	0.900 15	0.716 43	0.812 15	0.631 46	0.939 17	0.858 35	0.709 39
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
Virtual MVFusion	0.746 27	0.771 57	0.819 15	0.848 15	0.702 44	0.865 10	0.397 93	0.899 14	0.699 10	0.664 22	0.948 64	0.588 16	0.330 25	0.746 33	0.851 40	0.764 22	0.796 31	0.704 13	0.935 22	0.866 30	0.728 26
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
DiffSeg3D2	0.745 29	0.725 80	0.814 22	0.837 25	0.751 27	0.831 48	0.514 38	0.896 16	0.674 21	0.684 12	0.960 20	0.564 28	0.303 36	0.773 13	0.820 49	0.713 46	0.798 29	0.690 20	0.923 32	0.875 22	0.757 16

Retro-FPN	0.744 30	0.842 32	0.800 32	0.767 63	0.740 33	0.836 43	0.541 24	0.914 8	0.672 23	0.626 39	0.958 25	0.552 34	0.272 56	0.777 10	0.886 23	0.696 54	0.801 26	0.674 30	0.941 15	0.858 35	0.717 35
Peng Xiang, Xin Wen, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
ODIN	0.744 30	0.658 95	0.752 66	0.870 3	0.714 41	0.843 34	0.569 12	0.919 6	0.703 9	0.622 42	0.949 61	0.591 13	0.343 16	0.736 35	0.784 57	0.816 8	0.838 2	0.672 32	0.918 38	0.854 41	0.725 30
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024
EQ-Net	0.743 32	0.620 103	0.799 35	0.849 13	0.730 36	0.822 58	0.493 52	0.897 15	0.664 24	0.681 13	0.955 36	0.562 30	0.378 4	0.760 22	0.903 13	0.738 31	0.801 26	0.673 31	0.907 44	0.877 18	0.745 19
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT	0.742 33	0.860 26	0.765 57	0.819 35	0.769 15	0.848 28	0.533 28	0.829 42	0.663 25	0.631 38	0.955 36	0.586 18	0.274 54	0.753 28	0.896 18	0.729 34	0.760 58	0.666 34	0.921 34	0.855 39	0.733 24

LRPNet	0.742 33	0.816 40	0.806 29	0.807 44	0.752 25	0.828 52	0.575 9	0.839 39	0.699 10	0.637 36	0.954 42	0.520 48	0.320 29	0.755 27	0.834 44	0.760 23	0.772 47	0.676 27	0.915 42	0.862 32	0.717 35

LargeKernel3D	0.739 35	0.909 14	0.820 13	0.806 46	0.740 33	0.852 23	0.545 22	0.826 43	0.594 59	0.643 29	0.955 36	0.541 36	0.263 64	0.723 39	0.858 33	0.775 19	0.767 51	0.678 23	0.933 24	0.848 45	0.694 44
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN	0.736 36	0.776 53	0.790 41	0.851 11	0.754 24	0.854 19	0.491 54	0.866 27	0.596 58	0.686 10	0.955 36	0.536 38	0.342 17	0.624 58	0.869 27	0.787 12	0.802 22	0.628 47	0.927 28	0.875 22	0.704 41

MinkowskiNet	0.736 36	0.859 27	0.818 18	0.832 31	0.709 42	0.840 36	0.521 35	0.853 31	0.660 27	0.643 29	0.951 53	0.544 35	0.286 46	0.731 37	0.893 19	0.675 63	0.772 47	0.683 22	0.874 75	0.852 43	0.727 28
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA	0.731 38	0.890 19	0.837 5	0.864 4	0.726 38	0.873 5	0.530 32	0.824 45	0.489 95	0.647 26	0.978 7	0.609 6	0.336 21	0.624 58	0.733 65	0.758 24	0.776 45	0.570 73	0.949 10	0.877 18	0.728 26

MS-SFA-net	0.730 39	0.910 13	0.819 15	0.837 25	0.698 45	0.838 39	0.532 30	0.872 22	0.605 51	0.676 16	0.959 24	0.535 40	0.341 18	0.649 47	0.598 89	0.708 48	0.810 16	0.664 36	0.895 55	0.879 17	0.771 13

online3d	0.727 40	0.715 85	0.777 50	0.854 8	0.748 30	0.858 14	0.497 49	0.872 22	0.572 68	0.639 34	0.957 30	0.523 45	0.297 39	0.750 31	0.803 54	0.744 29	0.810 16	0.587 69	0.938 19	0.871 27	0.719 34

PointTransformer++	0.725 41	0.727 78	0.811 26	0.819 35	0.765 16	0.841 35	0.502 43	0.814 50	0.621 43	0.623 41	0.955 36	0.556 32	0.284 47	0.620 60	0.866 28	0.781 15	0.757 62	0.648 38	0.932 26	0.862 32	0.709 39

SparseConvNet	0.725 41	0.647 98	0.821 12	0.846 17	0.721 39	0.869 6	0.533 28	0.754 66	0.603 54	0.614 44	0.955 36	0.572 25	0.325 27	0.710 40	0.870 26	0.724 38	0.823 4	0.628 47	0.934 23	0.865 31	0.683 47

MatchingNet	0.724 43	0.812 42	0.812 24	0.810 41	0.735 35	0.834 45	0.495 51	0.860 30	0.572 68	0.602 52	0.954 42	0.512 50	0.280 50	0.757 25	0.845 42	0.725 37	0.780 42	0.606 57	0.937 20	0.851 44	0.700 43

INS-Conv-semantic	0.717 44	0.751 66	0.759 60	0.812 39	0.704 43	0.868 7	0.537 27	0.842 37	0.609 49	0.608 48	0.953 46	0.534 41	0.293 41	0.616 61	0.864 29	0.719 42	0.793 35	0.640 42	0.933 24	0.845 49	0.663 53

PointMetaBase	0.714 45	0.835 33	0.785 45	0.821 33	0.684 50	0.846 31	0.531 31	0.865 28	0.614 44	0.596 56	0.953 46	0.500 53	0.246 70	0.674 42	0.888 21	0.692 55	0.764 54	0.624 49	0.849 90	0.844 50	0.675 49

contrastBoundary	0.705 46	0.769 60	0.775 51	0.809 42	0.687 49	0.820 61	0.439 81	0.812 51	0.661 26	0.591 58	0.945 72	0.515 49	0.171 100	0.633 55	0.856 34	0.720 40	0.796 31	0.668 33	0.889 60	0.847 46	0.689 45
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic	0.703 47	0.774 55	0.800 32	0.793 54	0.760 19	0.847 30	0.471 59	0.802 54	0.463 102	0.634 37	0.968 15	0.491 56	0.271 58	0.726 38	0.910 10	0.706 49	0.815 9	0.551 85	0.878 69	0.833 51	0.570 85

RFCR	0.702 48	0.889 20	0.745 72	0.813 38	0.672 53	0.818 65	0.493 52	0.815 49	0.623 41	0.610 46	0.947 66	0.470 65	0.249 69	0.594 65	0.848 41	0.705 50	0.779 43	0.646 39	0.892 58	0.823 57	0.611 68
Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma: Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning. CVPR2021
One Thing One Click	0.701 49	0.825 37	0.796 36	0.723 70	0.716 40	0.832 47	0.433 83	0.816 47	0.634 38	0.609 47	0.969 13	0.418 91	0.344 15	0.559 77	0.833 45	0.715 44	0.808 19	0.560 79	0.902 49	0.847 46	0.680 48

JSENet	0.699 50	0.881 22	0.762 58	0.821 33	0.667 54	0.800 78	0.522 34	0.792 57	0.613 45	0.607 49	0.935 92	0.492 55	0.205 87	0.576 70	0.853 38	0.691 57	0.758 60	0.652 37	0.872 78	0.828 54	0.649 57
Zeyu HU, Mingmin Zhen, Xuyang BAI, Hongbo Fu, Chiew-lan Tai: JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. ECCV 2020
One-Thing-One-Click	0.693 51	0.743 69	0.794 38	0.655 93	0.684 50	0.822 58	0.497 49	0.719 76	0.622 42	0.617 43	0.977 11	0.447 78	0.339 19	0.750 31	0.664 82	0.703 52	0.790 38	0.596 62	0.946 13	0.855 39	0.647 58
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-II	0.692 52	0.732 74	0.772 52	0.786 55	0.677 52	0.866 9	0.517 36	0.848 33	0.509 88	0.626 39	0.952 51	0.536 38	0.225 77	0.545 83	0.704 72	0.689 60	0.810 16	0.564 78	0.903 48	0.854 41	0.729 25
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNet	0.690 53	0.884 21	0.754 64	0.795 52	0.647 61	0.818 65	0.422 85	0.802 54	0.612 46	0.604 50	0.945 72	0.462 68	0.189 95	0.563 76	0.853 38	0.726 36	0.765 53	0.632 45	0.904 46	0.821 60	0.606 72
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 54	0.704 87	0.741 76	0.754 67	0.656 56	0.829 50	0.501 44	0.741 71	0.609 49	0.548 66	0.950 57	0.522 47	0.371 5	0.633 55	0.756 60	0.715 44	0.771 49	0.623 50	0.861 86	0.814 63	0.658 54
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 55	0.866 24	0.748 69	0.819 35	0.645 63	0.794 81	0.450 71	0.802 54	0.587 61	0.604 50	0.945 72	0.464 67	0.201 90	0.554 79	0.840 43	0.723 39	0.732 73	0.602 60	0.907 44	0.822 59	0.603 75

DGNet	0.684 56	0.712 86	0.784 46	0.782 59	0.658 55	0.835 44	0.499 48	0.823 46	0.641 35	0.597 55	0.950 57	0.487 58	0.281 49	0.575 71	0.619 86	0.647 76	0.764 54	0.620 52	0.871 81	0.846 48	0.688 46

VACNN++	0.684 56	0.728 77	0.757 63	0.776 60	0.690 46	0.804 76	0.464 64	0.816 47	0.577 67	0.587 59	0.945 72	0.508 52	0.276 53	0.671 43	0.710 70	0.663 68	0.750 66	0.589 67	0.881 66	0.832 53	0.653 56

KP-FCNN	0.684 56	0.847 30	0.758 62	0.784 57	0.647 61	0.814 68	0.473 58	0.772 60	0.605 51	0.594 57	0.935 92	0.450 76	0.181 98	0.587 66	0.805 53	0.690 58	0.785 41	0.614 53	0.882 65	0.819 61	0.632 64
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
PointContrast_LA_SEM	0.683 59	0.757 64	0.784 46	0.786 55	0.639 65	0.824 56	0.408 88	0.775 59	0.604 53	0.541 68	0.934 96	0.532 42	0.269 60	0.552 80	0.777 58	0.645 79	0.793 35	0.640 42	0.913 43	0.824 56	0.671 50

Superpoint Network	0.683 59	0.851 29	0.728 80	0.800 51	0.653 58	0.806 74	0.468 61	0.804 52	0.572 68	0.602 52	0.946 69	0.453 75	0.239 73	0.519 88	0.822 47	0.689 60	0.762 57	0.595 64	0.895 55	0.827 55	0.630 65

VI-PointConv	0.676 61	0.770 59	0.754 64	0.783 58	0.621 69	0.814 68	0.552 19	0.758 64	0.571 71	0.557 64	0.954 42	0.529 43	0.268 62	0.530 86	0.682 76	0.675 63	0.719 76	0.603 59	0.888 61	0.833 51	0.665 52
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D	0.673 62	0.789 46	0.748 69	0.763 65	0.635 67	0.814 68	0.407 90	0.747 68	0.581 65	0.573 61	0.950 57	0.484 59	0.271 58	0.607 62	0.754 61	0.649 73	0.774 46	0.596 62	0.883 64	0.823 57	0.606 72

SALANet	0.670 63	0.816 40	0.770 55	0.768 62	0.652 59	0.807 73	0.451 68	0.747 68	0.659 29	0.545 67	0.924 102	0.473 64	0.149 110	0.571 73	0.811 52	0.635 83	0.746 67	0.623 50	0.892 58	0.794 77	0.570 85

O3DSeg	0.668 64	0.822 38	0.771 54	0.496 114	0.651 60	0.833 46	0.541 24	0.761 63	0.555 77	0.611 45	0.966 16	0.489 57	0.370 6	0.388 107	0.580 90	0.776 18	0.751 64	0.570 73	0.956 8	0.817 62	0.646 59

PointConv	0.666 65	0.781 50	0.759 60	0.699 78	0.644 64	0.822 58	0.475 57	0.779 58	0.564 74	0.504 85	0.953 46	0.428 85	0.203 89	0.586 68	0.754 61	0.661 69	0.753 63	0.588 68	0.902 49	0.813 65	0.642 60
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNL	0.666 65	0.703 88	0.781 48	0.751 69	0.655 57	0.830 49	0.471 59	0.769 61	0.474 98	0.537 70	0.951 53	0.475 63	0.279 51	0.635 53	0.698 75	0.675 63	0.751 64	0.553 84	0.816 97	0.806 67	0.703 42
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PPCNN++	0.663 67	0.746 67	0.708 83	0.722 71	0.638 66	0.820 61	0.451 68	0.566 104	0.599 56	0.541 68	0.950 57	0.510 51	0.313 31	0.648 49	0.819 50	0.616 88	0.682 91	0.590 66	0.869 82	0.810 66	0.656 55
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
MVF-GNN	0.658 68	0.558 110	0.751 67	0.655 93	0.690 46	0.722 103	0.453 67	0.867 25	0.579 66	0.576 60	0.893 115	0.523 45	0.293 41	0.733 36	0.571 92	0.692 55	0.659 98	0.606 57	0.875 72	0.804 69	0.668 51

DCM-Net	0.658 68	0.778 51	0.702 86	0.806 46	0.619 70	0.813 71	0.468 61	0.693 84	0.494 91	0.524 76	0.941 84	0.449 77	0.298 38	0.510 90	0.821 48	0.675 63	0.727 75	0.568 76	0.826 95	0.803 70	0.637 62
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN	0.656 70	0.698 90	0.743 74	0.650 95	0.564 87	0.820 61	0.505 42	0.758 64	0.631 39	0.479 89	0.945 72	0.480 61	0.226 75	0.572 72	0.774 59	0.690 58	0.735 71	0.614 53	0.853 89	0.776 92	0.597 78
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 71	0.752 65	0.734 78	0.664 91	0.583 82	0.815 67	0.399 92	0.754 66	0.639 36	0.535 72	0.942 82	0.470 65	0.309 33	0.665 44	0.539 94	0.650 72	0.708 81	0.635 44	0.857 88	0.793 79	0.642 60
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 72	0.778 51	0.731 79	0.699 78	0.577 83	0.829 50	0.446 73	0.736 72	0.477 97	0.523 78	0.945 72	0.454 72	0.269 60	0.484 97	0.749 64	0.618 86	0.738 69	0.599 61	0.827 94	0.792 82	0.621 67

MVPNet	0.641 73	0.831 34	0.715 81	0.671 88	0.590 78	0.781 87	0.394 94	0.679 86	0.642 34	0.553 65	0.937 89	0.462 68	0.256 66	0.649 47	0.406 107	0.626 84	0.691 88	0.666 34	0.877 70	0.792 82	0.608 71
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN	0.641 73	0.776 53	0.703 85	0.721 72	0.557 90	0.826 53	0.451 68	0.672 89	0.563 75	0.483 88	0.943 81	0.425 88	0.162 105	0.644 50	0.726 66	0.659 70	0.709 80	0.572 72	0.875 72	0.786 87	0.559 91

PointMRNet	0.640 75	0.717 84	0.701 87	0.692 81	0.576 84	0.801 77	0.467 63	0.716 77	0.563 75	0.459 95	0.953 46	0.429 84	0.169 102	0.581 69	0.854 37	0.605 89	0.710 78	0.550 86	0.894 57	0.793 79	0.575 83

FPConv	0.639 76	0.785 48	0.760 59	0.713 76	0.603 73	0.798 79	0.392 96	0.534 109	0.603 54	0.524 76	0.948 64	0.457 70	0.250 68	0.538 84	0.723 68	0.598 93	0.696 86	0.614 53	0.872 78	0.799 72	0.567 88
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net	0.638 77	0.797 44	0.769 56	0.641 100	0.590 78	0.820 61	0.461 65	0.537 108	0.637 37	0.536 71	0.947 66	0.388 98	0.206 86	0.656 45	0.668 80	0.647 76	0.732 73	0.585 70	0.868 83	0.793 79	0.473 111

PointSPNet	0.637 78	0.734 73	0.692 94	0.714 75	0.576 84	0.797 80	0.446 73	0.743 70	0.598 57	0.437 100	0.942 82	0.403 94	0.150 109	0.626 57	0.800 56	0.649 73	0.697 85	0.557 82	0.846 91	0.777 91	0.563 89

SConv	0.636 79	0.830 35	0.697 90	0.752 68	0.572 86	0.780 89	0.445 75	0.716 77	0.529 81	0.530 73	0.951 53	0.446 79	0.170 101	0.507 92	0.666 81	0.636 82	0.682 91	0.541 92	0.886 62	0.799 72	0.594 79

Supervoxel-CNN	0.635 80	0.656 96	0.711 82	0.719 73	0.613 71	0.757 98	0.444 78	0.765 62	0.534 80	0.566 62	0.928 100	0.478 62	0.272 56	0.636 52	0.531 96	0.664 67	0.645 102	0.508 100	0.864 85	0.792 82	0.611 68

joint point-based	0.634 81	0.614 104	0.778 49	0.667 90	0.633 68	0.825 54	0.420 86	0.804 52	0.467 100	0.561 63	0.951 53	0.494 54	0.291 43	0.566 74	0.458 102	0.579 99	0.764 54	0.559 81	0.838 92	0.814 63	0.598 77
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL	0.632 82	0.731 75	0.688 97	0.675 85	0.591 77	0.784 86	0.444 78	0.565 105	0.610 47	0.492 86	0.949 61	0.456 71	0.254 67	0.587 66	0.706 71	0.599 92	0.665 97	0.612 56	0.868 83	0.791 85	0.579 82

APCF-Net	0.631 83	0.742 70	0.687 99	0.672 86	0.557 90	0.792 84	0.408 88	0.665 91	0.545 78	0.508 82	0.952 51	0.428 85	0.186 96	0.634 54	0.702 73	0.620 85	0.706 82	0.555 83	0.873 76	0.798 74	0.581 81
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN	0.631 83	0.771 57	0.692 94	0.672 86	0.524 96	0.837 41	0.440 80	0.706 82	0.538 79	0.446 97	0.944 78	0.421 90	0.219 80	0.552 80	0.751 63	0.591 95	0.737 70	0.543 91	0.901 51	0.768 94	0.557 92

3DSM_DMMF	0.631 83	0.626 101	0.745 72	0.801 49	0.607 72	0.751 99	0.506 41	0.729 75	0.565 73	0.491 87	0.866 118	0.434 80	0.197 93	0.595 64	0.630 85	0.709 47	0.705 83	0.560 79	0.875 72	0.740 102	0.491 106

FusionAwareConv	0.630 86	0.604 106	0.741 76	0.766 64	0.590 78	0.747 100	0.501 44	0.734 73	0.503 90	0.527 74	0.919 106	0.454 72	0.323 28	0.550 82	0.420 106	0.678 62	0.688 89	0.544 89	0.896 54	0.795 76	0.627 66
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 87	0.800 43	0.625 110	0.719 73	0.545 93	0.806 74	0.445 75	0.597 99	0.448 105	0.519 80	0.938 88	0.481 60	0.328 26	0.489 96	0.499 101	0.657 71	0.759 59	0.592 65	0.881 66	0.797 75	0.634 63

SegGroup_sem	0.627 88	0.818 39	0.747 71	0.701 77	0.602 74	0.764 95	0.385 100	0.629 96	0.490 93	0.508 82	0.931 99	0.409 93	0.201 90	0.564 75	0.725 67	0.618 86	0.692 87	0.539 93	0.873 76	0.794 77	0.548 95
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv	0.625 89	0.830 35	0.694 92	0.757 66	0.563 88	0.772 93	0.448 72	0.647 94	0.520 84	0.509 81	0.949 61	0.431 83	0.191 94	0.496 94	0.614 87	0.647 76	0.672 95	0.535 96	0.876 71	0.783 88	0.571 84

Weakly-Openseg v3	0.625 89	0.924 9	0.787 44	0.620 102	0.555 92	0.811 72	0.393 95	0.666 90	0.382 113	0.520 79	0.953 46	0.250 117	0.208 84	0.604 63	0.670 78	0.644 80	0.742 68	0.538 94	0.919 37	0.803 70	0.513 103

dtc_net	0.625 89	0.703 88	0.751 67	0.794 53	0.535 94	0.848 28	0.480 56	0.676 88	0.528 82	0.469 92	0.944 78	0.454 72	0.004 122	0.464 99	0.636 84	0.704 51	0.758 60	0.548 88	0.924 31	0.787 86	0.492 105

HPEIN	0.618 92	0.729 76	0.668 101	0.647 97	0.597 76	0.766 94	0.414 87	0.680 85	0.520 84	0.525 75	0.946 69	0.432 81	0.215 82	0.493 95	0.599 88	0.638 81	0.617 107	0.570 73	0.897 53	0.806 67	0.605 74
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia: Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. ICCV 2019
SPH3D-GCN	0.610 93	0.858 28	0.772 52	0.489 115	0.532 95	0.792 84	0.404 91	0.643 95	0.570 72	0.507 84	0.935 92	0.414 92	0.046 119	0.510 90	0.702 73	0.602 91	0.705 83	0.549 87	0.859 87	0.773 93	0.534 98
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 94	0.760 62	0.667 102	0.649 96	0.521 97	0.793 82	0.457 66	0.648 93	0.528 82	0.434 102	0.947 66	0.401 95	0.153 108	0.454 100	0.721 69	0.648 75	0.717 77	0.536 95	0.904 46	0.765 95	0.485 107
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer	0.600 95	0.634 100	0.743 74	0.697 80	0.601 75	0.781 87	0.437 82	0.585 102	0.493 92	0.446 97	0.933 97	0.394 96	0.011 121	0.654 46	0.661 83	0.603 90	0.733 72	0.526 97	0.832 93	0.761 97	0.480 108

LAP-D	0.594 96	0.720 82	0.692 94	0.637 101	0.456 106	0.773 92	0.391 98	0.730 74	0.587 61	0.445 99	0.940 86	0.381 99	0.288 44	0.434 103	0.453 104	0.591 95	0.649 100	0.581 71	0.777 101	0.749 101	0.610 70

DPC	0.592 97	0.720 82	0.700 88	0.602 106	0.480 102	0.762 97	0.380 101	0.713 80	0.585 64	0.437 100	0.940 86	0.369 101	0.288 44	0.434 103	0.509 100	0.590 97	0.639 105	0.567 77	0.772 102	0.755 99	0.592 80
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet	0.589 98	0.766 61	0.659 105	0.683 83	0.470 105	0.740 102	0.387 99	0.620 98	0.490 93	0.476 90	0.922 104	0.355 104	0.245 71	0.511 89	0.511 99	0.571 100	0.643 103	0.493 104	0.872 78	0.762 96	0.600 76

ROSMRF	0.580 99	0.772 56	0.707 84	0.681 84	0.563 88	0.764 95	0.362 103	0.515 110	0.465 101	0.465 94	0.936 91	0.427 87	0.207 85	0.438 101	0.577 91	0.536 103	0.675 94	0.486 105	0.723 108	0.779 89	0.524 100

SD-DETR	0.576 100	0.746 67	0.609 114	0.445 120	0.517 98	0.643 114	0.366 102	0.714 79	0.456 103	0.468 93	0.870 117	0.432 81	0.264 63	0.558 78	0.674 77	0.586 98	0.688 89	0.482 106	0.739 106	0.733 104	0.537 97

SQN_0.1%	0.569 101	0.676 92	0.696 91	0.657 92	0.497 99	0.779 90	0.424 84	0.548 106	0.515 86	0.376 107	0.902 114	0.422 89	0.357 10	0.379 108	0.456 103	0.596 94	0.659 98	0.544 89	0.685 111	0.665 115	0.556 93

TextureNet	0.566 102	0.672 94	0.664 103	0.671 88	0.494 100	0.719 104	0.445 75	0.678 87	0.411 111	0.396 105	0.935 92	0.356 103	0.225 77	0.412 105	0.535 95	0.565 101	0.636 106	0.464 108	0.794 100	0.680 112	0.568 87
Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkerhouser, Matthias Niessner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. CVPR
DVVNet	0.562 103	0.648 97	0.700 88	0.770 61	0.586 81	0.687 108	0.333 107	0.650 92	0.514 87	0.475 91	0.906 110	0.359 102	0.223 79	0.340 110	0.442 105	0.422 114	0.668 96	0.501 101	0.708 109	0.779 89	0.534 98

Pointnet++ & Feature	0.557 104	0.735 72	0.661 104	0.686 82	0.491 101	0.744 101	0.392 96	0.539 107	0.451 104	0.375 108	0.946 69	0.376 100	0.205 87	0.403 106	0.356 110	0.553 102	0.643 103	0.497 102	0.824 96	0.756 98	0.515 101

GMLPs	0.538 105	0.495 115	0.693 93	0.647 97	0.471 104	0.793 82	0.300 111	0.477 111	0.505 89	0.358 109	0.903 113	0.327 107	0.081 116	0.472 98	0.529 97	0.448 112	0.710 78	0.509 98	0.746 104	0.737 103	0.554 94

PanopticFusion-label	0.529 106	0.491 116	0.688 97	0.604 105	0.386 111	0.632 115	0.225 122	0.705 83	0.434 108	0.293 116	0.815 120	0.348 105	0.241 72	0.499 93	0.669 79	0.507 105	0.649 100	0.442 114	0.796 99	0.602 120	0.561 90
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
subcloud_weak	0.516 107	0.676 92	0.591 117	0.609 103	0.442 107	0.774 91	0.335 106	0.597 99	0.422 110	0.357 110	0.932 98	0.341 106	0.094 115	0.298 112	0.528 98	0.473 110	0.676 93	0.495 103	0.602 117	0.721 107	0.349 120

Online SegFusion	0.515 108	0.607 105	0.644 108	0.579 108	0.434 108	0.630 116	0.353 104	0.628 97	0.440 106	0.410 103	0.762 123	0.307 109	0.167 103	0.520 87	0.403 108	0.516 104	0.565 110	0.447 112	0.678 112	0.701 109	0.514 102
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
3DMV, FTSDF	0.501 109	0.558 110	0.608 115	0.424 122	0.478 103	0.690 107	0.246 118	0.586 101	0.468 99	0.450 96	0.911 108	0.394 96	0.160 106	0.438 101	0.212 117	0.432 113	0.541 115	0.475 107	0.742 105	0.727 105	0.477 109

PCNN	0.498 110	0.559 109	0.644 108	0.560 110	0.420 110	0.711 106	0.229 120	0.414 112	0.436 107	0.352 112	0.941 84	0.324 108	0.155 107	0.238 117	0.387 109	0.493 106	0.529 116	0.509 98	0.813 98	0.751 100	0.504 104

3DMV	0.484 111	0.484 117	0.538 120	0.643 99	0.424 109	0.606 119	0.310 108	0.574 103	0.433 109	0.378 106	0.796 121	0.301 110	0.214 83	0.537 85	0.208 118	0.472 111	0.507 120	0.413 117	0.693 110	0.602 120	0.539 96
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 112	0.577 108	0.611 113	0.356 124	0.321 119	0.715 105	0.299 113	0.376 116	0.328 119	0.319 114	0.944 78	0.285 112	0.164 104	0.216 120	0.229 115	0.484 108	0.545 114	0.456 110	0.755 103	0.709 108	0.475 110
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 113	0.679 91	0.604 116	0.578 109	0.380 112	0.682 109	0.291 114	0.106 124	0.483 96	0.258 122	0.920 105	0.258 116	0.025 120	0.231 119	0.325 111	0.480 109	0.560 112	0.463 109	0.725 107	0.666 114	0.231 124
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproduce	0.446 114	0.474 118	0.623 111	0.463 118	0.366 114	0.651 112	0.310 108	0.389 115	0.349 117	0.330 113	0.937 89	0.271 114	0.126 112	0.285 113	0.224 116	0.350 119	0.577 109	0.445 113	0.625 115	0.723 106	0.394 116
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
SurfaceConvPF	0.442 115	0.505 114	0.622 112	0.380 123	0.342 117	0.654 111	0.227 121	0.397 114	0.367 115	0.276 118	0.924 102	0.240 118	0.198 92	0.359 109	0.262 113	0.366 116	0.581 108	0.435 115	0.640 114	0.668 113	0.398 115
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET2	0.442 115	0.548 112	0.548 119	0.597 107	0.363 115	0.628 117	0.300 111	0.292 119	0.374 114	0.307 115	0.881 116	0.268 115	0.186 96	0.238 117	0.204 119	0.407 115	0.506 121	0.449 111	0.667 113	0.620 119	0.462 114

Tangent Convolutions	0.438 117	0.437 120	0.646 107	0.474 116	0.369 113	0.645 113	0.353 104	0.258 121	0.282 123	0.279 117	0.918 107	0.298 111	0.147 111	0.283 114	0.294 112	0.487 107	0.562 111	0.427 116	0.619 116	0.633 118	0.352 119
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 118	0.525 113	0.647 106	0.522 111	0.324 118	0.488 123	0.077 125	0.712 81	0.353 116	0.401 104	0.636 125	0.281 113	0.176 99	0.340 110	0.565 93	0.175 123	0.551 113	0.398 118	0.370 125	0.602 120	0.361 118

SPLAT Net	0.393 119	0.472 119	0.511 121	0.606 104	0.311 121	0.656 110	0.245 119	0.405 113	0.328 119	0.197 123	0.927 101	0.227 120	0.000 124	0.001 126	0.249 114	0.271 122	0.510 117	0.383 120	0.593 118	0.699 110	0.267 122
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
ScanNet+FTSDF	0.383 120	0.297 122	0.491 122	0.432 121	0.358 116	0.612 118	0.274 116	0.116 123	0.411 111	0.265 119	0.904 112	0.229 119	0.079 117	0.250 115	0.185 120	0.320 120	0.510 117	0.385 119	0.548 119	0.597 123	0.394 116

MSSP2	0.347 121	0.278 123	0.687 99	0.466 117	0.316 120	0.316 125	0.308 110	0.374 117	0.317 121	0.357 110	0.905 111	0.141 124	0.000 124	0.003 125	0.000 125	0.000 125	0.508 119	0.365 122	0.481 122	0.649 117	0.466 113

PointNet++	0.339 122	0.584 107	0.478 123	0.458 119	0.256 123	0.360 124	0.250 117	0.247 122	0.278 124	0.261 121	0.677 124	0.183 121	0.117 113	0.212 121	0.145 122	0.364 117	0.346 125	0.232 125	0.548 119	0.523 124	0.252 123
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
GrowSP++	0.323 123	0.114 125	0.589 118	0.499 113	0.147 125	0.555 120	0.290 115	0.336 118	0.290 122	0.262 120	0.865 119	0.102 125	0.000 124	0.037 123	0.000 125	0.000 125	0.462 122	0.381 121	0.389 124	0.664 116	0.473 111

SSC-UNet	0.308 124	0.353 121	0.290 125	0.278 125	0.166 124	0.553 121	0.169 124	0.286 120	0.147 125	0.148 125	0.908 109	0.182 122	0.064 118	0.023 124	0.018 124	0.354 118	0.363 123	0.345 123	0.546 121	0.685 111	0.278 121

ScanNet	0.306 125	0.203 124	0.366 124	0.501 112	0.311 121	0.524 122	0.211 123	0.002 126	0.342 118	0.189 124	0.786 122	0.145 123	0.102 114	0.245 116	0.152 121	0.318 121	0.348 124	0.300 124	0.460 123	0.437 125	0.182 125
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 126	0.000 126	0.041 126	0.172 126	0.030 126	0.062 126	0.001 126	0.035 125	0.004 126	0.051 126	0.143 126	0.019 126	0.003 123	0.041 122	0.050 123	0.003 124	0.054 126	0.018 126	0.005 126	0.264 126	0.082 126

This table lists the benchmark results for the 3D semantic instance scenario.

Method	avg ap 25%	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	window

Volt-SPFormerScanNet	0.908 1	1.000 1	0.981 23	0.975 1	0.885 1	0.964 7	0.744 24	0.845 19	0.906 16	0.916 2	0.842 1	0.820 3	0.879 1	0.959 53	0.955 10	0.944 1	0.872 19	0.999 42	0.869 3
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
AQ3D	0.907 2	1.000 1	0.997 8	0.876 15	0.868 5	0.964 6	0.827 9	0.846 18	0.861 28	0.901 10	0.815 4	0.860 1	0.863 2	1.000 1	0.982 5	0.930 5	0.895 3	1.000 1	0.840 7

PointRel	0.901 3	1.000 1	0.978 27	0.928 4	0.879 2	0.962 9	0.882 5	0.749 42	0.947 3	0.912 3	0.802 5	0.753 23	0.820 4	1.000 1	0.984 4	0.919 8	0.894 4	1.000 1	0.815 18
: Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation. CVPR 2025
PointComp	0.897 4	1.000 1	0.998 6	0.864 21	0.869 4	0.969 4	0.830 8	0.783 34	0.905 17	0.894 12	0.791 6	0.834 2	0.769 15	1.000 1	0.982 6	0.920 7	0.868 22	1.000 1	0.872 2

Competitor-MAFT	0.896 5	1.000 1	1.000 1	0.872 19	0.847 13	0.967 5	0.955 1	0.778 36	0.901 19	0.919 1	0.784 9	0.812 5	0.770 14	1.000 1	0.949 11	0.865 39	0.868 21	1.000 1	0.840 8

OneFormer3D	0.896 5	1.000 1	1.000 1	0.913 7	0.858 8	0.951 15	0.786 17	0.837 21	0.916 14	0.908 5	0.778 12	0.803 9	0.750 17	1.000 1	0.976 8	0.926 6	0.882 8	0.995 52	0.849 4
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
MG-Former	0.887 7	1.000 1	0.991 17	0.837 29	0.801 29	0.935 24	0.887 4	0.857 11	0.946 4	0.891 13	0.748 22	0.805 8	0.739 19	1.000 1	0.993 2	0.809 63	0.876 16	1.000 1	0.842 6

DCD	0.885 8	1.000 1	0.933 45	0.856 25	0.832 18	0.959 11	0.930 2	0.858 10	0.802 42	0.859 21	0.767 13	0.796 13	0.709 24	1.000 1	0.971 9	0.871 33	0.904 1	1.000 1	0.874 1

KmaxOneFormerNet	0.883 9	1.000 1	1.000 1	0.798 44	0.848 12	0.971 2	0.853 7	0.903 3	0.827 36	0.910 4	0.748 21	0.809 7	0.724 21	1.000 1	0.980 7	0.855 45	0.844 28	1.000 1	0.832 9

InsSSM	0.883 9	1.000 1	0.996 9	0.800 43	0.865 6	0.960 10	0.808 14	0.852 16	0.940 7	0.899 11	0.785 8	0.810 6	0.700 26	1.000 1	0.912 24	0.851 48	0.895 2	0.997 45	0.827 11
Lei Yao, Yi Wang, Moyun Liu, Lap-Pui Chau: SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation. TCSVT, 2024
Competitor-SPFormer	0.881 11	1.000 1	1.000 1	0.845 27	0.854 9	0.962 8	0.714 27	0.857 12	0.904 18	0.902 8	0.782 11	0.789 16	0.662 32	1.000 1	0.988 3	0.874 30	0.886 7	0.997 45	0.847 5

VDG-Uni3DSeg	0.880 12	1.000 1	0.990 19	0.889 11	0.823 22	0.952 14	0.764 19	0.893 6	0.941 6	0.907 6	0.756 18	0.781 18	0.628 50	1.000 1	0.918 22	0.903 11	0.872 20	0.999 42	0.821 15

TST3D	0.879 13	1.000 1	0.994 12	0.921 6	0.807 28	0.939 21	0.771 18	0.887 7	0.923 12	0.862 20	0.722 27	0.768 20	0.756 16	1.000 1	0.910 35	0.904 10	0.836 31	0.999 42	0.824 13
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
SIM3D	0.878 14	1.000 1	0.972 29	0.863 22	0.817 26	0.952 13	0.821 12	0.783 32	0.890 22	0.902 9	0.735 25	0.797 11	0.799 11	1.000 1	0.931 19	0.893 17	0.853 26	1.000 1	0.792 22

EV3D	0.877 15	1.000 1	0.996 11	0.873 17	0.854 10	0.950 16	0.691 31	0.783 33	0.926 9	0.889 16	0.754 19	0.794 15	0.820 4	1.000 1	0.912 24	0.900 13	0.860 24	1.000 1	0.779 25

Spherical Mask(CtoF)	0.875 16	1.000 1	0.991 18	0.873 17	0.850 11	0.946 18	0.691 31	0.752 41	0.926 9	0.889 15	0.759 16	0.794 14	0.820 4	1.000 1	0.912 24	0.900 13	0.878 13	1.000 1	0.769 27

TD3D	0.875 16	1.000 1	0.976 28	0.877 14	0.783 35	0.970 3	0.889 3	0.828 22	0.945 5	0.803 28	0.713 29	0.720 30	0.709 23	1.000 1	0.936 17	0.934 4	0.873 17	1.000 1	0.791 23
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
Queryformer	0.874 18	1.000 1	0.978 26	0.809 41	0.876 3	0.936 23	0.702 28	0.716 47	0.920 13	0.875 19	0.766 14	0.772 19	0.818 8	1.000 1	0.995 1	0.916 9	0.892 5	1.000 1	0.767 28

SoftGroup++	0.874 18	1.000 1	0.972 30	0.947 2	0.839 16	0.898 32	0.556 46	0.913 2	0.881 25	0.756 30	0.828 3	0.748 25	0.821 3	1.000 1	0.937 16	0.937 2	0.887 6	1.000 1	0.821 14

UniPerception	0.870 20	1.000 1	0.998 6	0.770 54	0.835 17	0.972 1	0.762 20	0.754 40	0.928 8	0.845 22	0.790 7	0.819 4	0.717 22	0.981 49	0.915 23	0.890 19	0.878 11	1.000 1	0.809 19

Mask3D	0.870 20	1.000 1	0.985 21	0.782 51	0.818 25	0.938 22	0.760 21	0.749 42	0.923 11	0.877 18	0.760 15	0.785 17	0.820 4	1.000 1	0.912 24	0.864 41	0.878 13	0.983 58	0.825 12
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
ExtMask3D	0.867 22	1.000 1	1.000 1	0.756 59	0.816 27	0.940 20	0.795 15	0.760 39	0.862 27	0.888 17	0.739 23	0.763 21	0.774 12	1.000 1	0.929 20	0.878 27	0.879 10	1.000 1	0.819 17

SoftGroup	0.865 23	1.000 1	0.969 31	0.860 23	0.860 7	0.913 28	0.558 43	0.899 4	0.911 15	0.760 29	0.828 2	0.736 27	0.802 10	0.981 49	0.919 21	0.875 28	0.877 15	1.000 1	0.820 16
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
MAFT	0.860 24	1.000 1	0.990 19	0.810 40	0.829 19	0.949 17	0.809 13	0.688 53	0.836 33	0.904 7	0.751 20	0.796 12	0.741 18	1.000 1	0.864 45	0.848 50	0.837 29	1.000 1	0.828 10

IPCA-Inst	0.851 25	1.000 1	0.968 32	0.884 13	0.842 15	0.862 45	0.693 30	0.812 27	0.888 24	0.677 42	0.783 10	0.698 31	0.807 9	1.000 1	0.911 32	0.865 40	0.865 23	1.000 1	0.757 31

SPFormer	0.851 25	1.000 1	0.994 13	0.806 42	0.774 37	0.942 19	0.637 35	0.849 17	0.859 30	0.889 14	0.720 28	0.730 28	0.665 31	1.000 1	0.911 32	0.868 38	0.873 18	1.000 1	0.796 21
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
ODIN - Ins	0.847 27	1.000 1	0.951 38	0.834 34	0.828 20	0.875 37	0.871 6	0.767 37	0.821 38	0.816 25	0.690 36	0.800 10	0.771 13	1.000 1	0.912 24	0.891 18	0.821 32	0.886 74	0.713 38
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024
Mask3D_evaluation	0.843 28	1.000 1	0.955 37	0.847 26	0.795 31	0.932 25	0.750 23	0.780 35	0.891 21	0.818 24	0.737 24	0.633 40	0.703 25	1.000 1	0.902 37	0.870 34	0.820 33	0.941 66	0.805 20

ISBNet	0.835 29	1.000 1	0.950 39	0.731 61	0.819 23	0.918 26	0.790 16	0.740 44	0.851 32	0.831 23	0.661 38	0.742 26	0.650 35	1.000 1	0.937 15	0.814 62	0.836 30	1.000 1	0.765 29
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
SphereSeg	0.835 29	1.000 1	0.963 35	0.891 10	0.794 32	0.954 12	0.822 11	0.710 48	0.961 2	0.721 34	0.693 35	0.530 53	0.653 34	1.000 1	0.867 44	0.857 44	0.859 25	0.991 55	0.771 26

TopoSeg	0.832 31	1.000 1	0.981 24	0.933 3	0.819 24	0.826 54	0.524 52	0.841 20	0.811 39	0.681 41	0.759 17	0.687 32	0.727 20	0.981 49	0.911 32	0.883 23	0.853 27	1.000 1	0.756 32

GraphCut	0.832 31	1.000 1	0.922 54	0.724 63	0.798 30	0.902 31	0.701 29	0.856 14	0.859 29	0.715 35	0.706 30	0.748 24	0.640 46	1.000 1	0.934 18	0.862 42	0.880 9	1.000 1	0.729 34

PBNet	0.825 33	1.000 1	0.963 34	0.837 31	0.843 14	0.865 40	0.822 10	0.647 56	0.878 26	0.733 32	0.639 45	0.683 33	0.650 35	1.000 1	0.853 46	0.870 35	0.820 34	1.000 1	0.744 33
Weiguang Zhao, Yuyao Yan, Chaolong Yang, Jianan Ye, Xi Yang, Kaizhu Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
SSEC	0.820 34	1.000 1	0.983 22	0.924 5	0.826 21	0.817 57	0.415 61	0.899 5	0.793 44	0.673 43	0.731 26	0.636 38	0.653 33	1.000 1	0.939 14	0.804 65	0.878 12	1.000 1	0.780 24

DKNet	0.815 35	1.000 1	0.930 46	0.844 28	0.765 41	0.915 27	0.534 50	0.805 29	0.805 41	0.807 27	0.654 39	0.763 22	0.650 35	1.000 1	0.794 58	0.881 24	0.766 38	1.000 1	0.758 30
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN	0.806 36	1.000 1	0.992 15	0.789 46	0.723 54	0.891 33	0.650 34	0.810 28	0.832 34	0.665 45	0.699 33	0.658 34	0.700 26	1.000 1	0.881 39	0.832 54	0.774 36	0.997 45	0.613 55
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAIS	0.803 37	1.000 1	0.994 13	0.820 36	0.759 42	0.855 46	0.554 47	0.882 8	0.827 37	0.615 51	0.676 37	0.638 37	0.646 44	1.000 1	0.912 24	0.797 68	0.767 37	0.994 53	0.726 35
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask	0.803 37	1.000 1	0.962 36	0.874 16	0.707 58	0.887 36	0.686 33	0.598 61	0.961 1	0.715 36	0.694 34	0.469 58	0.700 26	1.000 1	0.912 24	0.902 12	0.753 43	0.997 45	0.637 49
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group	0.792 39	1.000 1	0.968 33	0.812 37	0.766 40	0.864 41	0.460 55	0.815 26	0.888 23	0.598 55	0.651 42	0.639 36	0.600 53	0.918 56	0.941 12	0.896 16	0.721 50	1.000 1	0.723 36
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained	0.791 40	1.000 1	0.996 9	0.829 35	0.767 39	0.889 35	0.600 38	0.819 25	0.770 49	0.594 56	0.620 49	0.541 50	0.700 26	1.000 1	0.941 12	0.889 21	0.763 39	1.000 1	0.526 65

SSTNet	0.789 41	1.000 1	0.840 68	0.888 12	0.717 55	0.835 50	0.717 26	0.684 54	0.627 64	0.724 33	0.652 41	0.727 29	0.600 53	1.000 1	0.912 24	0.822 57	0.757 42	1.000 1	0.691 43
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN	0.788 42	1.000 1	0.978 25	0.867 20	0.781 36	0.833 51	0.527 51	0.824 23	0.806 40	0.549 64	0.596 52	0.551 46	0.700 26	1.000 1	0.853 46	0.935 3	0.733 47	1.000 1	0.651 46

DANCENET	0.786 43	1.000 1	0.936 42	0.783 49	0.737 51	0.852 48	0.742 25	0.647 56	0.765 51	0.811 26	0.624 48	0.579 43	0.632 49	1.000 1	0.909 36	0.898 15	0.696 55	0.944 62	0.601 58

DENet	0.786 43	1.000 1	0.929 47	0.736 60	0.750 48	0.720 70	0.755 22	0.934 1	0.794 43	0.590 57	0.561 58	0.537 51	0.650 35	1.000 1	0.882 38	0.804 66	0.789 35	1.000 1	0.719 37

DualGroup	0.782 45	1.000 1	0.927 48	0.811 38	0.772 38	0.853 47	0.631 37	0.805 29	0.773 46	0.613 52	0.611 50	0.610 41	0.650 35	0.835 67	0.881 39	0.879 26	0.750 45	1.000 1	0.675 44

PointGroup	0.778 46	1.000 1	0.900 58	0.798 45	0.715 56	0.863 42	0.493 53	0.706 49	0.895 20	0.569 62	0.701 31	0.576 44	0.639 47	1.000 1	0.880 41	0.851 47	0.719 51	0.997 45	0.709 40
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
PE	0.776 47	1.000 1	0.900 59	0.860 23	0.728 53	0.869 38	0.400 62	0.857 13	0.774 45	0.568 63	0.701 32	0.602 42	0.646 44	0.933 55	0.843 49	0.890 20	0.691 59	0.997 45	0.709 39
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA	0.767 48	1.000 1	0.937 41	0.810 39	0.740 50	0.906 29	0.550 48	0.800 31	0.706 56	0.577 61	0.624 47	0.544 49	0.596 58	0.857 59	0.879 43	0.880 25	0.750 44	0.992 54	0.658 45

DD-UNet+Group	0.764 49	1.000 1	0.897 61	0.837 30	0.753 45	0.830 53	0.459 57	0.824 23	0.699 58	0.629 49	0.653 40	0.438 61	0.650 35	1.000 1	0.880 41	0.858 43	0.690 60	1.000 1	0.650 47
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
INS-Conv-instance	0.762 50	1.000 1	0.923 51	0.765 55	0.785 34	0.905 30	0.600 38	0.655 55	0.646 63	0.683 40	0.647 43	0.530 52	0.650 35	1.000 1	0.824 51	0.830 55	0.693 58	0.944 62	0.644 48

Dyco3D	0.761 51	1.000 1	0.935 43	0.893 9	0.752 47	0.863 43	0.600 38	0.588 62	0.742 53	0.641 47	0.633 46	0.546 48	0.550 60	0.857 59	0.789 60	0.853 46	0.762 40	0.987 56	0.699 41
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance	0.742 52	1.000 1	0.923 51	0.785 47	0.745 49	0.867 39	0.557 44	0.578 65	0.729 54	0.670 44	0.644 44	0.488 56	0.577 59	1.000 1	0.794 58	0.830 55	0.620 68	1.000 1	0.550 61
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg	0.739 53	1.000 1	0.899 60	0.759 57	0.753 46	0.823 55	0.282 67	0.691 52	0.658 61	0.582 60	0.594 53	0.547 47	0.628 50	1.000 1	0.795 57	0.868 37	0.728 49	1.000 1	0.692 42

3D-MPA	0.737 54	1.000 1	0.933 44	0.785 47	0.794 33	0.831 52	0.279 69	0.588 62	0.695 59	0.616 50	0.559 59	0.556 45	0.650 35	1.000 1	0.809 55	0.875 29	0.696 56	1.000 1	0.608 57
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML	0.731 55	1.000 1	0.992 15	0.779 53	0.609 67	0.746 65	0.308 66	0.867 9	0.601 67	0.607 53	0.539 62	0.519 54	0.550 60	1.000 1	0.824 51	0.869 36	0.729 48	1.000 1	0.616 53
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS	0.725 56	1.000 1	0.885 64	0.653 69	0.657 64	0.801 58	0.576 42	0.695 51	0.828 35	0.698 38	0.534 63	0.457 60	0.500 67	0.857 59	0.831 50	0.841 52	0.627 66	1.000 1	0.619 52

SSEN	0.724 57	1.000 1	0.926 49	0.781 52	0.661 62	0.845 49	0.596 41	0.529 68	0.764 52	0.653 46	0.489 69	0.461 59	0.500 67	0.859 58	0.765 61	0.872 32	0.761 41	1.000 1	0.577 59
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF	0.718 58	1.000 1	0.945 40	0.901 8	0.754 44	0.817 56	0.460 55	0.700 50	0.772 47	0.688 39	0.568 57	0.000 80	0.500 67	0.981 49	0.606 71	0.872 31	0.740 46	1.000 1	0.614 54
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Sparse R-CNN	0.714 59	1.000 1	0.926 50	0.694 64	0.699 60	0.890 34	0.636 36	0.516 69	0.693 60	0.743 31	0.588 54	0.369 65	0.601 52	0.594 73	0.800 56	0.886 22	0.676 61	0.986 57	0.546 62

SALoss-ResNet	0.695 60	1.000 1	0.855 66	0.579 74	0.589 69	0.735 68	0.484 54	0.588 62	0.856 31	0.634 48	0.571 56	0.298 66	0.500 67	1.000 1	0.824 51	0.818 58	0.702 54	0.935 69	0.545 63
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
PanopticFusion-inst	0.693 61	1.000 1	0.852 67	0.655 68	0.616 66	0.788 60	0.334 64	0.763 38	0.771 48	0.457 74	0.555 60	0.652 35	0.518 64	0.857 59	0.765 61	0.732 74	0.631 64	0.944 62	0.577 60
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Occipital-SCS	0.688 62	1.000 1	0.913 55	0.730 62	0.737 52	0.743 67	0.442 58	0.855 15	0.655 62	0.546 65	0.546 61	0.263 68	0.508 66	0.889 57	0.568 72	0.771 71	0.705 53	0.889 72	0.625 51

3D-BoNet	0.687 63	1.000 1	0.887 63	0.836 32	0.587 70	0.643 77	0.550 48	0.620 58	0.724 55	0.522 69	0.501 67	0.243 69	0.512 65	1.000 1	0.751 63	0.807 64	0.661 63	0.909 71	0.612 56
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
ClickSeg_Instance	0.685 64	1.000 1	0.818 70	0.600 72	0.715 57	0.795 59	0.557 44	0.533 67	0.591 69	0.601 54	0.519 65	0.429 63	0.638 48	0.938 54	0.706 66	0.817 60	0.624 67	0.944 62	0.502 67

PCJC	0.684 65	1.000 1	0.895 62	0.757 58	0.659 63	0.862 44	0.189 76	0.739 45	0.606 66	0.712 37	0.581 55	0.515 55	0.650 35	0.857 59	0.357 77	0.785 69	0.631 65	0.889 72	0.635 50

SPG_WSIS	0.678 66	1.000 1	0.880 65	0.836 32	0.701 59	0.727 69	0.273 71	0.607 60	0.706 57	0.541 67	0.515 66	0.174 72	0.600 53	0.857 59	0.716 65	0.846 51	0.711 52	1.000 1	0.506 66

One_Thing_One_Click	0.675 67	1.000 1	0.823 69	0.782 50	0.621 65	0.766 62	0.211 73	0.736 46	0.560 71	0.586 58	0.522 64	0.636 39	0.453 71	0.641 71	0.853 46	0.850 49	0.694 57	0.997 45	0.411 72
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_ins	0.637 68	1.000 1	0.923 53	0.593 73	0.561 71	0.746 66	0.143 78	0.504 70	0.766 50	0.485 72	0.442 70	0.372 64	0.530 63	0.714 68	0.815 54	0.775 70	0.673 62	1.000 1	0.431 71
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASC	0.615 69	0.711 76	0.802 71	0.540 75	0.757 43	0.777 61	0.029 79	0.577 66	0.588 70	0.521 70	0.600 51	0.436 62	0.534 62	0.697 69	0.616 70	0.838 53	0.526 70	0.980 59	0.534 64
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone	0.605 70	1.000 1	0.909 56	0.764 56	0.603 68	0.704 71	0.415 60	0.301 75	0.548 72	0.461 73	0.394 71	0.267 67	0.386 73	0.857 59	0.649 69	0.817 59	0.504 72	0.959 60	0.356 75

3D-SIS	0.558 71	1.000 1	0.773 72	0.614 71	0.503 74	0.691 73	0.200 74	0.412 71	0.498 75	0.546 66	0.311 76	0.103 76	0.600 53	0.857 59	0.382 74	0.799 67	0.445 78	0.938 68	0.371 73
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet	0.544 72	0.500 79	0.655 78	0.661 67	0.663 61	0.765 63	0.432 59	0.214 78	0.612 65	0.584 59	0.499 68	0.204 71	0.286 77	0.429 76	0.655 68	0.650 79	0.539 69	0.950 61	0.499 68

Hier3D	0.540 73	1.000 1	0.727 73	0.626 70	0.467 77	0.693 72	0.200 74	0.412 71	0.480 76	0.528 68	0.318 75	0.077 79	0.600 53	0.688 70	0.382 74	0.768 72	0.472 74	0.941 66	0.350 76
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class	0.497 74	0.250 81	0.902 57	0.689 65	0.540 72	0.747 64	0.276 70	0.610 59	0.268 80	0.489 71	0.348 72	0.000 80	0.243 80	0.220 79	0.663 67	0.814 61	0.459 76	0.928 70	0.496 69

Sem_Recon_ins	0.484 75	0.764 75	0.608 80	0.470 77	0.521 73	0.637 78	0.311 65	0.218 77	0.348 79	0.365 78	0.223 77	0.222 70	0.258 78	0.629 72	0.734 64	0.596 80	0.509 71	0.858 76	0.444 70

tmp	0.474 76	1.000 1	0.727 73	0.433 79	0.481 76	0.673 75	0.022 81	0.380 73	0.517 74	0.436 76	0.338 74	0.128 74	0.343 75	0.429 76	0.291 79	0.728 75	0.473 73	0.833 77	0.300 78

SemRegionNet-20cls	0.470 77	1.000 1	0.727 73	0.447 78	0.481 75	0.678 74	0.024 80	0.380 73	0.518 73	0.440 75	0.339 73	0.128 74	0.350 74	0.429 76	0.212 80	0.711 76	0.465 75	0.833 77	0.290 79

ASIS	0.422 78	0.333 80	0.707 76	0.676 66	0.401 78	0.650 76	0.350 63	0.177 79	0.594 68	0.376 77	0.202 78	0.077 78	0.404 72	0.571 74	0.197 81	0.674 78	0.447 77	0.500 80	0.260 80

3D-BEVIS	0.401 79	0.667 77	0.687 77	0.419 80	0.137 81	0.587 79	0.188 77	0.235 76	0.359 78	0.211 80	0.093 81	0.080 77	0.311 76	0.571 74	0.382 74	0.754 73	0.300 80	0.874 75	0.357 74
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet	0.390 80	0.556 78	0.636 79	0.493 76	0.353 79	0.539 80	0.271 72	0.160 80	0.450 77	0.359 79	0.178 79	0.146 73	0.250 79	0.143 80	0.347 78	0.698 77	0.436 79	0.667 79	0.331 77

MaskRCNN 2d->3d Proj	0.261 81	0.903 74	0.081 81	0.008 81	0.233 80	0.175 81	0.280 68	0.106 81	0.150 81	0.203 81	0.175 80	0.480 57	0.218 81	0.143 80	0.542 73	0.404 81	0.153 81	0.393 81	0.049 81

Method	avg iou	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	floor	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	wall	window

Virtual MVFusion (R)	0.745 1	0.861 1	0.839 1	0.881 1	0.672 2	0.512 1	0.422 19	0.898 1	0.723 1	0.714 1	0.954 2	0.454 1	0.509 1	0.773 1	0.895 1	0.756 1	0.820 1	0.653 1	0.935 1	0.891 1	0.728 1
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
BPNet_2D	0.670 2	0.822 3	0.795 3	0.836 2	0.659 3	0.481 2	0.451 15	0.769 5	0.656 3	0.567 4	0.931 3	0.395 6	0.390 6	0.700 4	0.534 4	0.689 11	0.770 2	0.574 3	0.865 11	0.831 3	0.675 6
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MVF-GNN（2D）	0.636 3	0.606 16	0.794 4	0.434 17	0.688 1	0.337 8	0.464 14	0.798 4	0.632 5	0.589 3	0.908 9	0.420 2	0.329 14	0.743 2	0.594 2	0.738 2	0.676 5	0.527 4	0.906 2	0.818 6	0.715 3

CU-Hybrid-2D Net	0.636 3	0.825 2	0.820 2	0.179 25	0.648 4	0.463 3	0.549 2	0.742 9	0.676 2	0.628 2	0.961 1	0.420 2	0.379 7	0.684 8	0.381 20	0.732 3	0.723 3	0.599 2	0.827 18	0.851 2	0.634 9

DVEFormer	0.626 5	0.616 12	0.764 6	0.690 5	0.583 11	0.322 14	0.540 3	0.809 3	0.593 7	0.502 12	0.900 14	0.374 9	0.433 3	0.660 9	0.528 5	0.665 19	0.663 6	0.491 9	0.871 10	0.810 9	0.705 4
Fischedick, S., Seichter, D., Stephan, B., Schmidt, R., Gross, H.-M.: DVEFormer: Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers. IROS 2025
CMX	0.613 6	0.681 9	0.725 13	0.502 13	0.634 6	0.297 19	0.478 12	0.830 2	0.651 4	0.537 7	0.924 4	0.375 7	0.315 16	0.686 7	0.451 15	0.714 5	0.543 23	0.504 6	0.894 7	0.823 5	0.688 5

DMMF_3d	0.605 7	0.651 10	0.744 11	0.782 3	0.637 5	0.387 4	0.536 5	0.732 10	0.590 8	0.540 6	0.856 23	0.359 12	0.306 17	0.596 16	0.539 3	0.627 22	0.706 4	0.497 8	0.785 23	0.757 21	0.476 24

EMSANet	0.600 8	0.716 4	0.746 10	0.395 20	0.614 9	0.382 5	0.523 6	0.713 13	0.571 12	0.503 10	0.922 7	0.404 5	0.397 5	0.655 10	0.400 17	0.626 23	0.663 6	0.469 14	0.900 4	0.827 4	0.577 16
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
MCA-Net	0.595 9	0.533 22	0.756 9	0.746 4	0.590 10	0.334 10	0.506 9	0.670 17	0.587 9	0.500 13	0.905 11	0.366 11	0.352 10	0.601 15	0.506 9	0.669 17	0.648 10	0.501 7	0.839 17	0.769 17	0.516 23

RFBNet	0.592 10	0.616 12	0.758 8	0.659 6	0.581 12	0.330 11	0.469 13	0.655 20	0.543 15	0.524 8	0.924 4	0.355 14	0.336 12	0.572 19	0.479 11	0.671 15	0.648 10	0.480 11	0.814 21	0.814 7	0.614 12

FAN_NV_RVC	0.586 11	0.510 23	0.764 6	0.079 28	0.620 8	0.330 11	0.494 10	0.753 7	0.573 10	0.556 5	0.884 18	0.405 4	0.303 18	0.718 3	0.452 14	0.672 14	0.658 8	0.509 5	0.898 5	0.813 8	0.727 2

WSGFormer	0.585 12	0.706 5	0.708 18	0.434 17	0.574 14	0.283 22	0.538 4	0.759 6	0.542 17	0.482 17	0.924 4	0.351 16	0.333 13	0.614 12	0.393 18	0.692 10	0.551 22	0.461 15	0.874 9	0.809 10	0.673 7

DCRedNet	0.583 13	0.682 8	0.723 14	0.542 12	0.510 22	0.310 16	0.451 15	0.668 18	0.549 14	0.520 9	0.920 8	0.375 7	0.446 2	0.528 22	0.417 16	0.670 16	0.577 19	0.478 12	0.862 12	0.806 11	0.628 11

MIX6D_RVC	0.582 14	0.695 6	0.687 19	0.225 23	0.632 7	0.328 13	0.550 1	0.748 8	0.623 6	0.494 16	0.890 16	0.350 17	0.254 25	0.688 6	0.454 13	0.716 4	0.597 18	0.489 10	0.881 8	0.768 18	0.575 17

SSMA	0.577 15	0.695 6	0.716 16	0.439 15	0.563 16	0.314 15	0.444 17	0.719 11	0.551 13	0.503 10	0.887 17	0.346 18	0.348 11	0.603 14	0.353 22	0.709 6	0.600 16	0.457 16	0.901 3	0.786 13	0.599 15
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DMMF	0.567 16	0.623 11	0.767 5	0.238 22	0.571 15	0.347 6	0.413 21	0.719 11	0.472 22	0.418 24	0.895 15	0.357 13	0.260 24	0.696 5	0.523 8	0.666 18	0.642 12	0.437 20	0.895 6	0.793 12	0.603 14

UNIV_CNP_RVC_UE	0.566 17	0.569 21	0.686 21	0.435 16	0.524 19	0.294 20	0.421 20	0.712 14	0.543 15	0.463 19	0.872 19	0.320 19	0.363 9	0.611 13	0.477 12	0.686 12	0.627 13	0.443 19	0.862 12	0.775 16	0.639 8

EMSAFormer	0.564 18	0.581 18	0.736 12	0.564 11	0.546 18	0.219 25	0.517 7	0.675 16	0.486 21	0.427 23	0.904 12	0.352 15	0.320 15	0.589 17	0.528 5	0.708 7	0.464 26	0.413 24	0.847 16	0.786 13	0.611 13
Söhnke Benedikt Fischedick, Daniel Seichter, Robin Schmidt, Leonard Rabes, and Horst-Michael Gross: Efficient Multi-Task Scene Analysis with RGB-D Transformers. IJCNN 2023
SN_RN152pyrx8_RVC	0.546 19	0.572 19	0.663 23	0.638 8	0.518 20	0.298 18	0.366 26	0.633 23	0.510 19	0.446 21	0.864 21	0.296 22	0.267 21	0.542 21	0.346 23	0.704 8	0.575 20	0.431 21	0.853 15	0.766 19	0.630 10

UDSSEG_RVC	0.545 20	0.610 15	0.661 24	0.588 9	0.556 17	0.268 23	0.482 11	0.642 22	0.572 11	0.475 18	0.836 25	0.312 20	0.367 8	0.630 11	0.189 25	0.639 21	0.495 25	0.452 17	0.826 19	0.756 22	0.541 19

segfomer with 6d	0.542 21	0.594 17	0.687 19	0.146 26	0.579 13	0.308 17	0.515 8	0.703 15	0.472 22	0.498 14	0.868 20	0.369 10	0.282 19	0.589 17	0.390 19	0.701 9	0.556 21	0.416 23	0.860 14	0.759 20	0.539 21

FuseNet	0.535 22	0.570 20	0.681 22	0.182 24	0.512 21	0.290 21	0.431 18	0.659 19	0.504 20	0.495 15	0.903 13	0.308 21	0.428 4	0.523 23	0.365 21	0.676 13	0.621 15	0.470 13	0.762 24	0.779 15	0.541 19
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++	0.503 23	0.613 14	0.722 15	0.418 19	0.358 28	0.337 8	0.370 25	0.479 26	0.443 24	0.368 26	0.907 10	0.207 25	0.213 27	0.464 26	0.525 7	0.618 24	0.657 9	0.450 18	0.788 22	0.721 25	0.408 27
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)	0.498 24	0.481 26	0.612 25	0.579 10	0.456 24	0.343 7	0.384 23	0.623 24	0.525 18	0.381 25	0.845 24	0.254 24	0.264 23	0.557 20	0.182 26	0.581 26	0.598 17	0.429 22	0.760 25	0.661 27	0.446 26
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVC	0.485 25	0.505 24	0.709 17	0.092 27	0.427 25	0.241 24	0.411 22	0.654 21	0.385 28	0.457 20	0.861 22	0.053 28	0.279 20	0.503 24	0.481 10	0.645 20	0.626 14	0.365 26	0.748 26	0.725 24	0.529 22
John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet	0.475 26	0.490 25	0.581 26	0.289 21	0.507 23	0.067 28	0.379 24	0.610 25	0.417 26	0.435 22	0.822 27	0.278 23	0.267 21	0.503 24	0.228 24	0.616 25	0.533 24	0.375 25	0.820 20	0.729 23	0.560 18

Enet (reimpl)	0.376 27	0.264 28	0.452 28	0.452 14	0.365 26	0.181 26	0.143 28	0.456 27	0.409 27	0.346 27	0.769 28	0.164 26	0.218 26	0.359 27	0.123 28	0.403 28	0.381 28	0.313 28	0.571 27	0.685 26	0.472 25
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
ScanNet (2d proj)	0.330 28	0.293 27	0.521 27	0.657 7	0.361 27	0.161 27	0.250 27	0.004 28	0.440 25	0.183 28	0.836 25	0.125 27	0.060 28	0.319 28	0.132 27	0.417 27	0.412 27	0.344 27	0.541 28	0.427 28	0.109 28
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17

Method	avg ap	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	window

EMSANet (Instance)	0.241 1	0.401 1	0.439 1	0.085 1	0.242 1	0.220 1	0.081 1	0.289 2	0.117 2	0.121 1	0.182 1	0.126 1	0.346 1	0.181 2	0.181 2	0.358 1	0.156 1	0.675 2	0.131 1
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
UniDet_RVC	0.205 2	0.381 2	0.323 3	0.037 3	0.226 3	0.177 3	0.063 2	0.277 3	0.120 1	0.067 3	0.131 3	0.074 3	0.317 2	0.080 3	0.235 1	0.289 3	0.141 3	0.678 1	0.080 3

FKNet	0.204 3	0.334 3	0.358 2	0.038 2	0.234 2	0.184 2	0.025 3	0.318 1	0.042 4	0.088 2	0.141 2	0.053 4	0.300 3	0.207 1	0.171 3	0.292 2	0.149 2	0.636 3	0.109 2

MaskRCNN_ScanNet	0.119 4	0.129 4	0.212 4	0.002 4	0.112 4	0.148 4	0.014 4	0.205 4	0.044 3	0.066 4	0.078 4	0.095 2	0.142 4	0.030 4	0.128 4	0.139 4	0.080 4	0.459 4	0.057 4
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17

Presenting the ScanNet200 Benchmark

ScanNet200 Benchmark

ScanNet200 3D Semantic Label Benchmark

ScanNet200 3D Semantic Instance Benchmark

ScanNet Benchmark

3D Semantic Label Benchmark

3D Semantic Instance Benchmark

2D Semantic Label Benchmark

2D Semantic Instance Benchmark

Scene Type Classification Benchmark

Method	avg recall	apartment	bathroom	bedroom / hotel	bookstore / library	conference room	copy/mail room	hallway	kitchen	laundry room	living room / lounge	misc	office	storage / basement / garage

LAST-PCL-type	0.780 1	0.250 3	1.000 1	1.000 1	1.000 1	1.000 1	1.000 1	0.500 2	1.000 1	0.500 2	0.889 1	0.000 2	1.000 1	1.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, and Jian Zhang: Language-Assisted 3D Scene Understanding. arxiv23.12
multi-task	0.700 2	0.500 1	1.000 1	0.882 3	0.500 3	1.000 1	1.000 1	0.500 2	1.000 1	1.000 1	0.778 2	0.000 2	0.938 2	0.000 3
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
3DASPP-SCE	0.691 3	0.500 1	0.938 3	0.824 4	1.000 1	1.000 1	0.500 3	1.000 1	0.857 3	0.500 2	0.556 4	0.000 2	0.812 3	0.500 2

SE-ResNeXt-SSMA	0.498 4	0.000 5	0.812 4	0.941 2	0.500 3	0.500 4	0.500 3	0.500 2	0.429 5	0.500 2	0.667 3	0.500 1	0.625 4	0.000 3
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
resnet50_scannet	0.353 5	0.250 3	0.812 4	0.529 5	0.500 3	0.500 4	0.000 5	0.500 2	0.571 4	0.000 5	0.556 4	0.000 2	0.375 5	0.000 3