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

ALS-MinkowskiNet	0.414 3	0.610 3	0.322 3	0.271 2	0.542 2	0.153 3	0.159 12	0.000 3	0.000 8	0.000 1	0.404 4	0.503 5	0.532 7	0.672 17	0.804 5	0.285 1	0.888 3	0.000 3	0.900 3	0.226 3	0.087 2	0.598 5	0.342 5	0.671 1	0.217 11	0.087 4	0.449 4	0.000 1	0.000 3	0.253 3	0.477 7	1.000 1	0.000 1	0.118 6	0.000 3	0.905 1	0.071 14	0.710 3	0.076 3	0.047 17	0.665 2	0.376 9	0.981 1	0.000 1	0.000 2	0.466 7	0.632 8	0.113 4	0.769 1	0.956 5	0.795 2	0.031 9	0.314 1	0.936 1	0.000 1	0.390 2	0.601 4	0.000 7	0.458 9	0.366 3	0.719 4	0.440 6	0.564 1	0.699 4	0.314 1	0.464 8	0.784 3	0.200 1	0.283 6	0.973 1	0.142 9	0.000 1	0.250 8	0.285 6	0.220 8	0.718 1	0.752 6	0.723 2	0.460 1	0.248 16	0.475 10	0.463 14	0.000 4	0.000 1	0.446 9	0.021 5	0.025 11	0.285 1	0.000 5	0.972 1	0.149 8	0.769 1	0.230 3	0.535 1	0.879 3	0.252 9	0.000 1	0.693 1	0.129 2	0.000 14	0.000 4	0.000 1	0.447 1	0.958 1	0.662 9	0.159 2	0.598 4	0.780 12	0.344 2	0.646 4	0.106 6	0.893 3	0.135 3	0.455 4	0.000 1	0.194 3	0.259 1	0.726 3	0.475 4	0.000 9	0.000 1	0.741 1	0.865 2	0.571 2	0.817 3	0.445 4	0.000 1	0.506 3	0.630 4	0.230 13	0.916 2	0.728 1	0.635 1	1.000 1	0.252 7	0.000 1	0.804 3	0.697 8	0.137 11	0.043 8	0.717 3	0.807 4	0.000 1	0.510 14	0.245 2	0.000 7	0.000 1	0.709 3	0.000 2	0.000 1	0.703 3	0.572 5	0.646 2	0.223 11	0.531 6	0.984 1	0.397 4	0.813 1	0.798 1	0.135 13	0.800 1	0.000 1	0.097 2	0.832 3	0.752 9	0.842 8	0.000 1	0.852 1	0.149 10	0.846 11	0.000 1	0.666 5	0.359 6	0.252 9	0.777 1	0.690 2
Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum: ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding. CVPR 2025
Volt	0.416 2	0.619 2	0.318 4	0.269 3	0.528 3	0.138 4	0.862 1	0.000 3	0.356 1	0.000 1	0.380 8	0.438 7	0.616 2	0.952 1	0.795 7	0.143 13	0.891 2	0.000 3	0.904 2	0.227 2	0.087 2	0.606 4	0.237 13	0.625 2	0.238 8	0.188 3	0.429 5	0.000 1	0.000 3	0.251 4	0.504 3	0.791 3	0.000 1	0.218 4	0.000 3	0.900 5	0.082 8	0.735 1	0.097 1	0.093 8	0.754 1	0.475 1	0.981 1	0.000 1	0.000 2	0.425 9	0.653 4	0.000 10	0.696 8	0.988 2	0.773 3	0.000 17	0.265 4	0.905 5	0.000 1	0.000 11	0.631 2	0.000 7	0.493 8	0.401 1	0.753 2	0.499 1	0.392 9	0.437 12	0.000 17	0.609 4	0.881 1	0.000 7	0.277 7	0.958 5	0.142 9	0.000 1	0.518 2	0.000 15	0.274 4	0.700 2	0.752 6	0.709 3	0.421 5	0.431 9	0.462 11	0.583 3	0.000 4	0.000 1	0.553 5	0.020 6	0.007 17	0.218 4	0.631 2	0.934 2	0.005 16	0.614 8	0.223 4	0.430 4	0.884 2	0.407 1	0.000 1	0.652 5	0.040 18	0.000 14	0.000 4	0.000 1	0.398 2	0.855 2	0.635 11	0.151 4	0.624 3	0.903 2	0.335 3	0.686 1	0.063 11	0.865 4	0.000 6	0.551 1	0.000 1	0.000 8	0.000 3	0.678 4	0.000 5	0.000 9	0.000 1	0.696 2	0.962 1	0.410 8	0.679 15	0.997 1	0.000 1	0.542 2	0.635 3	0.588 1	0.909 3	0.728 1	0.414 3	1.000 1	0.261 6	0.000 1	0.834 2	0.737 4	0.136 12	0.066 5	0.888 1	0.924 1	0.000 1	0.541 12	0.069 10	0.000 7	0.000 1	0.682 6	0.000 2	0.000 1	0.747 2	0.639 1	0.603 4	0.329 8	0.778 2	0.982 2	0.501 1	0.725 3	0.680 3	0.141 7	0.719 4	0.000 1	0.000 12	0.893 1	0.842 6	0.930 1	0.000 1	0.850 4	0.272 7	0.898 2	0.000 1	0.351 14	0.576 1	0.357 3	0.721 4	0.324 13
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
DITR	0.449 1	0.629 1	0.392 1	0.289 1	0.650 1	0.168 2	0.862 1	0.000 3	0.313 4	0.000 1	0.580 1	0.568 2	0.564 4	0.766 8	0.867 1	0.238 5	0.949 1	0.000 3	0.866 4	0.300 1	0.000 10	0.664 1	0.482 1	0.508 13	0.317 1	0.420 1	0.551 2	0.000 1	0.000 3	0.486 2	0.519 1	0.662 5	0.000 1	0.385 1	0.000 3	0.901 3	0.079 10	0.727 2	0.000 8	0.160 3	0.606 4	0.417 5	0.967 3	0.000 1	0.000 2	0.498 5	0.596 12	0.130 2	0.728 3	0.998 1	0.805 1	0.000 17	0.314 1	0.934 2	0.000 1	0.278 4	0.636 1	0.000 7	0.403 13	0.367 2	0.741 3	0.484 2	0.500 2	1.000 1	0.113 12	0.828 1	0.815 2	0.000 7	0.733 2	0.969 4	0.374 2	0.000 1	0.579 1	1.000 1	0.230 6	0.617 6	0.983 1	0.729 1	0.423 4	0.855 1	0.508 6	0.622 2	0.018 3	0.000 1	0.591 3	0.034 4	0.028 10	0.066 12	0.869 1	0.904 8	0.334 2	0.651 5	0.716 1	0.514 2	0.871 7	0.315 4	0.000 1	0.664 3	0.128 3	0.014 10	0.000 4	0.000 1	0.392 3	0.851 3	0.817 1	0.153 3	0.823 1	0.991 1	0.318 4	0.680 2	0.134 3	0.913 1	0.157 2	0.448 5	0.000 1	0.000 8	0.000 3	0.826 1	0.978 1	0.091 6	0.000 1	0.660 5	0.647 4	0.571 2	0.804 4	0.001 10	0.000 1	0.480 4	0.700 1	0.421 6	0.947 1	0.433 15	0.411 4	0.148 7	0.262 5	0.000 1	0.849 1	0.709 7	0.138 10	0.150 2	0.714 4	0.889 2	0.000 1	0.698 1	0.222 4	0.000 7	0.000 1	0.720 2	0.000 2	0.000 1	0.805 1	0.600 2	0.642 3	0.268 10	0.904 1	0.982 2	0.477 2	0.632 7	0.718 2	0.139 10	0.776 2	0.000 1	0.178 1	0.886 2	0.962 1	0.839 9	0.000 1	0.851 2	0.043 13	0.869 5	0.000 1	0.710 1	0.315 7	0.348 4	0.753 2	0.397 8
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 ScanNet200	0.393 4	0.592 4	0.330 2	0.216 4	0.520 4	0.109 6	0.108 17	0.000 3	0.337 2	0.000 1	0.310 13	0.394 10	0.494 12	0.753 10	0.848 2	0.256 3	0.717 9	0.000 3	0.842 5	0.192 6	0.065 4	0.449 11	0.346 4	0.546 7	0.190 14	0.000 10	0.384 8	0.000 1	0.000 3	0.218 5	0.505 2	0.791 3	0.000 1	0.136 5	0.000 3	0.903 2	0.073 13	0.687 7	0.000 8	0.168 2	0.551 6	0.387 8	0.941 4	0.000 1	0.000 2	0.397 13	0.654 3	0.000 10	0.714 5	0.759 16	0.752 8	0.118 4	0.264 5	0.926 3	0.000 1	0.048 6	0.575 6	0.000 7	0.597 2	0.366 3	0.755 1	0.469 3	0.474 3	0.798 2	0.140 10	0.617 3	0.692 8	0.000 7	0.592 4	0.971 2	0.188 4	0.000 1	0.133 10	0.593 2	0.349 1	0.650 4	0.717 9	0.699 4	0.455 2	0.790 2	0.523 4	0.636 1	0.301 1	0.000 1	0.622 2	0.000 12	0.017 15	0.259 3	0.000 5	0.921 4	0.337 1	0.733 2	0.210 5	0.514 2	0.860 9	0.407 1	0.000 1	0.688 2	0.109 8	0.000 14	0.000 4	0.000 1	0.151 6	0.671 9	0.782 2	0.115 14	0.641 2	0.903 2	0.349 1	0.616 5	0.088 7	0.832 9	0.000 6	0.480 3	0.000 1	0.428 1	0.000 3	0.497 11	0.000 5	0.000 9	0.000 1	0.662 4	0.690 3	0.612 1	0.828 1	0.575 2	0.000 1	0.404 8	0.644 2	0.325 8	0.887 5	0.728 1	0.009 17	0.134 8	0.026 18	0.000 1	0.761 4	0.731 5	0.172 6	0.077 4	0.528 9	0.727 8	0.000 1	0.603 5	0.220 5	0.022 3	0.000 1	0.740 1	0.000 2	0.000 1	0.661 5	0.586 3	0.566 5	0.436 4	0.531 6	0.978 4	0.457 3	0.708 4	0.583 7	0.141 7	0.748 3	0.000 1	0.026 5	0.822 4	0.871 4	0.879 6	0.000 1	0.851 2	0.405 2	0.914 1	0.000 1	0.682 3	0.000 16	0.281 5	0.738 3	0.463 6
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)
BFANet ScanNet200	0.360 6	0.553 8	0.293 6	0.193 6	0.483 11	0.096 7	0.266 7	0.000 3	0.000 8	0.000 1	0.298 14	0.255 13	0.661 1	0.810 6	0.810 3	0.194 10	0.785 8	0.000 3	0.000 18	0.161 7	0.000 10	0.494 10	0.382 3	0.574 4	0.258 5	0.000 10	0.372 10	0.000 1	0.000 3	0.043 15	0.436 9	0.000 12	0.000 1	0.239 3	0.000 3	0.901 3	0.105 1	0.689 5	0.025 5	0.128 4	0.614 3	0.436 2	0.493 18	0.000 1	0.000 2	0.526 4	0.546 14	0.109 5	0.651 15	0.953 6	0.753 7	0.101 5	0.143 14	0.897 6	0.000 1	0.431 1	0.469 16	0.000 7	0.522 6	0.337 6	0.661 7	0.459 4	0.409 6	0.666 5	0.102 14	0.508 7	0.757 5	0.000 7	0.060 15	0.970 3	0.497 1	0.000 1	0.376 4	0.511 3	0.262 5	0.688 3	0.921 2	0.617 11	0.321 13	0.590 6	0.491 9	0.556 5	0.000 4	0.000 1	0.481 6	0.093 1	0.043 3	0.284 2	0.000 5	0.875 15	0.135 9	0.669 4	0.124 14	0.394 7	0.849 12	0.298 5	0.000 1	0.476 18	0.088 13	0.042 7	0.000 4	0.000 1	0.254 5	0.653 11	0.741 6	0.215 1	0.573 6	0.852 6	0.266 11	0.654 3	0.056 13	0.835 7	0.000 6	0.492 2	0.000 1	0.000 8	0.000 3	0.612 10	0.000 5	0.000 9	0.000 1	0.616 7	0.469 18	0.460 5	0.698 14	0.516 3	0.000 1	0.378 9	0.563 5	0.476 5	0.863 6	0.574 10	0.330 7	0.000 12	0.282 3	0.000 1	0.760 5	0.710 6	0.233 1	0.000 11	0.641 6	0.814 3	0.000 1	0.585 10	0.053 12	0.000 7	0.000 1	0.629 11	0.000 2	0.000 1	0.678 4	0.528 14	0.534 6	0.129 15	0.596 5	0.973 5	0.264 13	0.772 2	0.526 11	0.139 10	0.707 5	0.000 1	0.000 12	0.764 15	0.591 17	0.848 7	0.000 1	0.827 5	0.338 3	0.806 13	0.000 1	0.568 9	0.151 11	0.358 2	0.659 11	0.510 4
Weiguang Zhao, Rui Zhang, Qiufeng Wang, Guangliang Cheng, Kaizhu Huang: BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis. CVPR 2025
PonderV2 ScanNet200	0.346 7	0.552 9	0.270 9	0.175 10	0.497 8	0.070 13	0.239 8	0.000 3	0.000 8	0.000 1	0.232 18	0.412 9	0.584 3	0.842 4	0.804 5	0.212 7	0.540 11	0.000 3	0.433 17	0.106 11	0.000 10	0.590 6	0.290 12	0.548 6	0.243 7	0.000 10	0.356 12	0.000 1	0.000 3	0.062 11	0.398 14	0.441 11	0.000 1	0.104 11	0.000 3	0.888 6	0.076 12	0.682 10	0.030 4	0.094 7	0.491 12	0.351 13	0.869 11	0.000 1	0.063 1	0.403 12	0.700 2	0.000 10	0.660 14	0.881 10	0.761 4	0.050 8	0.186 11	0.852 14	0.000 1	0.007 9	0.570 9	0.100 2	0.565 3	0.326 7	0.641 11	0.431 7	0.290 15	0.621 6	0.259 3	0.408 12	0.622 11	0.125 2	0.082 13	0.950 6	0.179 5	0.000 1	0.263 7	0.424 5	0.193 10	0.558 8	0.880 4	0.545 14	0.375 8	0.727 3	0.445 13	0.499 9	0.000 4	0.000 1	0.475 8	0.002 10	0.034 6	0.083 9	0.000 5	0.924 3	0.290 4	0.636 6	0.115 15	0.400 6	0.874 5	0.186 11	0.000 1	0.611 9	0.128 3	0.113 2	0.000 4	0.000 1	0.000 12	0.584 13	0.636 10	0.103 15	0.385 11	0.843 7	0.283 5	0.603 7	0.080 8	0.825 11	0.000 6	0.377 11	0.000 1	0.000 8	0.000 3	0.457 12	0.000 5	0.000 9	0.000 1	0.574 13	0.608 10	0.481 4	0.792 5	0.394 6	0.000 1	0.357 11	0.503 12	0.261 11	0.817 14	0.504 13	0.304 8	0.472 5	0.115 12	0.000 1	0.750 8	0.677 10	0.202 2	0.000 11	0.509 10	0.729 7	0.000 1	0.519 13	0.000 15	0.000 7	0.000 1	0.620 13	0.000 2	0.000 1	0.660 7	0.560 8	0.486 7	0.384 6	0.346 11	0.952 6	0.247 15	0.667 5	0.436 13	0.269 3	0.691 7	0.000 1	0.010 7	0.787 11	0.889 3	0.880 5	0.000 1	0.810 8	0.336 4	0.860 9	0.000 1	0.606 8	0.009 12	0.248 10	0.681 8	0.392 9
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.
OA-CNN-L_ScanNet200	0.333 12	0.558 6	0.269 10	0.124 14	0.448 15	0.080 10	0.272 6	0.000 3	0.000 8	0.000 1	0.342 9	0.515 4	0.524 8	0.713 14	0.789 10	0.158 12	0.384 13	0.000 3	0.806 7	0.125 8	0.000 10	0.496 9	0.332 7	0.498 15	0.227 9	0.024 7	0.474 3	0.000 1	0.003 2	0.071 10	0.487 4	0.000 12	0.000 1	0.110 9	0.000 3	0.876 8	0.013 18	0.703 4	0.000 8	0.076 10	0.473 13	0.355 12	0.906 7	0.000 1	0.000 2	0.476 6	0.706 1	0.000 10	0.672 11	0.835 14	0.748 10	0.015 13	0.223 8	0.860 12	0.000 1	0.000 11	0.572 8	0.000 7	0.509 7	0.313 8	0.662 5	0.398 14	0.396 8	0.411 14	0.276 2	0.527 5	0.711 6	0.000 7	0.076 14	0.946 7	0.166 6	0.000 1	0.022 11	0.160 7	0.183 14	0.493 14	0.699 10	0.637 7	0.403 7	0.330 13	0.406 14	0.526 7	0.024 2	0.000 1	0.392 12	0.000 12	0.016 16	0.000 13	0.196 4	0.915 6	0.112 12	0.557 11	0.197 7	0.352 11	0.877 4	0.000 13	0.000 1	0.592 13	0.103 11	0.000 14	0.067 1	0.000 1	0.089 8	0.735 8	0.625 12	0.130 10	0.568 7	0.836 8	0.271 9	0.534 10	0.043 14	0.799 12	0.001 5	0.445 6	0.000 1	0.000 8	0.024 2	0.661 5	0.000 5	0.262 3	0.000 1	0.591 9	0.517 14	0.373 9	0.788 7	0.021 9	0.000 1	0.455 5	0.517 10	0.320 9	0.823 13	0.200 17	0.001 18	0.150 6	0.100 13	0.000 1	0.736 10	0.668 11	0.103 15	0.052 7	0.662 5	0.720 9	0.000 1	0.602 6	0.112 7	0.002 6	0.000 1	0.637 10	0.000 2	0.000 1	0.621 11	0.569 6	0.398 10	0.412 5	0.234 13	0.949 7	0.363 6	0.492 15	0.495 12	0.251 4	0.665 10	0.000 1	0.001 11	0.805 8	0.833 7	0.794 12	0.000 1	0.821 6	0.314 5	0.843 12	0.000 1	0.560 10	0.245 8	0.262 7	0.713 5	0.370 11

GSTran	0.334 11	0.533 13	0.250 13	0.179 9	0.487 9	0.041 17	0.139 14	0.003 1	0.273 6	0.000 1	0.273 17	0.189 17	0.465 13	0.704 15	0.794 9	0.198 8	0.831 6	0.000 3	0.712 9	0.055 17	0.063 6	0.518 7	0.306 9	0.459 17	0.217 11	0.028 5	0.282 15	0.000 1	0.000 3	0.044 13	0.405 12	0.558 9	0.000 1	0.080 13	0.000 3	0.873 10	0.020 17	0.684 8	0.000 8	0.075 13	0.496 10	0.363 10	0.651 16	0.000 1	0.000 2	0.425 9	0.648 6	0.000 10	0.669 12	0.914 7	0.741 11	0.009 15	0.200 10	0.864 10	0.000 1	0.000 11	0.560 10	0.000 7	0.357 15	0.233 13	0.633 12	0.408 12	0.411 4	0.320 17	0.242 5	0.440 10	0.598 15	0.047 4	0.205 9	0.940 11	0.139 12	0.000 1	0.372 5	0.138 9	0.191 11	0.495 12	0.618 14	0.624 10	0.321 13	0.595 4	0.496 7	0.499 9	0.000 4	0.000 1	0.340 13	0.014 7	0.032 7	0.136 5	0.000 5	0.903 9	0.279 5	0.601 10	0.198 6	0.345 12	0.849 12	0.260 7	0.000 1	0.573 15	0.072 17	0.060 5	0.000 4	0.000 1	0.089 8	0.838 5	0.775 4	0.125 12	0.381 12	0.752 14	0.274 6	0.517 14	0.032 16	0.841 6	0.000 6	0.354 15	0.000 1	0.047 6	0.000 3	0.439 14	0.787 3	0.252 4	0.000 1	0.512 17	0.507 17	0.158 17	0.717 12	0.000 11	0.000 1	0.337 13	0.483 14	0.570 2	0.853 9	0.614 8	0.121 12	0.070 10	0.229 8	0.000 1	0.732 12	0.773 2	0.193 3	0.000 11	0.606 8	0.791 6	0.000 1	0.593 9	0.000 15	0.010 5	0.000 1	0.574 17	0.000 2	0.000 1	0.507 13	0.554 10	0.361 12	0.136 14	0.608 4	0.948 8	0.304 9	0.593 11	0.533 9	0.011 17	0.634 13	0.000 1	0.060 3	0.821 5	0.613 14	0.797 11	0.000 1	0.799 12	0.036 14	0.782 15	0.000 1	0.609 7	0.423 4	0.133 18	0.647 13	0.213 16

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

CeCo	0.340 8	0.551 10	0.247 14	0.181 7	0.475 13	0.057 16	0.142 13	0.000 3	0.000 8	0.000 1	0.387 6	0.463 6	0.499 10	0.924 3	0.774 12	0.213 6	0.257 14	0.000 3	0.546 16	0.100 12	0.006 9	0.615 2	0.177 18	0.534 8	0.246 6	0.000 10	0.400 6	0.000 1	0.338 1	0.006 17	0.484 6	0.609 6	0.000 1	0.083 12	0.000 3	0.873 10	0.089 5	0.661 15	0.000 8	0.048 16	0.560 5	0.408 7	0.892 9	0.000 1	0.000 2	0.586 1	0.616 9	0.000 10	0.692 9	0.900 9	0.721 13	0.162 1	0.228 7	0.860 12	0.000 1	0.000 11	0.575 6	0.083 3	0.550 4	0.347 5	0.624 14	0.410 11	0.360 10	0.740 3	0.109 13	0.321 16	0.660 9	0.000 7	0.121 10	0.939 14	0.143 8	0.000 1	0.400 3	0.003 13	0.190 12	0.564 7	0.652 11	0.615 12	0.421 5	0.304 14	0.579 1	0.547 6	0.000 4	0.000 1	0.296 15	0.000 12	0.030 9	0.096 8	0.000 5	0.916 5	0.037 13	0.551 13	0.171 10	0.376 8	0.865 8	0.286 6	0.000 1	0.633 6	0.102 12	0.027 8	0.011 3	0.000 1	0.000 12	0.474 15	0.742 5	0.133 8	0.311 14	0.824 9	0.242 14	0.503 15	0.068 9	0.828 10	0.000 6	0.429 8	0.000 1	0.063 5	0.000 3	0.781 2	0.000 5	0.000 9	0.000 1	0.665 3	0.633 7	0.450 6	0.818 2	0.000 11	0.000 1	0.429 6	0.532 8	0.226 14	0.825 12	0.510 12	0.377 6	0.709 3	0.079 15	0.000 1	0.753 6	0.683 9	0.102 16	0.063 6	0.401 17	0.620 14	0.000 1	0.619 3	0.000 15	0.000 7	0.000 1	0.595 14	0.000 2	0.000 1	0.345 15	0.564 7	0.411 9	0.603 1	0.384 9	0.945 10	0.266 12	0.643 6	0.367 15	0.304 1	0.663 11	0.000 1	0.010 7	0.726 16	0.767 8	0.898 4	0.000 1	0.784 14	0.435 1	0.861 8	0.000 1	0.447 11	0.000 16	0.257 8	0.656 12	0.377 10
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
OctFormer ScanNet200	0.326 14	0.539 11	0.265 11	0.131 13	0.499 7	0.110 5	0.522 4	0.000 3	0.000 8	0.000 1	0.318 12	0.427 8	0.455 16	0.743 12	0.765 14	0.175 11	0.842 5	0.000 3	0.828 6	0.204 5	0.033 7	0.429 12	0.335 6	0.601 3	0.312 3	0.000 10	0.357 11	0.000 1	0.000 3	0.047 12	0.423 10	0.000 12	0.000 1	0.105 10	0.000 3	0.873 10	0.079 10	0.670 13	0.000 8	0.117 5	0.471 14	0.432 4	0.829 12	0.000 1	0.000 2	0.584 2	0.417 18	0.089 6	0.684 10	0.837 13	0.705 17	0.021 12	0.178 12	0.892 7	0.000 1	0.028 8	0.505 14	0.000 7	0.457 10	0.200 15	0.662 5	0.412 10	0.244 16	0.496 8	0.000 17	0.451 9	0.626 10	0.000 7	0.102 12	0.943 10	0.138 14	0.000 1	0.000 13	0.149 8	0.291 3	0.534 10	0.722 8	0.632 8	0.331 11	0.253 15	0.453 12	0.487 12	0.000 4	0.000 1	0.479 7	0.000 12	0.022 13	0.000 13	0.000 5	0.900 11	0.128 11	0.684 3	0.164 11	0.413 5	0.854 11	0.000 13	0.000 1	0.512 17	0.074 15	0.003 11	0.000 4	0.000 1	0.000 12	0.469 16	0.613 13	0.132 9	0.529 8	0.871 4	0.227 17	0.582 8	0.026 18	0.787 13	0.000 6	0.339 16	0.000 1	0.000 8	0.000 3	0.626 8	0.000 5	0.029 8	0.000 1	0.587 10	0.612 9	0.411 7	0.724 10	0.000 11	0.000 1	0.407 7	0.552 6	0.513 4	0.849 11	0.655 5	0.408 5	0.000 12	0.296 2	0.000 1	0.686 16	0.645 15	0.145 8	0.022 9	0.414 15	0.633 12	0.000 1	0.637 2	0.224 3	0.000 7	0.000 1	0.650 9	0.000 2	0.000 1	0.622 10	0.535 13	0.343 13	0.483 3	0.230 14	0.943 11	0.289 11	0.618 8	0.596 6	0.140 9	0.679 9	0.000 1	0.022 6	0.783 12	0.620 13	0.906 2	0.000 1	0.806 9	0.137 11	0.865 6	0.000 1	0.378 12	0.000 16	0.168 16	0.680 9	0.227 14
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
PPT-SpUNet-F.T.	0.332 13	0.556 7	0.270 8	0.123 15	0.519 5	0.091 8	0.349 5	0.000 3	0.000 8	0.000 1	0.339 10	0.383 11	0.498 11	0.833 5	0.807 4	0.241 4	0.584 10	0.000 3	0.755 8	0.124 9	0.000 10	0.608 3	0.330 8	0.530 10	0.314 2	0.000 10	0.374 9	0.000 1	0.000 3	0.197 6	0.459 8	0.000 12	0.000 1	0.117 7	0.000 3	0.876 8	0.095 2	0.682 10	0.000 8	0.086 9	0.518 8	0.433 3	0.930 5	0.000 1	0.000 2	0.563 3	0.542 15	0.077 7	0.715 4	0.858 12	0.756 6	0.008 16	0.171 13	0.874 9	0.000 1	0.039 7	0.550 12	0.000 7	0.545 5	0.256 9	0.657 9	0.453 5	0.351 11	0.449 11	0.213 6	0.392 13	0.611 12	0.000 7	0.037 16	0.946 7	0.138 14	0.000 1	0.000 13	0.063 11	0.308 2	0.537 9	0.796 5	0.673 5	0.323 12	0.392 11	0.400 15	0.509 8	0.000 4	0.000 1	0.649 1	0.000 12	0.023 12	0.000 13	0.000 5	0.914 7	0.002 17	0.506 17	0.163 12	0.359 9	0.872 6	0.000 13	0.000 1	0.623 8	0.112 6	0.001 12	0.000 4	0.000 1	0.021 10	0.753 6	0.565 16	0.150 5	0.579 5	0.806 10	0.267 10	0.616 5	0.042 15	0.783 14	0.000 6	0.374 12	0.000 1	0.000 8	0.000 3	0.620 9	0.000 5	0.000 9	0.000 1	0.572 14	0.634 6	0.350 10	0.792 5	0.000 11	0.000 1	0.376 10	0.535 7	0.378 7	0.855 8	0.672 4	0.074 14	0.000 12	0.185 11	0.000 1	0.727 13	0.660 13	0.076 18	0.000 11	0.432 13	0.646 11	0.000 1	0.594 8	0.006 14	0.000 7	0.000 1	0.658 8	0.000 2	0.000 1	0.661 5	0.549 11	0.300 15	0.291 9	0.045 15	0.942 12	0.304 9	0.600 9	0.572 8	0.135 13	0.695 6	0.000 1	0.008 9	0.793 10	0.942 2	0.899 3	0.000 1	0.816 7	0.181 8	0.897 3	0.000 1	0.679 4	0.223 9	0.264 6	0.691 6	0.345 12
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
L3DETR-ScanNet_200	0.336 9	0.533 12	0.279 7	0.155 11	0.508 6	0.073 12	0.101 18	0.000 3	0.058 7	0.000 1	0.294 15	0.233 15	0.548 5	0.927 2	0.788 11	0.264 2	0.463 12	0.000 3	0.638 13	0.098 14	0.014 8	0.411 13	0.226 14	0.525 11	0.225 10	0.010 8	0.397 7	0.000 1	0.000 3	0.192 7	0.380 15	0.598 7	0.000 1	0.117 7	0.000 3	0.883 7	0.082 8	0.689 5	0.000 8	0.032 18	0.549 7	0.417 5	0.910 6	0.000 1	0.000 2	0.448 8	0.613 10	0.000 10	0.697 7	0.960 4	0.759 5	0.158 2	0.293 3	0.883 8	0.000 1	0.312 3	0.583 5	0.079 4	0.422 12	0.068 18	0.660 8	0.418 8	0.298 13	0.430 13	0.114 11	0.526 6	0.776 4	0.051 3	0.679 3	0.946 7	0.152 7	0.000 1	0.183 9	0.000 15	0.211 9	0.511 11	0.409 17	0.565 13	0.355 9	0.448 8	0.512 5	0.557 4	0.000 4	0.000 1	0.420 10	0.000 12	0.007 17	0.104 7	0.000 5	0.125 18	0.330 3	0.514 16	0.146 13	0.321 14	0.860 9	0.174 12	0.000 1	0.629 7	0.075 14	0.000 14	0.000 4	0.000 1	0.002 11	0.671 9	0.712 7	0.141 7	0.339 13	0.856 5	0.261 13	0.529 11	0.067 10	0.835 7	0.000 6	0.369 13	0.000 1	0.259 2	0.000 3	0.629 7	0.000 5	0.487 1	0.000 1	0.579 12	0.646 5	0.107 18	0.720 11	0.122 8	0.000 1	0.333 15	0.505 11	0.303 10	0.908 4	0.503 14	0.565 2	0.074 9	0.324 1	0.000 1	0.740 9	0.661 12	0.109 14	0.000 11	0.427 14	0.563 18	0.000 1	0.579 11	0.108 8	0.000 7	0.000 1	0.664 7	0.000 2	0.000 1	0.641 8	0.539 12	0.416 8	0.515 2	0.256 12	0.940 13	0.312 7	0.209 18	0.620 4	0.138 12	0.636 12	0.000 1	0.000 12	0.775 14	0.861 5	0.765 13	0.000 1	0.801 10	0.119 12	0.860 9	0.000 1	0.687 2	0.001 15	0.192 15	0.679 10	0.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
ODIN - Sem200	0.368 5	0.562 5	0.297 5	0.207 5	0.380 18	0.196 1	0.828 3	0.000 3	0.321 3	0.000 1	0.400 5	0.775 1	0.460 14	0.501 18	0.769 13	0.065 16	0.870 4	0.000 3	0.913 1	0.213 4	0.000 10	0.000 18	0.389 2	0.554 5	0.312 3	0.000 10	0.591 1	0.000 1	0.000 3	0.491 1	0.487 4	0.894 2	0.000 1	0.378 2	0.303 1	0.796 18	0.088 6	0.669 14	0.081 2	0.216 1	0.256 18	0.334 14	0.898 8	0.000 1	0.000 2	0.370 15	0.599 11	0.000 10	0.581 17	0.988 2	0.749 9	0.090 6	0.242 6	0.921 4	0.000 1	0.202 5	0.609 3	0.000 7	0.655 1	0.214 14	0.654 10	0.346 16	0.408 7	0.485 9	0.169 8	0.631 2	0.704 7	0.000 7	0.814 1	0.940 11	0.127 17	0.000 1	0.000 13	0.462 4	0.227 7	0.641 5	0.885 3	0.657 6	0.434 3	0.000 18	0.550 2	0.393 16	0.000 4	0.000 1	0.590 4	0.000 12	0.048 2	0.077 10	0.000 5	0.784 17	0.131 10	0.557 11	0.316 2	0.359 9	0.833 15	0.373 3	0.000 1	0.661 4	0.108 9	0.001 12	0.000 4	0.000 1	0.301 4	0.612 12	0.565 16	0.129 11	0.482 9	0.468 17	0.274 6	0.561 9	0.376 1	0.912 2	0.181 1	0.440 7	0.000 1	0.166 4	0.000 3	0.641 6	0.000 5	0.426 2	0.000 1	0.642 6	0.626 8	0.259 12	0.787 8	0.429 5	0.000 1	0.589 1	0.523 9	0.246 12	0.857 7	0.000 18	0.228 10	0.000 12	0.265 4	0.000 1	0.752 7	0.832 1	0.090 17	0.157 1	0.791 2	0.578 17	0.000 1	0.373 16	0.539 1	0.000 7	0.000 1	0.685 5	0.000 2	0.000 1	0.632 9	0.575 4	0.663 1	0.152 12	0.358 10	0.926 14	0.397 4	0.454 16	0.610 5	0.119 16	0.685 8	0.000 1	0.000 12	0.803 9	0.740 10	0.441 15	0.000 1	0.800 11	0.000 18	0.871 4	0.000 1	0.220 18	0.487 2	0.862 1	0.682 7	0.054 18
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
AWCS	0.305 15	0.508 15	0.225 15	0.142 12	0.463 14	0.063 14	0.195 10	0.000 3	0.000 8	0.000 1	0.467 3	0.551 3	0.504 9	0.773 7	0.764 15	0.142 14	0.029 18	0.000 3	0.626 14	0.100 12	0.000 10	0.360 14	0.179 16	0.507 14	0.137 16	0.006 9	0.300 13	0.000 1	0.000 3	0.172 9	0.364 16	0.512 10	0.000 1	0.056 15	0.000 3	0.865 14	0.093 4	0.634 18	0.000 8	0.071 14	0.396 15	0.296 17	0.876 10	0.000 1	0.000 2	0.373 14	0.436 17	0.063 9	0.749 2	0.877 11	0.721 13	0.131 3	0.124 15	0.804 16	0.000 1	0.000 11	0.515 13	0.010 6	0.452 11	0.252 10	0.578 15	0.417 9	0.179 18	0.484 10	0.171 7	0.337 15	0.606 13	0.000 7	0.115 11	0.937 15	0.142 9	0.000 1	0.008 12	0.000 15	0.157 17	0.484 15	0.402 18	0.501 16	0.339 10	0.553 7	0.529 3	0.478 13	0.000 4	0.000 1	0.404 11	0.001 11	0.022 13	0.077 10	0.000 5	0.894 13	0.219 7	0.628 7	0.093 16	0.305 15	0.886 1	0.233 10	0.000 1	0.603 10	0.112 6	0.023 9	0.000 4	0.000 1	0.000 12	0.741 7	0.664 8	0.097 16	0.253 15	0.782 11	0.264 12	0.523 12	0.154 2	0.707 17	0.000 6	0.411 9	0.000 1	0.000 8	0.000 3	0.332 17	0.000 5	0.000 9	0.000 1	0.602 8	0.595 11	0.185 14	0.656 17	0.159 7	0.000 1	0.355 12	0.424 16	0.154 16	0.729 16	0.516 11	0.220 11	0.620 4	0.084 14	0.000 1	0.707 15	0.651 14	0.173 5	0.014 10	0.381 18	0.582 15	0.000 1	0.619 3	0.049 13	0.000 7	0.000 1	0.702 4	0.000 2	0.000 1	0.302 17	0.489 16	0.317 14	0.334 7	0.392 8	0.922 15	0.254 14	0.533 14	0.394 14	0.129 15	0.613 16	0.000 1	0.000 12	0.820 6	0.649 12	0.749 14	0.000 1	0.782 15	0.282 6	0.863 7	0.000 1	0.288 16	0.006 13	0.220 12	0.633 15	0.542 3
: Long-Tailed 3D Semantic Segmentation with Adaptive Weight Constraint and Sampling. ICRA 2024
LGround	0.272 16	0.485 16	0.184 16	0.106 16	0.476 12	0.077 11	0.218 9	0.000 3	0.000 8	0.000 1	0.547 2	0.295 12	0.540 6	0.746 11	0.745 16	0.058 17	0.112 17	0.005 1	0.658 12	0.077 16	0.000 10	0.322 15	0.178 17	0.512 12	0.190 14	0.199 2	0.277 16	0.000 1	0.000 3	0.173 8	0.399 13	0.000 12	0.000 1	0.039 17	0.000 3	0.858 15	0.085 7	0.676 12	0.002 6	0.103 6	0.498 9	0.323 15	0.703 13	0.000 1	0.000 2	0.296 16	0.549 13	0.216 1	0.702 6	0.768 15	0.718 15	0.028 10	0.092 17	0.786 17	0.000 1	0.000 11	0.453 17	0.022 5	0.251 18	0.252 10	0.572 16	0.348 15	0.321 12	0.514 7	0.063 15	0.279 17	0.552 16	0.000 7	0.019 17	0.932 16	0.132 16	0.000 1	0.000 13	0.000 15	0.156 18	0.457 16	0.623 13	0.518 15	0.265 17	0.358 12	0.381 16	0.395 15	0.000 4	0.000 1	0.127 18	0.012 9	0.051 1	0.000 13	0.000 5	0.886 14	0.014 14	0.437 18	0.179 9	0.244 16	0.826 16	0.000 13	0.000 1	0.599 11	0.136 1	0.085 3	0.000 4	0.000 1	0.000 12	0.565 14	0.612 14	0.143 6	0.207 16	0.566 15	0.232 16	0.446 16	0.127 4	0.708 16	0.000 6	0.384 10	0.000 1	0.000 8	0.000 3	0.402 15	0.000 5	0.059 7	0.000 1	0.525 16	0.566 12	0.229 13	0.659 16	0.000 11	0.000 1	0.265 16	0.446 15	0.147 17	0.720 18	0.597 9	0.066 15	0.000 12	0.187 10	0.000 1	0.726 14	0.467 18	0.134 13	0.000 11	0.413 16	0.629 13	0.000 1	0.363 17	0.055 11	0.022 3	0.000 1	0.626 12	0.000 2	0.000 1	0.323 16	0.479 18	0.154 17	0.117 16	0.028 17	0.901 16	0.243 16	0.415 17	0.295 18	0.143 6	0.610 17	0.000 1	0.000 12	0.777 13	0.397 18	0.324 17	0.000 1	0.778 16	0.179 9	0.702 17	0.000 1	0.274 17	0.404 5	0.233 11	0.622 16	0.398 7
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	0.418 16	0.059 15	0.186 11	0.000 3	0.000 8	0.000 1	0.335 11	0.250 14	0.316 17	0.766 8	0.697 18	0.142 14	0.170 15	0.003 2	0.553 15	0.112 10	0.097 1	0.201 17	0.186 15	0.476 16	0.081 17	0.000 10	0.216 18	0.000 1	0.000 3	0.001 18	0.314 18	0.000 12	0.000 1	0.055 16	0.000 3	0.832 17	0.094 3	0.659 16	0.002 6	0.076 10	0.310 17	0.293 18	0.664 15	0.000 1	0.000 2	0.175 18	0.634 7	0.130 2	0.552 18	0.686 18	0.700 18	0.076 7	0.110 16	0.770 18	0.000 1	0.000 11	0.430 18	0.000 7	0.319 16	0.166 16	0.542 18	0.327 17	0.205 17	0.332 15	0.052 16	0.375 14	0.444 18	0.000 7	0.012 18	0.930 18	0.203 3	0.000 1	0.000 13	0.046 12	0.175 15	0.413 17	0.592 15	0.471 17	0.299 16	0.152 17	0.340 17	0.247 18	0.000 4	0.000 1	0.225 16	0.058 3	0.037 4	0.000 13	0.207 3	0.862 16	0.014 14	0.548 14	0.033 17	0.233 17	0.816 17	0.000 13	0.000 1	0.542 16	0.123 5	0.121 1	0.019 2	0.000 1	0.000 12	0.463 17	0.454 18	0.045 18	0.128 18	0.557 16	0.235 15	0.441 17	0.063 11	0.484 18	0.000 6	0.308 18	0.000 1	0.000 8	0.000 3	0.318 18	0.000 5	0.000 9	0.000 1	0.545 15	0.543 13	0.164 15	0.734 9	0.000 11	0.000 1	0.215 18	0.371 17	0.198 15	0.743 15	0.205 16	0.062 16	0.000 12	0.079 15	0.000 1	0.683 17	0.547 17	0.142 9	0.000 11	0.441 12	0.579 16	0.000 1	0.464 15	0.098 9	0.041 1	0.000 1	0.590 15	0.000 2	0.000 1	0.373 14	0.494 15	0.174 16	0.105 17	0.001 18	0.895 17	0.222 17	0.537 13	0.307 17	0.180 5	0.625 15	0.000 1	0.000 12	0.591 18	0.609 15	0.398 16	0.000 1	0.766 18	0.014 17	0.638 18	0.000 1	0.377 13	0.004 14	0.206 14	0.609 18	0.465 5
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	0.381 17	0.084 9	0.134 16	0.000 3	0.000 8	0.000 1	0.386 7	0.141 18	0.279 18	0.737 13	0.703 17	0.014 18	0.164 16	0.000 3	0.663 11	0.092 15	0.000 10	0.224 16	0.291 11	0.531 9	0.056 18	0.000 10	0.242 17	0.000 1	0.000 3	0.013 16	0.331 17	0.000 12	0.000 1	0.035 18	0.001 2	0.858 15	0.059 15	0.650 17	0.000 8	0.056 15	0.353 16	0.299 16	0.670 14	0.000 1	0.000 2	0.284 17	0.484 16	0.071 8	0.594 16	0.720 17	0.710 16	0.027 11	0.068 18	0.813 15	0.000 1	0.005 10	0.492 15	0.164 1	0.274 17	0.111 17	0.571 17	0.307 18	0.293 14	0.307 18	0.150 9	0.163 18	0.531 17	0.002 6	0.545 5	0.932 16	0.093 18	0.000 1	0.000 13	0.002 14	0.159 16	0.368 18	0.581 16	0.440 18	0.228 18	0.406 10	0.282 18	0.294 17	0.000 4	0.000 1	0.189 17	0.060 2	0.036 5	0.000 13	0.000 5	0.897 12	0.000 18	0.525 15	0.025 18	0.205 18	0.771 18	0.000 13	0.000 1	0.593 12	0.108 9	0.044 6	0.000 4	0.000 1	0.000 12	0.282 18	0.589 15	0.094 17	0.169 17	0.466 18	0.227 17	0.419 18	0.125 5	0.757 15	0.002 4	0.334 17	0.000 1	0.000 8	0.000 3	0.357 16	0.000 5	0.000 9	0.000 1	0.582 11	0.513 15	0.337 11	0.612 18	0.000 11	0.000 1	0.250 17	0.352 18	0.136 18	0.724 17	0.655 5	0.280 9	0.000 12	0.046 17	0.000 1	0.606 18	0.559 16	0.159 7	0.102 3	0.445 11	0.655 10	0.000 1	0.310 18	0.117 6	0.000 7	0.000 1	0.581 16	0.026 1	0.000 1	0.265 18	0.483 17	0.084 18	0.097 18	0.044 16	0.865 18	0.142 18	0.588 12	0.351 16	0.272 2	0.596 18	0.000 1	0.003 10	0.622 17	0.720 11	0.096 18	0.000 1	0.771 17	0.016 16	0.772 16	0.000 1	0.302 15	0.194 10	0.214 13	0.621 17	0.197 17
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 50%	head ap 50%	common ap 50%	tail ap 50%	backpack	bag	ball	bar	basket	bathroom cabinet	bathroom stall	bathroom stall door	bathroom vanity	bathtub	bed	bench	bicycle	bin	blackboard	blanket	blinds	board	book	bookshelf	bottle	bowl	box	broom	bucket	bulletin board	cabinet	calendar	candle	cart	case of water bottles	ceiling	ceiling light	chair	clock	closet	closet rod	clothes	clothes dryer	coat rack	coffee kettle	coffee maker	coffee table	column	computer tower	copier	couch	counter	cup	curtain	cushion	decoration	desk	dining table	dish rack	dishwasher	door	doorframe	dresser	dumbbell	end table	fan	file cabinet	fire alarm	fire extinguisher	folded chair	hat	headphones	ironing board	jacket	keyboard	keyboard piano	kitchen cabinet	kitchen counter	ladder	lamp	laptop	laundry basket	laundry detergent	laundry hamper	ledge	light	light switch	machine	mailbox	mat	microwave	mini fridge	mirror	monitor	mouse	music stand	nightstand	object	office chair	oven	paper	paper bag	paper cutter	paper towel dispenser	paper towel roll	person	piano	picture	pillow	pipe	plant	plate	plunger	poster	power outlet	power strip	printer	projector	projector screen	rack	radiator	range hood	recycling bin	refrigerator	scale	seat	shelf	shoe	shower	shower curtain	shower curtain rod	shower floor	shower head	shower wall	sign	sink	soap dispenser	sofa chair	speaker	stair rail	stairs	stand	stool	storage bin	storage container	storage organizer	stove	structure	stuffed animal	suitcase	table	telephone	tissue box	toaster	toilet	toilet paper	toilet paper dispenser	towel	trash bin	trash can	tray	tube	tv	tv stand	vacuum cleaner	vent	wardrobe	washing machine	water bottle	water cooler	water pitcher	whiteboard	window	windowsill

CompetitorFormer-200	0.415 3	0.574 3	0.370 4	0.274 3	0.632 3	0.054 6	0.500 1	0.083 1	0.000 4	0.000 1	0.260 2	0.541 4	0.410 4	0.903 6	0.987 2	0.885 1	0.500 3	0.064 1	0.250 4	0.378 2	1.000 1	0.243 5	0.428 1	0.599 6	0.218 5	1.000 1	0.196 4	0.000 1	0.000 2	0.587 3	0.318 6	1.000 1	0.000 1	0.500 1	0.000 3	0.845 1	0.232 4	0.885 1	0.005 2	0.015 3	0.216 4	0.183 5	0.399 3	0.082 1	0.000 1	0.724 4	0.806 3	0.500 2	0.869 2	1.000 1	0.779 7	0.095 3	0.443 1	0.685 4	0.021 3	0.269 3	0.704 3	0.083 5	0.467 7	0.400 1	0.846 2	0.551 1	0.663 3	0.261 7	0.103 5	0.482 3	0.758 3	0.025 2	0.018 6	0.400 2	0.000 2	0.677 2	0.500 1	0.207 5	0.881 2	1.000 1	0.600 3	0.648 2	0.144 8	0.641 3	0.452 3	0.000 2	0.000 1	0.327 5	0.142 2	0.209 5	0.000 4	0.083 2	0.215 6	0.317 5	0.748 5	0.508 4	0.484 3	0.957 1	0.000 4	0.000 1	0.833 3	0.132 1	0.400 1	0.663 1	0.015 3	0.103 3	1.000 1	0.759 4	0.125 3	0.286 4	0.500 2	0.830 2	0.651 3	0.089 2	0.540 7	0.380 3	0.581 2	0.000 1	0.500 1	0.000 3	0.745 2	0.050 2	1.000 1	0.000 1	0.622 6	0.694 5	0.213 4	0.870 5	0.125 5	0.000 4	0.205 4	0.562 2	0.000 7	0.933 7	1.000 1	0.820 5	0.250 3	0.347 6	0.000 3	0.731 4	0.877 1	0.289 3	0.160 2	0.186 4	0.684 5	0.008 4	0.538 3	0.000 2	0.000 3	0.000 2	0.700 4	0.056 1	0.000 1	0.491 4	0.584 6	0.602 4	0.489 3	0.565 1	1.000 1	0.311 7	0.750 3	0.583 4	0.292 4	0.832 5	0.000 1	0.157 1	0.780 3	1.000 1	0.625 4	0.000 1	0.131 3	0.794 3	0.000 1	0.667 1	0.071 8	0.545 3	0.682 1	0.462 2

TD3D Scannet200	0.320 6	0.501 6	0.264 6	0.164 6	0.506 6	0.062 5	0.500 1	0.000 2	0.000 4	0.000 1	0.208 3	0.431 6	0.252 7	1.000 1	0.733 7	0.587 3	0.000 6	0.008 5	0.000 6	0.106 4	0.000 4	0.356 3	0.123 8	0.686 2	0.101 6	0.000 4	0.152 6	0.000 1	0.000 2	0.226 5	0.280 7	0.000 6	0.000 1	0.250 4	0.000 3	0.619 5	0.061 7	0.841 3	0.000 3	0.000 6	0.167 5	0.194 4	0.333 4	0.000 4	0.000 1	0.667 5	0.820 2	0.250 5	0.790 7	1.000 1	0.879 3	0.077 4	0.094 7	0.708 1	0.217 2	0.049 6	0.634 4	0.792 1	0.331 8	0.033 9	0.716 6	0.159 6	0.396 6	0.331 6	0.099 6	0.415 4	0.842 1	0.000 3	0.458 3	0.542 1	0.000 2	0.101 5	0.000 5	0.218 4	0.513 6	0.500 6	0.458 6	0.104 6	0.516 3	0.456 4	0.268 8	0.000 2	0.000 1	0.400 3	0.022 4	0.233 4	0.143 3	0.000 3	0.677 1	0.400 2	0.504 9	0.095 7	0.083 9	0.890 5	0.061 3	0.000 1	0.906 1	0.076 5	0.231 2	0.125 6	0.000 4	0.003 6	0.792 7	0.881 1	0.000 6	0.098 7	0.125 8	0.498 8	0.459 6	0.063 3	0.715 4	0.000 6	0.241 7	0.000 1	0.396 4	0.063 2	0.605 5	0.000 3	0.000 6	0.000 1	0.448 9	0.629 7	0.202 5	0.967 1	0.250 4	0.038 1	0.192 5	0.185 6	0.083 6	1.000 1	1.000 1	0.857 2	0.000 4	0.470 4	0.012 1	0.565 7	0.798 5	0.621 1	0.111 3	0.500 1	1.000 1	0.017 3	0.509 4	0.000 2	0.008 2	1.000 1	0.525 6	0.000 2	0.000 1	0.332 7	0.679 2	0.264 6	0.333 5	0.267 4	1.000 1	0.549 3	0.299 9	0.387 6	0.328 3	0.744 8	0.000 1	0.000 5	0.435 9	1.000 1	0.283 8	0.000 1	0.196 2	0.817 2	0.000 1	0.472 3	0.222 6	0.123 8	0.560 5	0.156 6
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
LGround Inst.	0.246 7	0.413 7	0.170 7	0.130 7	0.455 9	0.003 9	0.500 1	0.000 2	0.000 4	0.000 1	0.017 8	0.333 8	0.111 9	1.000 1	0.681 8	0.400 5	0.000 6	0.000 6	1.000 1	0.003 9	0.000 4	0.167 6	0.190 6	0.637 4	0.067 7	0.000 4	0.081 7	0.000 1	0.000 2	0.000 7	0.264 8	0.000 6	0.000 1	0.000 7	0.000 3	0.387 8	0.031 9	0.754 6	0.000 3	0.000 6	0.151 6	0.135 6	0.056 8	0.000 4	0.000 1	0.582 7	0.589 9	0.500 2	0.815 4	1.000 1	0.903 1	0.000 7	0.097 6	0.588 7	0.000 4	0.000 7	0.234 7	0.000 6	0.500 6	0.400 1	0.682 8	0.156 7	0.159 8	0.750 1	0.046 7	0.125 8	0.660 6	0.000 3	0.200 5	0.000 9	0.000 2	0.000 6	0.000 5	0.164 7	0.402 7	0.500 6	0.373 7	0.025 7	0.143 9	0.426 6	0.317 6	0.000 2	0.000 1	0.000 7	0.000 6	0.063 7	0.000 4	0.000 3	0.000 8	0.000 8	0.575 7	0.250 6	0.241 6	0.772 7	0.000 4	0.000 1	0.653 8	0.034 7	0.000 7	0.000 7	0.000 4	0.000 7	1.000 1	0.561 8	0.000 6	0.100 6	0.500 2	0.541 7	0.452 7	0.000 7	0.581 6	0.000 6	0.364 5	0.000 1	0.000 7	0.000 3	0.571 6	0.000 3	0.000 6	0.000 1	0.568 8	0.511 8	0.167 6	0.857 6	0.000 6	0.000 4	0.164 6	0.112 7	0.000 7	0.530 9	1.000 1	0.286 7	0.000 4	0.125 7	0.000 3	0.464 9	0.706 7	0.208 7	0.000 5	0.125 6	0.744 4	0.000 5	0.500 5	0.000 2	0.000 3	0.000 2	0.511 7	0.000 2	0.000 1	0.344 6	0.541 7	0.068 7	0.333 5	0.000 7	1.000 1	0.196 8	0.533 6	0.318 7	0.000 8	0.748 7	0.000 1	0.000 5	0.690 5	1.000 1	0.400 7	0.000 1	0.000 6	0.667 5	0.000 1	0.333 7	0.333 4	0.270 7	0.399 7	0.083 8
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.	0.203 9	0.369 8	0.134 9	0.078 9	0.479 8	0.003 8	0.500 1	0.000 2	0.000 4	0.000 1	0.100 5	0.371 7	0.300 6	0.667 7	0.746 6	0.400 5	0.000 6	0.000 6	0.000 6	0.031 7	0.000 4	0.074 7	0.165 7	0.413 9	0.000 8	0.000 4	0.070 8	0.000 1	0.000 2	0.000 7	0.221 9	0.000 6	0.000 1	0.000 7	0.000 3	0.372 9	0.070 5	0.706 7	0.000 3	0.000 6	0.000 9	0.123 8	0.033 9	0.000 4	0.000 1	0.422 8	0.732 5	0.000 8	0.778 9	1.000 1	0.845 5	0.000 7	0.090 8	0.636 5	0.000 4	0.000 7	0.158 8	0.000 6	0.250 9	0.050 8	0.693 7	0.123 8	0.051 9	0.385 5	0.009 8	0.118 9	0.406 9	0.000 3	0.000 8	0.200 3	0.000 2	0.000 6	0.000 5	0.133 8	0.307 9	0.500 6	0.251 8	0.000 8	0.281 6	0.402 7	0.317 6	0.000 2	0.000 1	0.000 7	0.000 6	0.060 8	0.000 4	0.000 3	0.396 4	0.200 6	0.669 6	0.021 8	0.218 8	0.720 9	0.000 4	0.000 1	0.696 7	0.025 8	0.000 7	0.000 7	0.000 4	0.000 7	0.125 9	0.596 6	0.000 6	0.191 5	0.500 2	0.595 5	0.369 8	0.000 7	0.500 8	0.000 6	0.143 9	0.000 1	0.000 7	0.000 3	0.226 9	0.000 3	0.000 6	0.000 1	0.701 4	0.511 8	0.000 9	0.851 7	0.000 6	0.000 4	0.150 8	0.052 9	0.100 5	0.981 6	0.500 7	0.286 7	0.000 4	0.000 9	0.000 3	0.545 8	0.522 9	0.250 6	0.000 5	0.000 9	0.522 9	0.000 5	0.500 5	0.000 2	0.000 3	0.000 2	0.282 9	0.000 2	0.000 1	0.178 9	0.382 8	0.018 9	0.056 8	0.000 7	0.997 4	0.107 9	0.677 5	0.313 8	0.000 8	0.726 9	0.000 1	0.000 5	0.583 7	0.903 7	0.200 9	0.000 1	0.000 6	0.333 8	0.000 1	0.442 5	0.083 7	0.109 9	0.387 8	0.000 9
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.	0.209 8	0.361 9	0.157 8	0.085 8	0.506 5	0.007 7	0.500 1	0.000 2	0.000 4	0.000 1	0.000 9	0.093 9	0.221 8	0.667 7	0.524 9	0.400 5	0.000 6	0.000 6	0.000 6	0.004 8	0.000 4	0.000 9	0.109 9	0.589 7	0.000 8	0.000 4	0.059 9	0.000 1	0.000 2	0.000 7	0.322 5	0.000 6	0.000 1	0.000 7	0.000 3	0.405 7	0.055 8	0.700 8	0.000 3	0.000 6	0.028 8	0.091 9	0.083 6	0.000 4	0.000 1	0.667 5	0.768 4	0.000 8	0.807 5	1.000 1	0.776 8	0.000 7	0.000 9	0.340 9	0.000 4	0.000 7	0.103 9	0.000 6	0.750 1	0.200 6	0.634 9	0.053 9	0.246 7	0.677 3	0.006 9	0.198 7	0.432 8	0.000 3	0.000 8	0.050 8	0.000 2	0.000 6	0.000 5	0.111 9	0.356 8	0.500 6	0.188 9	0.000 8	0.220 7	0.448 5	0.050 9	0.000 2	0.000 1	0.000 7	0.000 6	0.032 9	0.000 4	0.000 3	0.396 4	0.000 8	0.573 8	0.000 9	0.228 7	0.747 8	0.000 4	0.000 1	0.573 9	0.021 9	0.000 7	0.000 7	0.000 4	0.000 7	0.500 8	0.573 7	0.000 6	0.000 9	0.125 8	0.592 6	0.364 9	0.000 7	0.450 9	0.000 6	0.364 5	0.000 1	0.000 7	0.000 3	0.340 7	0.000 3	0.000 6	0.000 1	0.610 7	0.833 3	0.221 3	0.702 8	0.000 6	0.000 4	0.135 9	0.094 8	0.125 3	0.571 8	0.500 7	0.143 9	0.000 4	0.125 7	0.000 3	0.618 5	0.667 8	0.115 9	0.000 5	0.125 6	1.000 1	0.000 5	0.500 5	0.000 2	0.000 3	0.000 2	0.502 8	0.000 2	0.000 1	0.312 8	0.248 9	0.050 8	0.000 9	0.000 7	0.997 4	0.420 6	0.500 7	0.149 9	0.451 2	0.748 6	0.000 1	0.000 5	0.636 6	0.667 9	0.600 5	0.000 1	0.000 6	0.278 9	0.000 1	0.333 7	0.000 9	0.294 6	0.381 9	0.110 7
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Volt-SPFormer	0.475 1	0.630 1	0.451 2	0.314 1	0.772 2	0.068 4	0.500 1	0.000 2	0.125 1	0.000 1	0.107 4	0.524 5	0.742 1	1.000 1	0.994 1	0.400 5	0.500 3	0.019 4	1.000 1	0.410 1	0.667 2	0.500 1	0.423 2	0.811 1	0.412 3	0.250 2	0.281 2	0.000 1	0.000 2	0.519 4	0.541 3	1.000 1	0.000 1	0.331 3	0.000 3	0.841 2	0.638 1	0.806 5	0.000 3	0.014 4	0.241 3	0.245 2	0.333 4	0.028 3	0.000 1	0.817 2	0.825 1	0.250 5	0.799 6	1.000 1	0.847 4	0.129 1	0.294 3	0.702 2	0.000 4	0.304 2	0.755 1	0.000 6	0.750 1	0.400 1	0.923 1	0.482 2	0.900 1	0.208 8	0.319 1	0.750 1	0.823 2	0.000 3	0.510 2	0.200 3	0.000 2	0.500 3	0.500 1	0.300 3	0.903 1	1.000 1	0.564 4	0.372 4	1.000 1	0.787 2	0.449 4	0.250 1	0.000 1	0.600 1	0.026 3	0.375 1	0.000 4	1.000 1	0.455 3	0.400 2	0.878 2	0.641 3	0.612 1	0.894 4	0.000 4	0.000 1	0.800 4	0.078 4	0.008 4	0.500 2	0.056 1	0.278 2	1.000 1	0.797 3	0.500 2	0.585 2	1.000 1	0.869 1	0.735 2	0.056 4	0.768 2	0.043 5	0.714 1	0.000 1	0.500 1	0.250 1	0.683 4	0.000 3	1.000 1	0.000 1	0.853 1	0.944 2	0.255 2	0.923 2	1.000 1	0.002 3	0.224 3	0.499 3	0.250 2	1.000 1	1.000 1	0.857 2	1.000 1	0.613 1	0.000 3	0.818 1	0.857 2	0.343 2	0.000 5	0.209 3	0.629 8	0.025 2	0.500 5	0.000 2	0.000 3	0.000 2	0.725 3	0.000 2	0.000 1	0.716 1	0.666 4	0.651 3	1.000 1	0.500 2	0.990 6	0.565 2	0.750 3	0.699 2	0.167 7	0.930 1	0.000 1	0.019 2	0.784 2	1.000 1	1.000 1	0.000 1	0.099 4	1.000 1	0.000 1	0.472 3	0.764 1	0.546 2	0.621 2	0.452 3
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
DINO3D-Scannet200	0.454 2	0.587 2	0.453 1	0.296 2	0.851 1	0.200 1	0.500 1	0.000 2	0.042 3	0.000 1	0.378 1	0.545 3	0.729 2	1.000 1	0.981 3	0.355 9	1.000 1	0.046 2	0.000 6	0.248 3	0.000 4	0.494 2	0.381 3	0.586 8	0.496 2	0.250 2	0.409 1	0.000 1	0.000 2	0.714 1	0.572 1	1.000 1	0.000 1	0.250 4	0.050 2	0.793 3	0.436 3	0.871 2	0.000 3	0.216 1	0.284 1	0.290 1	0.083 6	0.000 4	0.000 1	0.764 3	0.716 8	0.500 2	0.842 3	1.000 1	0.891 2	0.096 2	0.361 2	0.690 3	0.000 4	0.595 1	0.753 2	0.708 3	0.750 1	0.400 1	0.845 3	0.475 3	0.728 2	0.750 1	0.214 2	0.683 2	0.743 4	0.000 3	0.400 4	0.200 3	0.500 1	0.944 1	0.125 4	0.327 1	0.823 3	0.792 5	0.602 2	0.662 1	0.777 2	0.803 1	0.675 1	0.000 2	0.000 1	0.200 6	0.298 1	0.324 2	0.000 4	0.000 3	0.000 8	0.800 1	0.824 4	0.750 1	0.507 2	0.937 2	0.000 4	0.000 1	0.779 6	0.116 2	0.001 6	0.417 5	0.000 4	0.014 5	1.000 1	0.816 2	0.548 1	0.600 1	0.500 2	0.771 3	0.773 1	0.117 1	0.944 1	0.764 1	0.571 3	0.000 1	0.250 5	0.000 3	1.000 1	0.063 1	1.000 1	0.000 1	0.720 3	0.974 1	0.079 7	0.918 3	0.000 6	0.000 4	0.312 2	0.616 1	0.125 3	1.000 1	1.000 1	0.857 2	0.000 4	0.594 2	0.000 3	0.767 2	0.845 3	0.264 5	0.419 1	0.177 5	0.667 6	0.000 5	0.677 1	0.000 2	0.194 1	0.000 2	0.857 1	0.000 2	0.000 1	0.563 3	0.703 1	0.835 2	0.850 2	0.346 3	0.944 7	0.499 5	0.866 2	0.777 1	0.221 6	0.911 2	0.000 1	0.011 3	0.721 4	0.764 8	0.520 6	0.000 1	0.442 1	0.405 7	0.000 1	0.667 1	0.655 2	0.473 5	0.614 3	0.437 4
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
ODIN - Ins200	0.381 5	0.507 5	0.375 3	0.237 4	0.484 7	0.108 2	0.500 1	0.000 2	0.125 1	0.000 1	0.058 7	0.647 2	0.385 5	0.667 7	0.853 5	0.542 4	1.000 1	0.000 6	1.000 1	0.093 5	0.000 4	0.028 8	0.274 5	0.682 3	0.550 1	0.000 4	0.269 3	0.000 1	0.000 2	0.714 1	0.566 2	1.000 1	0.000 1	0.500 1	0.125 1	0.585 6	0.066 6	0.653 9	0.083 1	0.049 2	0.264 2	0.227 3	0.667 1	0.000 4	0.000 1	0.278 9	0.723 7	0.250 5	0.786 8	1.000 1	0.744 9	0.039 5	0.209 4	0.494 8	0.000 4	0.250 4	0.446 6	0.500 4	0.750 1	0.200 6	0.780 4	0.333 4	0.602 4	0.469 4	0.163 3	0.406 5	0.530 7	0.000 3	0.668 1	0.200 3	0.000 2	0.000 6	0.500 1	0.313 2	0.769 4	1.000 1	0.511 5	0.196 5	0.286 5	0.393 8	0.337 5	0.000 2	0.000 1	0.600 1	0.000 6	0.174 6	0.226 2	0.000 3	0.579 2	0.200 6	0.887 1	0.750 1	0.428 5	0.782 6	0.438 1	0.000 1	0.795 5	0.063 6	0.003 5	0.500 2	0.000 4	0.333 1	1.000 1	0.742 5	0.083 4	0.585 2	0.417 7	0.448 9	0.496 5	0.055 5	0.734 3	0.472 2	0.174 8	0.000 1	0.250 5	0.000 3	0.688 3	0.000 3	1.000 1	0.000 1	0.631 5	0.667 6	0.275 1	0.694 9	1.000 1	0.000 4	0.328 1	0.422 4	0.000 7	1.000 1	0.500 7	0.638 6	0.000 4	0.391 5	0.000 3	0.582 6	0.800 4	0.208 8	0.000 5	0.246 2	0.667 6	0.000 5	0.638 2	0.167 1	0.000 3	0.000 2	0.778 2	0.000 2	0.000 1	0.563 2	0.614 5	0.841 1	0.333 5	0.250 5	0.938 8	0.569 1	0.500 7	0.695 3	0.264 5	0.863 3	0.000 1	0.000 5	0.550 8	1.000 1	0.668 3	0.000 1	0.000 6	0.667 5	0.000 1	0.333 7	0.333 4	0.665 1	0.434 6	0.264 5

Mask3D Scannet200	0.388 4	0.542 4	0.357 5	0.237 5	0.610 4	0.091 3	0.125 9	0.000 2	0.000 4	0.000 1	0.065 6	0.668 1	0.451 3	1.000 1	0.955 4	0.640 2	0.500 3	0.039 3	0.125 5	0.063 6	0.409 3	0.311 4	0.291 4	0.609 5	0.266 4	0.000 4	0.163 5	0.000 1	0.008 1	0.044 6	0.496 4	1.000 1	0.000 1	0.018 6	0.000 3	0.756 4	0.573 2	0.808 4	0.000 3	0.010 5	0.042 7	0.130 7	0.552 2	0.042 2	0.000 1	1.000 1	0.725 6	0.750 1	0.883 1	1.000 1	0.832 6	0.024 6	0.107 5	0.614 6	0.226 1	0.250 4	0.628 5	0.792 1	0.677 5	0.400 1	0.741 5	0.278 5	0.511 5	0.077 9	0.111 4	0.313 6	0.715 5	0.302 1	0.017 7	0.200 3	0.000 2	0.188 4	0.000 5	0.178 6	0.736 5	1.000 1	0.615 1	0.514 3	0.409 4	0.380 9	0.600 2	0.000 2	0.000 1	0.400 3	0.013 5	0.254 3	0.381 1	0.000 3	0.123 7	0.400 2	0.839 3	0.258 5	0.463 4	0.926 3	0.265 2	0.000 1	0.857 2	0.099 3	0.021 3	0.500 2	0.027 2	0.028 4	1.000 1	0.502 9	0.016 5	0.076 8	0.500 2	0.612 4	0.578 4	0.005 6	0.597 5	0.194 4	0.497 4	0.000 1	0.500 1	0.000 3	0.323 8	0.000 3	1.000 1	0.000 1	0.748 2	0.708 4	0.050 8	0.890 4	1.000 1	0.008 2	0.151 7	0.301 5	1.000 1	1.000 1	0.792 6	0.945 1	1.000 1	0.511 3	0.004 2	0.753 3	0.776 6	0.287 4	0.020 4	0.003 8	0.974 3	0.033 1	0.412 9	0.000 2	0.000 3	0.000 2	0.667 5	0.000 2	0.000 1	0.491 5	0.676 3	0.352 5	0.335 4	0.060 6	0.822 9	0.527 4	1.000 1	0.517 5	0.606 1	0.853 4	0.000 1	0.004 4	0.806 1	1.000 1	0.727 2	0.000 1	0.042 5	0.739 4	0.000 1	0.399 6	0.391 3	0.504 4	0.591 4	0.571 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023

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
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

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

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

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.
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
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
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
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

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
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
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

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

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

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

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
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

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

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

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

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
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]
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	0.893 114	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

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

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

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
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

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	0.866 117	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

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

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	0.625 109	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
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

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

HPEIN	0.618 92	0.729 76	0.668 100	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	0.667 101	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	0.659 104	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	0.609 113	0.445 119	0.517 98	0.643 114	0.366 102	0.714 79	0.456 103	0.468 93	0.870 116	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	0.902 113	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	0.664 102	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	0.661 103	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	0.300 110	0.477 111	0.505 89	0.358 109	0.903 112	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	0.225 121	0.705 83	0.434 108	0.293 115	0.815 119	0.348 105	0.241 72	0.499 93	0.669 79	0.507 105	0.649 100	0.442 114	0.796 99	0.602 119	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	0.591 116	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	0.349 119

Online SegFusion	0.515 108	0.607 105	0.644 107	0.579 108	0.434 108	0.630 116	0.353 104	0.628 97	0.440 106	0.410 103	0.762 122	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	0.608 114	0.424 121	0.478 103	0.690 107	0.246 117	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	0.644 107	0.560 110	0.420 110	0.711 106	0.229 119	0.414 112	0.436 107	0.352 111	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	0.538 119	0.643 99	0.424 109	0.606 119	0.310 108	0.574 103	0.433 109	0.378 106	0.796 120	0.301 110	0.214 83	0.537 85	0.208 118	0.472 111	0.507 119	0.413 117	0.693 110	0.602 119	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	0.611 112	0.356 123	0.321 119	0.715 105	0.299 112	0.376 116	0.328 119	0.319 113	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	0.604 115	0.578 109	0.380 112	0.682 109	0.291 113	0.106 123	0.483 96	0.258 121	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	0.231 123
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	0.623 110	0.463 117	0.366 114	0.651 112	0.310 108	0.389 115	0.349 117	0.330 112	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	0.394 115
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
PNET2	0.442 115	0.548 112	0.548 118	0.597 107	0.363 115	0.628 117	0.300 110	0.292 118	0.374 114	0.307 114	0.881 115	0.268 115	0.186 96	0.238 117	0.204 119	0.407 115	0.506 120	0.449 111	0.667 113	0.620 118	0.462 113

SurfaceConvPF	0.442 115	0.505 114	0.622 111	0.380 122	0.342 117	0.654 111	0.227 120	0.397 114	0.367 115	0.276 117	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	0.398 114
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutions	0.438 117	0.437 120	0.646 106	0.474 116	0.369 113	0.645 113	0.353 104	0.258 120	0.282 122	0.279 116	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	0.633 117	0.352 118
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	0.647 105	0.522 111	0.324 118	0.488 123	0.077 124	0.712 81	0.353 116	0.401 104	0.636 124	0.281 113	0.176 99	0.340 110	0.565 93	0.175 123	0.551 113	0.398 118	0.370 124	0.602 119	0.361 117

SPLAT Net	0.393 119	0.472 119	0.511 120	0.606 104	0.311 120	0.656 110	0.245 118	0.405 113	0.328 119	0.197 122	0.927 101	0.227 120	0.000 124	0.001 125	0.249 114	0.271 122	0.510 117	0.383 120	0.593 118	0.699 110	0.267 121
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	0.491 121	0.432 120	0.358 116	0.612 118	0.274 115	0.116 122	0.411 111	0.265 118	0.904 111	0.229 119	0.079 117	0.250 115	0.185 120	0.320 120	0.510 117	0.385 119	0.548 119	0.597 122	0.394 115

PointNet++	0.339 121	0.584 107	0.478 122	0.458 118	0.256 122	0.360 124	0.250 116	0.247 121	0.278 123	0.261 120	0.677 123	0.183 121	0.117 113	0.212 121	0.145 122	0.364 117	0.346 124	0.232 124	0.548 119	0.523 123	0.252 122
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
GrowSP++	0.323 122	0.114 124	0.589 117	0.499 113	0.147 124	0.555 120	0.290 114	0.336 117	0.290 121	0.262 119	0.865 118	0.102 124	0.000 124	0.037 123	0.000 125	0.000 125	0.462 121	0.381 121	0.389 123	0.664 116	0.473 111

SSC-UNet	0.308 123	0.353 121	0.290 124	0.278 124	0.166 123	0.553 121	0.169 123	0.286 119	0.147 124	0.148 124	0.908 109	0.182 122	0.064 118	0.023 124	0.018 124	0.354 118	0.363 122	0.345 122	0.546 121	0.685 111	0.278 120

ScanNet	0.306 124	0.203 123	0.366 123	0.501 112	0.311 120	0.524 122	0.211 122	0.002 125	0.342 118	0.189 123	0.786 121	0.145 123	0.102 114	0.245 116	0.152 121	0.318 121	0.348 123	0.300 123	0.460 122	0.437 124	0.182 124
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 125	0.000 125	0.041 125	0.172 125	0.030 125	0.062 125	0.001 125	0.035 124	0.004 125	0.051 125	0.143 125	0.019 125	0.003 123	0.041 122	0.050 123	0.003 124	0.054 125	0.018 125	0.005 125	0.264 125	0.082 125

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

Method	avg ap 50%	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	window

Volt-SPFormerScanNet	0.827 1	1.000 1	0.981 6	0.975 1	0.801 1	0.940 4	0.426 24	0.693 30	0.752 13	0.762 7	0.800 1	0.804 2	0.855 1	0.959 48	0.745 23	0.879 7	0.806 7	0.997 43	0.710 1
Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus, Bastian Leibe: Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding.
Competitor-MAFT	0.816 2	1.000 1	0.983 4	0.872 12	0.718 6	0.941 3	0.588 5	0.652 42	0.819 3	0.776 3	0.720 7	0.780 7	0.769 12	1.000 1	0.797 11	0.813 32	0.798 9	1.000 1	0.659 5

PointRel	0.816 2	1.000 1	0.971 10	0.908 7	0.743 3	0.923 11	0.573 9	0.714 22	0.695 21	0.734 11	0.747 3	0.725 14	0.809 2	1.000 1	0.814 9	0.899 5	0.820 3	1.000 1	0.610 20
: Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation. CVPR 2025
Spherical Mask(CtoF)	0.812 4	1.000 1	0.973 9	0.852 16	0.718 7	0.917 13	0.574 7	0.677 32	0.748 14	0.729 15	0.715 10	0.795 4	0.809 2	1.000 1	0.831 4	0.854 13	0.787 13	1.000 1	0.638 9

PointComp	0.811 5	0.850 61	0.969 11	0.864 14	0.739 4	0.946 2	0.539 16	0.671 35	0.835 2	0.700 19	0.742 4	0.817 1	0.766 13	1.000 1	0.755 21	0.909 1	0.808 6	1.000 1	0.687 3

EV3D	0.811 5	1.000 1	0.968 12	0.852 16	0.717 8	0.921 12	0.574 8	0.677 32	0.748 14	0.730 14	0.703 16	0.795 4	0.809 2	1.000 1	0.831 4	0.854 13	0.778 17	1.000 1	0.638 10

VDG-Uni3DSeg	0.804 7	1.000 1	0.990 1	0.886 10	0.688 21	0.912 15	0.602 2	0.703 26	0.786 8	0.771 4	0.708 14	0.700 19	0.669 27	0.981 41	0.789 17	0.903 2	0.772 21	1.000 1	0.609 21

SIM3D	0.803 8	1.000 1	0.967 13	0.863 15	0.692 20	0.924 10	0.552 13	0.732 20	0.667 26	0.732 13	0.662 20	0.796 3	0.789 10	1.000 1	0.803 10	0.864 10	0.766 24	1.000 1	0.643 7

OneFormer3D	0.801 9	1.000 1	0.973 8	0.909 6	0.698 16	0.928 8	0.582 6	0.668 38	0.685 22	0.780 2	0.687 18	0.698 23	0.702 16	1.000 1	0.794 13	0.900 4	0.784 15	0.986 56	0.635 11
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
Competitor-SPFormer	0.800 10	1.000 1	0.986 3	0.845 18	0.705 14	0.915 14	0.532 17	0.733 19	0.757 12	0.733 12	0.708 13	0.698 22	0.648 39	0.981 41	0.890 1	0.830 23	0.796 10	0.997 43	0.644 6

InsSSM	0.799 11	1.000 1	0.915 16	0.710 45	0.729 5	0.925 9	0.664 1	0.670 36	0.770 9	0.766 5	0.739 5	0.737 10	0.700 17	1.000 1	0.792 14	0.829 25	0.815 4	0.997 43	0.625 13
Lei Yao, Yi Wang, Moyun Liu, Lap-Pui Chau: SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation. TCSVT, 2024
DCD	0.798 12	1.000 1	0.878 24	0.792 30	0.693 19	0.936 5	0.596 3	0.685 31	0.663 28	0.736 9	0.717 8	0.788 6	0.693 22	1.000 1	0.825 7	0.840 19	0.837 1	1.000 1	0.689 2

TST3D	0.795 13	1.000 1	0.929 15	0.918 5	0.709 11	0.884 24	0.596 4	0.704 25	0.769 10	0.734 10	0.644 25	0.699 21	0.751 14	1.000 1	0.794 12	0.876 9	0.757 27	0.997 43	0.550 37
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
MG-Former	0.791 14	1.000 1	0.980 7	0.837 21	0.626 30	0.897 17	0.543 15	0.759 14	0.800 7	0.766 6	0.659 21	0.769 9	0.697 20	1.000 1	0.791 15	0.707 53	0.791 12	1.000 1	0.610 19

ExtMask3D	0.789 15	1.000 1	0.988 2	0.756 38	0.706 13	0.912 16	0.429 23	0.647 44	0.806 6	0.755 8	0.673 19	0.689 24	0.772 11	1.000 1	0.789 16	0.852 15	0.811 5	1.000 1	0.617 16

UniPerception	0.787 16	1.000 1	0.909 17	0.768 35	0.687 22	0.947 1	0.551 14	0.714 21	0.843 1	0.696 20	0.713 12	0.773 8	0.607 45	0.981 41	0.690 30	0.878 8	0.775 20	1.000 1	0.640 8

Queryformer	0.787 16	1.000 1	0.933 14	0.601 55	0.754 2	0.886 22	0.558 12	0.661 40	0.767 11	0.665 23	0.716 9	0.639 30	0.808 6	1.000 1	0.844 3	0.897 6	0.804 8	1.000 1	0.624 14

MAFT	0.786 18	1.000 1	0.894 22	0.807 25	0.694 18	0.893 20	0.486 19	0.674 34	0.740 16	0.786 1	0.704 15	0.727 13	0.739 15	1.000 1	0.707 28	0.849 17	0.756 28	1.000 1	0.685 4

KmaxOneFormerNet	0.783 19	0.903 59	0.981 5	0.794 29	0.706 12	0.931 7	0.561 11	0.701 27	0.706 19	0.727 16	0.697 17	0.731 12	0.689 24	1.000 1	0.856 2	0.750 44	0.761 26	1.000 1	0.599 25

Mask3D	0.780 20	1.000 1	0.786 48	0.716 43	0.696 17	0.885 23	0.500 18	0.714 22	0.810 5	0.672 22	0.715 10	0.679 25	0.809 2	1.000 1	0.831 4	0.833 22	0.787 13	1.000 1	0.602 23
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SPFormer	0.770 21	0.903 59	0.903 19	0.806 26	0.609 37	0.886 21	0.568 10	0.815 6	0.705 20	0.711 17	0.655 22	0.652 29	0.685 25	1.000 1	0.789 18	0.809 33	0.776 19	1.000 1	0.583 29
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SoftGroup++	0.769 22	1.000 1	0.803 41	0.937 2	0.684 23	0.865 26	0.213 40	0.870 2	0.664 27	0.571 30	0.758 2	0.702 18	0.807 7	1.000 1	0.653 36	0.902 3	0.792 11	1.000 1	0.626 12

SoftGroup	0.761 23	1.000 1	0.808 37	0.845 18	0.716 9	0.862 28	0.243 37	0.824 4	0.655 30	0.620 24	0.734 6	0.699 20	0.791 9	0.981 41	0.716 25	0.844 18	0.769 22	1.000 1	0.594 27
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
ISBNet	0.757 24	1.000 1	0.904 18	0.731 41	0.678 24	0.895 18	0.458 21	0.644 46	0.670 25	0.710 18	0.620 30	0.732 11	0.650 29	1.000 1	0.756 20	0.778 36	0.779 16	1.000 1	0.614 17
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
TD3D	0.751 25	1.000 1	0.774 49	0.867 13	0.621 32	0.934 6	0.404 25	0.706 24	0.812 4	0.605 27	0.633 28	0.626 31	0.690 23	1.000 1	0.640 38	0.820 28	0.777 18	1.000 1	0.612 18
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
PBNet	0.747 26	1.000 1	0.818 33	0.837 22	0.713 10	0.844 30	0.457 22	0.647 44	0.711 18	0.614 25	0.617 32	0.657 28	0.650 29	1.000 1	0.692 29	0.822 27	0.765 25	1.000 1	0.595 26
Weiguang Zhao, Yuyao Yan, Chaolong Yang, Jianan Ye, Xi Yang, Kaizhu Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
GraphCut	0.732 27	1.000 1	0.788 46	0.724 42	0.642 29	0.859 29	0.248 36	0.787 11	0.618 33	0.596 28	0.653 24	0.722 16	0.583 52	1.000 1	0.766 19	0.861 11	0.825 2	1.000 1	0.504 43

IPCA-Inst	0.731 28	1.000 1	0.788 47	0.884 11	0.698 15	0.788 46	0.252 35	0.760 13	0.646 31	0.511 38	0.637 27	0.665 27	0.804 8	1.000 1	0.644 37	0.778 37	0.747 30	1.000 1	0.561 33

TopoSeg	0.725 29	1.000 1	0.806 40	0.933 3	0.668 26	0.758 51	0.272 34	0.734 18	0.630 32	0.549 34	0.654 23	0.606 32	0.697 21	0.966 47	0.612 42	0.839 20	0.754 29	1.000 1	0.573 30

DKNet	0.718 30	1.000 1	0.814 34	0.782 31	0.619 34	0.872 25	0.224 38	0.751 16	0.569 37	0.677 21	0.585 37	0.724 15	0.633 41	0.981 41	0.515 52	0.819 29	0.736 31	1.000 1	0.617 15
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
SSEC	0.707 31	1.000 1	0.850 26	0.924 4	0.648 27	0.747 54	0.162 42	0.862 3	0.572 36	0.520 36	0.624 29	0.549 35	0.649 38	1.000 1	0.560 47	0.706 54	0.768 23	1.000 1	0.591 28

HAIS	0.699 32	1.000 1	0.849 27	0.820 23	0.675 25	0.808 40	0.279 32	0.757 15	0.465 43	0.517 37	0.596 34	0.559 34	0.600 46	1.000 1	0.654 35	0.767 39	0.676 35	0.994 52	0.560 34
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNet	0.698 33	1.000 1	0.697 65	0.888 9	0.556 44	0.803 41	0.387 26	0.626 48	0.417 48	0.556 33	0.585 38	0.702 17	0.600 46	1.000 1	0.824 8	0.720 52	0.692 33	1.000 1	0.509 42
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
DualGroup	0.694 34	1.000 1	0.799 43	0.811 24	0.622 31	0.817 35	0.376 27	0.805 9	0.590 35	0.487 42	0.568 41	0.525 39	0.650 29	0.835 60	0.600 43	0.829 24	0.655 38	1.000 1	0.526 39

ODIN - Ins	0.693 35	1.000 1	0.880 23	0.647 50	0.620 33	0.779 48	0.336 29	0.501 63	0.681 23	0.577 29	0.595 35	0.679 26	0.683 26	1.000 1	0.709 27	0.816 31	0.637 42	0.770 72	0.557 35
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
SphereSeg	0.680 36	1.000 1	0.856 25	0.744 39	0.618 35	0.893 19	0.151 43	0.651 43	0.713 17	0.537 35	0.579 40	0.430 49	0.651 28	1.000 1	0.389 63	0.744 47	0.697 32	0.991 54	0.601 24

DANCENET	0.680 36	1.000 1	0.807 38	0.733 40	0.600 38	0.768 50	0.375 28	0.543 56	0.538 38	0.610 26	0.599 33	0.498 40	0.632 43	0.981 41	0.739 24	0.856 12	0.633 45	0.882 67	0.454 52

Box2Mask	0.677 38	1.000 1	0.847 28	0.771 33	0.509 53	0.816 36	0.277 33	0.558 55	0.482 40	0.562 32	0.640 26	0.448 45	0.700 17	1.000 1	0.666 31	0.852 16	0.578 52	0.997 43	0.488 47
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
OccuSeg+instance	0.672 39	1.000 1	0.758 57	0.682 47	0.576 42	0.842 31	0.477 20	0.504 62	0.524 39	0.567 31	0.585 39	0.451 44	0.557 54	1.000 1	0.751 22	0.797 34	0.563 55	1.000 1	0.467 51
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group	0.664 40	1.000 1	0.822 32	0.764 37	0.616 36	0.815 37	0.139 47	0.694 29	0.597 34	0.459 46	0.566 42	0.599 33	0.600 46	0.516 70	0.715 26	0.819 30	0.635 43	1.000 1	0.603 22
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
INS-Conv-instance	0.657 41	1.000 1	0.760 55	0.667 49	0.581 40	0.863 27	0.323 30	0.655 41	0.477 41	0.473 44	0.549 44	0.432 48	0.650 29	1.000 1	0.655 34	0.738 48	0.585 51	0.944 59	0.472 50

CSC-Pretrained	0.648 42	1.000 1	0.810 35	0.768 34	0.523 51	0.813 38	0.143 46	0.819 5	0.389 51	0.422 55	0.511 48	0.443 46	0.650 29	1.000 1	0.624 40	0.732 49	0.634 44	1.000 1	0.375 59

PE	0.645 43	1.000 1	0.773 51	0.798 28	0.538 46	0.786 47	0.088 55	0.799 10	0.350 55	0.435 53	0.547 45	0.545 36	0.646 40	0.933 50	0.562 46	0.761 42	0.556 60	0.997 43	0.501 45
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN	0.643 44	1.000 1	0.758 56	0.582 61	0.539 45	0.826 34	0.046 60	0.765 12	0.372 53	0.436 52	0.588 36	0.539 38	0.650 29	1.000 1	0.577 44	0.750 45	0.653 40	0.997 43	0.495 46
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
Dyco3D	0.641 45	1.000 1	0.841 29	0.893 8	0.531 48	0.802 42	0.115 52	0.588 53	0.448 45	0.438 50	0.537 47	0.430 50	0.550 55	0.857 52	0.534 50	0.764 41	0.657 37	0.987 55	0.568 31
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN	0.638 46	1.000 1	0.895 21	0.800 27	0.480 57	0.676 59	0.144 45	0.737 17	0.354 54	0.447 47	0.400 61	0.365 56	0.700 17	1.000 1	0.569 45	0.836 21	0.599 47	1.000 1	0.473 49

PointGroup	0.636 47	1.000 1	0.765 52	0.624 52	0.505 55	0.797 43	0.116 51	0.696 28	0.384 52	0.441 48	0.559 43	0.476 42	0.596 49	1.000 1	0.666 31	0.756 43	0.556 59	0.997 43	0.513 41
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]
DD-UNet+Group	0.635 48	0.667 63	0.797 45	0.714 44	0.562 43	0.774 49	0.146 44	0.810 8	0.429 47	0.476 43	0.546 46	0.399 52	0.633 41	1.000 1	0.632 39	0.722 51	0.609 46	1.000 1	0.514 40
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
Mask3D_evaluation	0.631 49	1.000 1	0.829 31	0.606 54	0.646 28	0.836 32	0.068 56	0.511 60	0.462 44	0.507 39	0.619 31	0.389 54	0.610 44	1.000 1	0.432 58	0.828 26	0.673 36	0.788 71	0.552 36

DENet	0.629 50	1.000 1	0.797 44	0.608 53	0.589 39	0.627 63	0.219 39	0.882 1	0.310 57	0.402 60	0.383 63	0.396 53	0.650 29	1.000 1	0.663 33	0.543 71	0.691 34	1.000 1	0.568 32

3D-MPA	0.611 51	1.000 1	0.833 30	0.765 36	0.526 50	0.756 52	0.136 49	0.588 53	0.470 42	0.438 51	0.432 57	0.358 58	0.650 29	0.857 52	0.429 59	0.765 40	0.557 58	1.000 1	0.430 54
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
OSIS	0.605 52	1.000 1	0.801 42	0.599 56	0.535 47	0.728 56	0.286 31	0.436 67	0.679 24	0.491 40	0.433 55	0.256 60	0.404 67	0.857 52	0.620 41	0.724 50	0.510 65	1.000 1	0.539 38

AOIA	0.601 53	1.000 1	0.761 54	0.687 46	0.485 56	0.828 33	0.008 67	0.663 39	0.405 50	0.405 59	0.425 58	0.490 41	0.596 49	0.714 63	0.553 49	0.779 35	0.597 48	0.992 53	0.424 56

PCJC	0.578 54	1.000 1	0.810 36	0.583 60	0.449 60	0.813 39	0.042 61	0.603 51	0.341 56	0.490 41	0.465 52	0.410 51	0.650 29	0.835 60	0.264 69	0.694 58	0.561 56	0.889 64	0.504 44

SSEN	0.575 55	1.000 1	0.761 53	0.473 63	0.477 58	0.795 44	0.066 57	0.529 58	0.658 29	0.460 45	0.461 53	0.380 55	0.331 69	0.859 51	0.401 62	0.692 60	0.653 39	1.000 1	0.348 61
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RWSeg	0.567 56	0.528 73	0.708 64	0.626 51	0.580 41	0.745 55	0.063 58	0.627 47	0.240 61	0.400 61	0.497 49	0.464 43	0.515 56	1.000 1	0.475 54	0.745 46	0.571 53	1.000 1	0.429 55

NeuralBF	0.555 57	0.667 63	0.896 20	0.843 20	0.517 52	0.751 53	0.029 62	0.519 59	0.414 49	0.439 49	0.465 51	0.000 79	0.484 58	0.857 52	0.287 67	0.693 59	0.651 41	1.000 1	0.485 48
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
MTML	0.549 58	1.000 1	0.807 39	0.588 59	0.327 65	0.647 61	0.004 69	0.815 7	0.180 64	0.418 56	0.364 65	0.182 63	0.445 61	1.000 1	0.442 57	0.688 61	0.571 54	1.000 1	0.396 57
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
ClickSeg_Instance	0.539 59	1.000 1	0.621 68	0.300 66	0.530 49	0.698 57	0.127 50	0.533 57	0.222 62	0.430 54	0.400 60	0.365 56	0.574 53	0.938 49	0.472 55	0.659 63	0.543 61	0.944 59	0.347 62

One_Thing_One_Click	0.529 60	0.667 63	0.718 60	0.777 32	0.399 61	0.683 58	0.000 72	0.669 37	0.138 67	0.391 62	0.374 64	0.539 37	0.360 68	0.641 67	0.556 48	0.774 38	0.593 49	0.997 43	0.251 67
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Sparse R-CNN	0.515 61	1.000 1	0.538 73	0.282 67	0.468 59	0.790 45	0.173 41	0.345 69	0.429 46	0.413 58	0.484 50	0.176 64	0.595 51	0.591 68	0.522 51	0.668 62	0.476 66	0.986 57	0.327 63

Occipital-SCS	0.512 62	1.000 1	0.716 61	0.509 62	0.506 54	0.611 64	0.092 54	0.602 52	0.177 65	0.346 65	0.383 62	0.165 65	0.442 62	0.850 59	0.386 64	0.618 67	0.543 62	0.889 64	0.389 58

3D-BoNet	0.488 63	1.000 1	0.672 67	0.590 58	0.301 67	0.484 74	0.098 53	0.620 49	0.306 58	0.341 66	0.259 69	0.125 67	0.434 64	0.796 62	0.402 61	0.499 73	0.513 64	0.909 63	0.439 53
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
PanopticFusion-inst	0.478 64	0.667 63	0.712 63	0.595 57	0.259 70	0.550 70	0.000 72	0.613 50	0.175 66	0.250 71	0.434 54	0.437 47	0.411 66	0.857 52	0.485 53	0.591 70	0.267 76	0.944 59	0.359 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)
SPG_WSIS	0.470 65	0.667 63	0.685 66	0.677 48	0.372 63	0.562 68	0.000 72	0.482 64	0.244 60	0.316 68	0.298 66	0.052 74	0.442 63	0.857 52	0.267 68	0.702 55	0.559 57	1.000 1	0.287 65

SALoss-ResNet	0.459 66	1.000 1	0.737 59	0.159 77	0.259 69	0.587 66	0.138 48	0.475 65	0.217 63	0.416 57	0.408 59	0.128 66	0.315 70	0.714 63	0.411 60	0.536 72	0.590 50	0.873 68	0.304 64
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)
MASC	0.447 67	0.528 73	0.555 71	0.381 64	0.382 62	0.633 62	0.002 70	0.509 61	0.260 59	0.361 64	0.432 56	0.327 59	0.451 60	0.571 69	0.367 65	0.639 65	0.386 67	0.980 58	0.276 66
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_ins	0.445 68	0.667 63	0.773 50	0.185 74	0.317 66	0.656 60	0.000 72	0.407 68	0.134 68	0.381 63	0.267 68	0.217 62	0.476 59	0.714 63	0.452 56	0.629 66	0.514 63	1.000 1	0.222 70
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
3D-SIS	0.382 69	1.000 1	0.432 76	0.245 69	0.190 71	0.577 67	0.013 66	0.263 71	0.033 74	0.320 67	0.240 70	0.075 70	0.422 65	0.857 52	0.117 74	0.699 56	0.271 75	0.883 66	0.235 69
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3D	0.323 70	0.667 63	0.542 72	0.264 68	0.157 74	0.550 69	0.000 72	0.205 74	0.009 76	0.270 70	0.218 71	0.075 70	0.500 57	0.688 66	0.007 80	0.698 57	0.301 72	0.459 77	0.200 71
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone	0.319 71	0.667 63	0.715 62	0.233 70	0.189 72	0.479 75	0.008 67	0.218 72	0.067 73	0.201 73	0.173 72	0.107 68	0.123 75	0.438 71	0.150 71	0.615 68	0.355 68	0.916 62	0.093 79

R-PointNet	0.306 72	0.500 75	0.405 77	0.311 65	0.348 64	0.589 65	0.054 59	0.068 77	0.126 69	0.283 69	0.290 67	0.028 75	0.219 73	0.214 74	0.331 66	0.396 77	0.275 73	0.821 70	0.245 68

Region-18class	0.284 73	0.250 79	0.751 58	0.228 72	0.270 68	0.521 71	0.000 72	0.468 66	0.008 78	0.205 72	0.127 73	0.000 79	0.068 77	0.070 78	0.262 70	0.652 64	0.323 70	0.740 73	0.173 72

SemRegionNet-20cls	0.250 74	0.333 76	0.613 69	0.229 71	0.163 73	0.493 72	0.000 72	0.304 70	0.107 70	0.147 76	0.100 75	0.052 73	0.231 71	0.119 76	0.039 76	0.445 75	0.325 69	0.654 74	0.141 75

tmp	0.248 75	0.667 63	0.437 75	0.188 73	0.153 75	0.491 73	0.000 72	0.208 73	0.094 72	0.153 75	0.099 76	0.057 72	0.217 74	0.119 76	0.039 76	0.466 74	0.302 71	0.640 75	0.140 76

3D-BEVIS	0.248 75	0.667 63	0.566 70	0.076 78	0.035 80	0.394 78	0.027 64	0.035 79	0.098 71	0.099 78	0.030 79	0.025 76	0.098 76	0.375 73	0.126 73	0.604 69	0.181 78	0.854 69	0.171 73
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sem_Recon_ins	0.227 77	0.764 62	0.486 74	0.069 79	0.098 77	0.426 77	0.017 65	0.067 78	0.015 75	0.172 74	0.100 74	0.096 69	0.054 79	0.183 75	0.135 72	0.366 78	0.260 77	0.614 76	0.168 74

ASIS	0.199 78	0.333 76	0.253 79	0.167 76	0.140 76	0.438 76	0.000 72	0.177 75	0.008 77	0.121 77	0.069 77	0.004 78	0.231 72	0.429 72	0.036 78	0.445 76	0.273 74	0.333 79	0.119 78

Sgpn_scannet	0.143 79	0.208 80	0.390 78	0.169 75	0.065 78	0.275 79	0.029 63	0.069 76	0.000 79	0.087 79	0.043 78	0.014 77	0.027 80	0.000 79	0.112 75	0.351 79	0.168 79	0.438 78	0.138 77

MaskRCNN 2d->3d Proj	0.058 80	0.333 76	0.002 80	0.000 80	0.053 79	0.002 80	0.002 71	0.021 80	0.000 79	0.045 80	0.024 80	0.238 61	0.065 78	0.000 79	0.014 79	0.107 80	0.020 80	0.110 80	0.006 80

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 50%	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	window

EMSANet (Instance)	0.380 1	0.549 3	0.651 1	0.147 1	0.397 3	0.399 1	0.167 2	0.437 3	0.319 2	0.210 1	0.301 1	0.235 1	0.463 2	0.245 2	0.372 3	0.511 1	0.296 2	0.876 1	0.268 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
FKNet	0.368 2	0.588 1	0.618 2	0.099 3	0.466 1	0.395 2	0.108 3	0.548 1	0.157 3	0.175 2	0.268 2	0.096 4	0.439 3	0.343 1	0.420 2	0.500 3	0.317 1	0.855 3	0.234 2

UniDet_RVC	0.358 3	0.554 2	0.543 3	0.128 2	0.402 2	0.381 3	0.200 1	0.461 2	0.328 1	0.138 3	0.232 3	0.148 3	0.466 1	0.109 3	0.538 1	0.506 2	0.294 3	0.862 2	0.159 3

MaskRCNN_ScanNet	0.227 4	0.228 4	0.381 4	0.013 4	0.237 4	0.339 4	0.089 4	0.339 4	0.150 4	0.134 4	0.143 4	0.179 2	0.255 4	0.053 4	0.331 4	0.244 4	0.154 4	0.687 4	0.127 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