Benchmark Results - ScanNet Benchmark

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

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

CeCo	0.340 6	0.551 8	0.247 12	0.181 5	0.784 12	0.661 13	0.939 12	0.564 5	0.624 12	0.721 11	0.484 4	0.429 4	0.575 4	0.027 6	0.774 11	0.503 13	0.753 6	0.242 12	0.656 11	0.945 8	0.534 8	0.865 6	0.860 9	0.177 16	0.616 7	0.400 4	0.818 2	0.579 1	0.615 10	0.367 13	0.408 7	0.726 14	0.633 6	0.162 1	0.360 8	0.619 2	0.000 1	0.828 6	0.873 11	0.924 2	0.109 11	0.083 3	0.564 5	0.057 16	0.475 12	0.266 10	0.781 1	0.767 8	0.257 7	0.100 12	0.825 9	0.663 10	0.048 14	0.620 13	0.551 10	0.595 14	0.532 7	0.692 8	0.246 5	0.000 3	0.213 7	0.615 1	0.861 7	0.376 7	0.900 6	0.000 4	0.102 13	0.660 7	0.321 14	0.547 4	0.226 12	0.000 1	0.311 12	0.742 3	0.011 3	0.006 8	0.000 1	0.000 6	0.546 14	0.824 9	0.345 13	0.665 3	0.450 5	0.435 1	0.683 5	0.411 8	0.338 1	0.000 7	0.000 1	0.030 7	0.000 4	0.068 8	0.892 7	0.000 1	0.063 4	0.000 10	0.257 12	0.304 13	0.387 5	0.079 12	0.228 6	0.190 11	0.000 14	0.586 1	0.347 4	0.133 8	0.000 5	0.037 12	0.377 11	0.000 1	0.384 7	0.006 15	0.003 12	0.421 3	0.410 10	0.643 7	0.171 7	0.121 7	0.142 13	0.000 1	0.510 11	0.447 9	0.474 13	0.000 1	0.000 8	0.286 3	0.083 12	0.000 6	0.000 9	0.603 1	0.096 7	0.063 6	0.000 11	0.000 2	0.000 3	0.898 3	0.000 1	0.429 7	0.000 1	0.400 1	0.550 3	0.000 1	0.633 6	0.000 1	0.000 1	0.377 4	0.000 14	0.916 5	0.000 8	0.000 8	0.000 1	0.000 6	0.000 1	0.102 12	0.499 10	0.296 13	0.463 5	0.089 6	0.304 1	0.740 2	0.401 15	0.010 7	0.000 1	0.560 4	0.000 2	0.000 2	0.709 2	0.652 10	0.000 2	0.000 1	0.000 1	0.143 8	0.000 8	0.000 4	0.609 3	0.000 1
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
PPT-SpUNet-F.T.	0.332 11	0.556 5	0.270 7	0.123 13	0.816 6	0.682 9	0.946 8	0.549 7	0.657 10	0.756 7	0.459 6	0.376 9	0.550 8	0.001 10	0.807 4	0.616 4	0.727 11	0.267 7	0.691 6	0.942 10	0.530 10	0.872 5	0.874 8	0.330 8	0.542 13	0.374 7	0.792 4	0.400 13	0.673 4	0.572 7	0.433 2	0.793 8	0.623 8	0.008 15	0.351 9	0.594 7	0.000 1	0.783 12	0.876 8	0.833 4	0.213 6	0.000 7	0.537 7	0.091 6	0.519 5	0.304 7	0.620 7	0.942 1	0.264 5	0.124 9	0.855 6	0.695 5	0.086 8	0.646 10	0.506 14	0.658 6	0.535 6	0.715 4	0.314 2	0.000 3	0.241 6	0.608 2	0.897 2	0.359 8	0.858 10	0.000 4	0.076 15	0.611 11	0.392 11	0.509 7	0.378 5	0.000 1	0.579 4	0.565 15	0.000 4	0.000 9	0.000 1	0.000 6	0.755 8	0.806 11	0.661 4	0.572 13	0.350 10	0.181 7	0.660 10	0.300 13	0.000 3	0.000 7	0.000 1	0.023 9	0.000 4	0.042 15	0.930 4	0.000 1	0.000 10	0.077 7	0.584 8	0.392 10	0.339 9	0.185 8	0.171 10	0.308 2	0.006 13	0.563 3	0.256 9	0.150 4	0.000 5	0.002 15	0.345 13	0.000 1	0.045 13	0.197 4	0.063 10	0.323 11	0.453 3	0.600 9	0.163 9	0.037 14	0.349 4	0.000 1	0.672 3	0.679 4	0.753 3	0.000 1	0.000 8	0.000 11	0.117 6	0.000 6	0.000 9	0.291 10	0.000 11	0.000 7	0.039 6	0.000 2	0.000 3	0.899 2	0.000 1	0.374 12	0.000 1	0.000 12	0.545 4	0.000 1	0.634 5	0.000 1	0.000 1	0.074 11	0.223 4	0.914 7	0.000 8	0.021 6	0.000 1	0.000 6	0.000 1	0.112 5	0.498 11	0.649 1	0.383 9	0.095 2	0.135 13	0.449 10	0.432 11	0.008 9	0.000 1	0.518 7	0.000 2	0.000 2	0.000 11	0.796 4	0.000 2	0.000 1	0.000 1	0.138 12	0.000 8	0.000 4	0.000 10	0.000 1
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
ALS-MinkowskiNet	0.414 1	0.610 2	0.322 3	0.271 1	0.852 1	0.710 3	0.973 1	0.572 3	0.719 3	0.795 1	0.477 5	0.506 2	0.601 1	0.000 11	0.804 5	0.646 2	0.804 1	0.344 2	0.777 1	0.984 1	0.671 1	0.879 2	0.936 1	0.342 5	0.632 6	0.449 3	0.817 3	0.475 7	0.723 2	0.798 1	0.376 9	0.832 3	0.693 1	0.031 10	0.564 1	0.510 12	0.000 1	0.893 2	0.905 1	0.672 16	0.314 2	0.000 7	0.718 1	0.153 2	0.542 2	0.397 2	0.726 3	0.752 9	0.252 8	0.226 1	0.916 2	0.800 1	0.047 15	0.807 4	0.769 1	0.709 3	0.630 2	0.769 1	0.217 9	0.000 3	0.285 2	0.598 3	0.846 10	0.535 2	0.956 3	0.000 4	0.137 9	0.784 2	0.464 7	0.463 12	0.230 11	0.000 1	0.598 3	0.662 8	0.000 4	0.087 2	0.000 1	0.135 2	0.900 1	0.780 13	0.703 2	0.741 1	0.571 2	0.149 9	0.697 3	0.646 1	0.000 3	0.076 1	0.000 1	0.025 8	0.000 4	0.106 4	0.981 1	0.000 1	0.043 6	0.113 3	0.888 1	0.248 15	0.404 4	0.252 6	0.314 1	0.220 6	0.245 1	0.466 7	0.366 2	0.159 2	0.000 5	0.149 7	0.690 2	0.000 1	0.531 3	0.253 2	0.285 7	0.460 1	0.440 4	0.813 1	0.230 2	0.283 6	0.159 11	0.000 1	0.728 1	0.666 5	0.958 1	0.000 1	0.021 4	0.252 4	0.118 4	0.000 6	0.445 3	0.223 12	0.285 1	0.194 3	0.390 2	0.000 2	0.475 2	0.842 8	0.000 1	0.455 4	0.000 1	0.250 5	0.458 8	0.000 1	0.865 1	0.000 1	0.000 1	0.635 1	0.359 2	0.972 1	0.087 3	0.447 2	0.000 1	0.000 6	0.000 1	0.129 2	0.532 7	0.446 8	0.503 3	0.071 12	0.135 13	0.699 3	0.717 2	0.097 2	0.000 1	0.665 1	0.000 2	0.000 2	1.000 1	0.752 6	0.000 2	0.000 1	0.000 1	0.142 9	0.200 1	0.259 1	1.000 1	0.000 1

PonderV2 ScanNet200	0.346 5	0.552 7	0.270 8	0.175 6	0.810 8	0.682 9	0.950 4	0.560 6	0.641 11	0.761 4	0.398 11	0.357 10	0.570 7	0.113 2	0.804 5	0.603 6	0.750 7	0.283 4	0.681 7	0.952 6	0.548 5	0.874 4	0.852 11	0.290 10	0.700 2	0.356 10	0.792 4	0.445 9	0.545 12	0.436 11	0.351 12	0.787 9	0.611 9	0.050 9	0.290 13	0.519 11	0.000 1	0.825 7	0.888 4	0.842 3	0.259 5	0.100 2	0.558 6	0.070 13	0.497 8	0.247 13	0.457 12	0.889 3	0.248 9	0.106 11	0.817 11	0.691 6	0.094 7	0.729 6	0.636 7	0.620 12	0.503 11	0.660 12	0.243 6	0.000 3	0.212 8	0.590 4	0.860 8	0.400 5	0.881 8	0.000 4	0.202 2	0.622 10	0.408 10	0.499 8	0.261 10	0.000 1	0.385 9	0.636 10	0.000 4	0.000 9	0.000 1	0.000 6	0.433 15	0.843 7	0.660 6	0.574 12	0.481 3	0.336 4	0.677 7	0.486 5	0.000 3	0.030 3	0.000 1	0.034 6	0.000 4	0.080 7	0.869 9	0.000 1	0.000 10	0.000 10	0.540 9	0.727 3	0.232 15	0.115 9	0.186 8	0.193 9	0.000 14	0.403 11	0.326 6	0.103 12	0.000 5	0.290 4	0.392 10	0.000 1	0.346 8	0.062 10	0.424 6	0.375 7	0.431 5	0.667 5	0.115 13	0.082 10	0.239 7	0.000 1	0.504 13	0.606 6	0.584 11	0.000 1	0.002 6	0.186 8	0.104 10	0.000 6	0.394 4	0.384 7	0.083 8	0.000 7	0.007 8	0.000 2	0.000 3	0.880 4	0.000 1	0.377 11	0.000 1	0.263 3	0.565 2	0.000 1	0.608 8	0.000 1	0.000 1	0.304 7	0.009 8	0.924 3	0.000 8	0.000 8	0.000 1	0.000 6	0.000 1	0.128 3	0.584 3	0.475 7	0.412 7	0.076 10	0.269 3	0.621 5	0.509 8	0.010 7	0.000 1	0.491 10	0.063 1	0.000 2	0.472 4	0.880 2	0.000 2	0.000 1	0.000 1	0.179 5	0.125 3	0.000 4	0.441 6	0.000 1
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
OA-CNN-L_ScanNet200	0.333 10	0.558 4	0.269 9	0.124 12	0.821 5	0.703 4	0.946 8	0.569 4	0.662 6	0.748 10	0.487 3	0.455 3	0.572 6	0.000 11	0.789 8	0.534 10	0.736 10	0.271 6	0.713 4	0.949 7	0.498 14	0.877 3	0.860 9	0.332 7	0.706 1	0.474 2	0.788 6	0.406 12	0.637 6	0.495 10	0.355 11	0.805 7	0.592 13	0.015 14	0.396 5	0.602 6	0.000 1	0.799 9	0.876 8	0.713 13	0.276 4	0.000 7	0.493 11	0.080 8	0.448 14	0.363 5	0.661 4	0.833 6	0.262 6	0.125 8	0.823 10	0.665 9	0.076 10	0.720 8	0.557 9	0.637 9	0.517 9	0.672 11	0.227 7	0.000 3	0.158 11	0.496 5	0.843 11	0.352 9	0.835 12	0.000 4	0.103 12	0.711 5	0.527 3	0.526 5	0.320 8	0.000 1	0.568 6	0.625 11	0.067 1	0.000 9	0.000 1	0.001 5	0.806 7	0.836 8	0.621 9	0.591 7	0.373 8	0.314 5	0.668 8	0.398 9	0.003 2	0.000 7	0.000 1	0.016 15	0.024 3	0.043 14	0.906 6	0.000 1	0.052 5	0.000 10	0.384 11	0.330 12	0.342 7	0.100 10	0.223 7	0.183 12	0.112 6	0.476 5	0.313 7	0.130 10	0.196 3	0.112 11	0.370 12	0.000 1	0.234 10	0.071 9	0.160 8	0.403 5	0.398 11	0.492 14	0.197 5	0.076 11	0.272 5	0.000 1	0.200 16	0.560 8	0.735 6	0.000 1	0.000 8	0.000 11	0.110 8	0.002 5	0.021 8	0.412 6	0.000 11	0.000 7	0.000 11	0.000 2	0.000 3	0.794 10	0.000 1	0.445 6	0.000 1	0.022 10	0.509 6	0.000 1	0.517 14	0.000 1	0.000 1	0.001 15	0.245 3	0.915 6	0.024 4	0.089 5	0.000 1	0.262 2	0.000 1	0.103 11	0.524 8	0.392 11	0.515 2	0.013 16	0.251 4	0.411 12	0.662 3	0.001 11	0.000 1	0.473 12	0.000 2	0.000 2	0.150 5	0.699 9	0.000 2	0.000 1	0.000 1	0.166 6	0.000 8	0.024 3	0.000 10	0.000 1

BFANet ScanNet200	0.360 4	0.553 6	0.293 4	0.193 4	0.827 4	0.689 6	0.970 3	0.528 11	0.661 8	0.753 8	0.436 7	0.378 8	0.469 14	0.042 5	0.810 3	0.654 1	0.760 4	0.266 8	0.659 10	0.973 3	0.574 4	0.849 12	0.897 4	0.382 2	0.546 12	0.372 8	0.698 12	0.491 6	0.617 9	0.526 8	0.436 1	0.764 13	0.476 16	0.101 6	0.409 4	0.585 8	0.000 1	0.835 3	0.901 3	0.810 5	0.102 12	0.000 7	0.688 2	0.096 5	0.483 10	0.264 11	0.612 8	0.591 15	0.358 2	0.161 7	0.863 5	0.707 4	0.128 2	0.814 3	0.669 5	0.629 10	0.563 4	0.651 13	0.258 4	0.000 3	0.194 9	0.494 6	0.806 12	0.394 6	0.953 4	0.000 4	0.233 1	0.757 4	0.508 6	0.556 3	0.476 4	0.000 1	0.573 5	0.741 4	0.000 4	0.000 9	0.000 1	0.000 6	0.000 16	0.852 6	0.678 3	0.616 5	0.460 4	0.338 3	0.710 2	0.534 4	0.000 3	0.025 4	0.000 1	0.043 2	0.000 4	0.056 11	0.493 15	0.000 1	0.000 10	0.109 4	0.785 6	0.590 6	0.298 13	0.282 4	0.143 12	0.262 5	0.053 11	0.526 4	0.337 5	0.215 1	0.000 5	0.135 8	0.510 4	0.000 1	0.596 2	0.043 12	0.511 5	0.321 12	0.459 2	0.772 2	0.124 12	0.060 13	0.266 6	0.000 1	0.574 8	0.568 7	0.653 10	0.000 1	0.093 1	0.298 2	0.239 2	0.000 6	0.516 2	0.129 13	0.284 2	0.000 7	0.431 1	0.000 2	0.000 3	0.848 7	0.000 1	0.492 2	0.000 1	0.376 2	0.522 5	0.000 1	0.469 16	0.000 1	0.000 1	0.330 6	0.151 6	0.875 14	0.000 8	0.254 3	0.000 1	0.000 6	0.000 1	0.088 13	0.661 1	0.481 5	0.255 11	0.105 1	0.139 10	0.666 4	0.641 4	0.000 12	0.000 1	0.614 2	0.000 2	0.000 2	0.000 11	0.921 1	0.000 2	0.000 1	0.000 1	0.497 1	0.000 8	0.000 4	0.000 10	0.000 1

PTv3 ScanNet200	0.393 3	0.592 3	0.330 2	0.216 2	0.851 2	0.687 8	0.971 2	0.586 2	0.755 1	0.752 9	0.505 1	0.404 7	0.575 4	0.000 11	0.848 2	0.616 4	0.761 3	0.349 1	0.738 2	0.978 2	0.546 6	0.860 8	0.926 2	0.346 4	0.654 4	0.384 6	0.828 1	0.523 3	0.699 3	0.583 6	0.387 8	0.822 5	0.688 2	0.118 5	0.474 2	0.603 5	0.000 1	0.832 5	0.903 2	0.753 9	0.140 9	0.000 7	0.650 3	0.109 4	0.520 4	0.457 1	0.497 10	0.871 4	0.281 4	0.192 4	0.887 4	0.748 3	0.168 1	0.727 7	0.733 2	0.740 1	0.644 1	0.714 5	0.190 11	0.000 3	0.256 5	0.449 7	0.914 1	0.514 3	0.759 14	0.337 2	0.172 4	0.692 6	0.617 2	0.636 1	0.325 7	0.000 1	0.641 2	0.782 1	0.000 4	0.065 4	0.000 1	0.000 6	0.842 5	0.903 2	0.661 4	0.662 4	0.612 1	0.405 2	0.731 1	0.566 3	0.000 3	0.000 7	0.000 1	0.017 14	0.301 1	0.088 6	0.941 2	0.000 1	0.077 3	0.000 10	0.717 7	0.790 2	0.310 12	0.026 16	0.264 4	0.349 1	0.220 3	0.397 12	0.366 2	0.115 11	0.000 5	0.337 2	0.463 6	0.000 1	0.531 3	0.218 3	0.593 2	0.455 2	0.469 1	0.708 4	0.210 4	0.592 3	0.108 15	0.000 1	0.728 1	0.682 3	0.671 8	0.000 1	0.000 8	0.407 1	0.136 3	0.022 3	0.575 1	0.436 5	0.259 3	0.428 1	0.048 5	0.000 2	0.000 3	0.879 5	0.000 1	0.480 3	0.000 1	0.133 8	0.597 1	0.000 1	0.690 2	0.000 1	0.000 1	0.009 14	0.000 14	0.921 4	0.000 8	0.151 4	0.000 1	0.000 6	0.000 1	0.109 8	0.494 12	0.622 2	0.394 8	0.073 11	0.141 8	0.798 1	0.528 7	0.026 5	0.000 1	0.551 5	0.000 2	0.000 2	0.134 6	0.717 8	0.000 2	0.000 1	0.000 1	0.188 3	0.000 8	0.000 4	0.791 2	0.000 1
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
OctFormer ScanNet200	0.326 12	0.539 9	0.265 11	0.131 11	0.806 10	0.670 12	0.943 11	0.535 10	0.662 6	0.705 15	0.423 8	0.407 5	0.505 10	0.003 9	0.765 12	0.582 8	0.686 14	0.227 15	0.680 8	0.943 9	0.601 3	0.854 10	0.892 5	0.335 6	0.417 16	0.357 9	0.724 9	0.453 8	0.632 8	0.596 5	0.432 3	0.783 10	0.512 15	0.021 13	0.244 14	0.637 1	0.000 1	0.787 10	0.873 11	0.743 11	0.000 16	0.000 7	0.534 9	0.110 3	0.499 7	0.289 9	0.626 6	0.620 13	0.168 16	0.204 2	0.849 7	0.679 7	0.117 4	0.633 11	0.684 3	0.650 7	0.552 5	0.684 10	0.312 3	0.000 3	0.175 10	0.429 8	0.865 5	0.413 4	0.837 11	0.000 4	0.145 7	0.626 9	0.451 8	0.487 9	0.513 2	0.000 1	0.529 7	0.613 12	0.000 4	0.033 6	0.000 1	0.000 6	0.828 6	0.871 4	0.622 8	0.587 9	0.411 7	0.137 10	0.645 13	0.343 11	0.000 3	0.000 7	0.000 1	0.022 10	0.000 4	0.026 16	0.829 10	0.000 1	0.022 8	0.089 6	0.842 4	0.253 14	0.318 11	0.296 3	0.178 9	0.291 3	0.224 2	0.584 2	0.200 13	0.132 9	0.000 5	0.128 10	0.227 15	0.000 1	0.230 11	0.047 11	0.149 9	0.331 10	0.412 9	0.618 8	0.164 8	0.102 9	0.522 1	0.000 1	0.655 4	0.378 11	0.469 14	0.000 1	0.000 8	0.000 11	0.105 9	0.000 6	0.000 9	0.483 3	0.000 11	0.000 7	0.028 7	0.000 2	0.000 3	0.906 1	0.000 1	0.339 14	0.000 1	0.000 12	0.457 9	0.000 1	0.612 7	0.000 1	0.000 1	0.408 3	0.000 14	0.900 9	0.000 8	0.000 8	0.000 1	0.029 4	0.000 1	0.074 15	0.455 14	0.479 6	0.427 6	0.079 9	0.140 9	0.496 7	0.414 13	0.022 6	0.000 1	0.471 13	0.000 2	0.000 2	0.000 11	0.722 7	0.000 2	0.000 1	0.000 1	0.138 12	0.000 8	0.000 4	0.000 10	0.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
L3DETR-ScanNet_200	0.336 9	0.533 12	0.279 5	0.155 9	0.801 11	0.689 6	0.946 8	0.539 9	0.660 9	0.759 5	0.380 13	0.333 12	0.583 3	0.000 11	0.788 9	0.529 11	0.740 9	0.261 11	0.679 9	0.940 11	0.525 11	0.860 8	0.883 7	0.226 12	0.613 8	0.397 5	0.720 10	0.512 4	0.565 11	0.620 3	0.417 6	0.775 12	0.629 7	0.158 2	0.298 11	0.579 9	0.000 1	0.835 3	0.883 6	0.927 1	0.114 10	0.079 4	0.511 10	0.073 10	0.508 6	0.312 6	0.629 5	0.861 5	0.192 14	0.098 14	0.908 3	0.636 12	0.032 16	0.563 16	0.514 13	0.664 5	0.505 10	0.697 7	0.225 8	0.000 3	0.264 3	0.411 9	0.860 8	0.321 12	0.960 2	0.058 3	0.109 11	0.776 3	0.526 4	0.557 2	0.303 9	0.000 1	0.339 11	0.712 5	0.000 4	0.014 7	0.000 1	0.000 6	0.638 11	0.856 5	0.641 7	0.579 11	0.107 16	0.119 12	0.661 9	0.416 7	0.000 3	0.000 7	0.000 1	0.007 16	0.000 4	0.067 9	0.910 5	0.000 1	0.000 10	0.000 10	0.463 10	0.448 8	0.294 14	0.324 2	0.293 2	0.211 7	0.108 8	0.448 9	0.068 16	0.141 7	0.000 5	0.330 3	0.699 1	0.000 1	0.256 9	0.192 5	0.000 14	0.355 8	0.418 7	0.209 16	0.146 11	0.679 1	0.101 16	0.000 1	0.503 14	0.687 2	0.671 8	0.000 1	0.000 8	0.174 9	0.117 6	0.000 6	0.122 6	0.515 2	0.104 6	0.259 2	0.312 3	0.000 2	0.000 3	0.765 11	0.000 1	0.369 13	0.000 1	0.183 6	0.422 11	0.000 1	0.646 3	0.000 1	0.000 1	0.565 2	0.001 13	0.125 16	0.010 5	0.002 7	0.000 1	0.487 1	0.000 1	0.075 14	0.548 4	0.420 9	0.233 14	0.082 8	0.138 12	0.430 11	0.427 12	0.000 12	0.000 1	0.549 6	0.000 2	0.000 2	0.074 9	0.409 15	0.000 2	0.000 1	0.000 1	0.152 7	0.051 4	0.000 4	0.598 4	0.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
IMFSegNet	0.337 8	0.535 11	0.266 10	0.169 8	0.810 8	0.715 2	0.947 6	0.545 8	0.675 5	0.759 5	0.418 9	0.406 6	0.493 11	0.000 11	0.803 7	0.571 9	0.755 5	0.264 9	0.644 12	0.953 5	0.366 16	0.840 13	0.831 12	0.357 3	0.564 9	0.317 11	0.699 11	0.422 11	0.633 7	0.509 9	0.424 5	0.824 4	0.637 5	0.001 16	0.382 6	0.383 14	0.000 1	0.810 8	0.884 5	0.678 15	0.311 3	0.000 7	0.469 13	0.072 11	0.527 3	0.300 8	0.576 9	0.769 7	0.177 15	0.181 5	0.829 8	0.642 11	0.095 6	0.791 5	0.655 6	0.645 8	0.524 8	0.692 8	0.208 10	0.000 3	0.264 3	0.398 10	0.867 4	0.343 11	0.915 5	0.000 4	0.036 16	0.551 14	0.442 9	0.432 13	0.568 1	0.000 1	0.359 10	0.660 9	0.000 4	0.040 5	0.000 1	0.000 6	0.853 4	0.821 10	0.469 11	0.546 14	0.361 9	0.000 15	0.683 5	0.373 10	0.000 3	0.000 7	0.000 1	0.038 3	0.000 4	0.054 12	0.472 16	0.000 1	0.026 7	0.000 10	0.868 2	0.708 4	0.341 8	0.263 5	0.170 11	0.263 4	0.109 7	0.426 10	0.228 12	0.143 5	0.000 5	0.251 5	0.442 7	0.000 1	0.447 5	0.187 6	0.544 4	0.311 13	0.396 12	0.728 3	0.211 3	0.066 12	0.147 12	0.000 1	0.505 12	0.378 11	0.743 4	0.000 1	0.000 8	0.204 6	0.118 4	0.000 6	0.000 9	0.297 9	0.122 5	0.133 4	0.004 10	0.032 1	0.667 1	0.839 9	0.000 1	0.380 10	0.000 1	0.051 9	0.492 7	0.000 1	0.572 10	0.000 1	0.000 1	0.196 10	0.004 11	0.910 8	0.000 8	0.000 8	0.000 1	0.000 6	0.000 1	0.112 5	0.544 5	0.497 4	0.152 15	0.095 2	0.132 15	0.277 16	0.634 5	0.031 4	0.000 1	0.592 3	0.000 2	0.000 2	0.119 7	0.786 5	0.000 2	0.000 1	0.000 1	0.126 15	0.177 2	0.094 2	0.274 8	0.000 1

AWCS	0.305 13	0.508 13	0.225 13	0.142 10	0.782 13	0.634 16	0.937 13	0.489 14	0.578 13	0.721 11	0.364 14	0.355 11	0.515 9	0.023 7	0.764 13	0.523 12	0.707 13	0.264 9	0.633 13	0.922 12	0.507 13	0.886 1	0.804 14	0.179 14	0.436 15	0.300 13	0.656 15	0.529 2	0.501 14	0.394 12	0.296 15	0.820 6	0.603 10	0.131 4	0.179 16	0.619 2	0.000 1	0.707 15	0.865 13	0.773 6	0.171 7	0.010 6	0.484 12	0.063 14	0.463 13	0.254 12	0.332 15	0.649 12	0.220 11	0.100 12	0.729 13	0.613 14	0.071 12	0.582 14	0.628 8	0.702 4	0.424 14	0.749 2	0.137 14	0.000 3	0.142 13	0.360 11	0.863 6	0.305 13	0.877 9	0.000 4	0.173 3	0.606 12	0.337 13	0.478 10	0.154 14	0.000 1	0.253 13	0.664 7	0.000 4	0.000 9	0.000 1	0.000 6	0.626 12	0.782 12	0.302 15	0.602 6	0.185 13	0.282 6	0.651 11	0.317 12	0.000 3	0.000 7	0.000 1	0.022 10	0.000 4	0.154 1	0.876 8	0.000 1	0.014 9	0.063 9	0.029 16	0.553 7	0.467 3	0.084 11	0.124 13	0.157 15	0.049 12	0.373 13	0.252 10	0.097 13	0.000 5	0.219 6	0.542 3	0.000 1	0.392 6	0.172 8	0.000 14	0.339 9	0.417 8	0.533 13	0.093 14	0.115 8	0.195 9	0.000 1	0.516 10	0.288 15	0.741 5	0.000 1	0.001 7	0.233 5	0.056 13	0.000 6	0.159 5	0.334 8	0.077 9	0.000 7	0.000 11	0.000 2	0.000 3	0.749 12	0.000 1	0.411 8	0.000 1	0.008 11	0.452 10	0.000 1	0.595 9	0.000 1	0.000 1	0.220 9	0.006 9	0.894 11	0.006 6	0.000 8	0.000 1	0.000 6	0.000 1	0.112 5	0.504 9	0.404 10	0.551 1	0.093 5	0.129 16	0.484 8	0.381 16	0.000 12	0.000 1	0.396 14	0.000 2	0.000 2	0.620 3	0.402 16	0.000 2	0.000 1	0.000 1	0.142 9	0.000 8	0.000 4	0.512 5	0.000 1

LGround	0.272 14	0.485 14	0.184 14	0.106 14	0.778 14	0.676 11	0.932 14	0.479 16	0.572 14	0.718 13	0.399 10	0.265 13	0.453 15	0.085 3	0.745 14	0.446 14	0.726 12	0.232 14	0.622 14	0.901 14	0.512 12	0.826 14	0.786 15	0.178 15	0.549 11	0.277 14	0.659 14	0.381 14	0.518 13	0.295 16	0.323 13	0.777 11	0.599 11	0.028 11	0.321 10	0.363 15	0.000 1	0.708 14	0.858 14	0.746 10	0.063 13	0.022 5	0.457 14	0.077 9	0.476 11	0.243 14	0.402 13	0.397 16	0.233 10	0.077 16	0.720 15	0.610 15	0.103 5	0.629 12	0.437 16	0.626 11	0.446 13	0.702 6	0.190 11	0.005 1	0.058 15	0.322 12	0.702 15	0.244 14	0.768 13	0.000 4	0.134 10	0.552 13	0.279 15	0.395 14	0.147 15	0.000 1	0.207 14	0.612 13	0.000 4	0.000 9	0.000 1	0.000 6	0.658 10	0.566 14	0.323 14	0.525 16	0.229 12	0.179 8	0.467 16	0.154 15	0.000 3	0.002 5	0.000 1	0.051 1	0.000 4	0.127 2	0.703 11	0.000 1	0.000 10	0.216 1	0.112 15	0.358 11	0.547 1	0.187 7	0.092 15	0.156 16	0.055 10	0.296 14	0.252 10	0.143 5	0.000 5	0.014 13	0.398 9	0.000 1	0.028 15	0.173 7	0.000 14	0.265 15	0.348 14	0.415 15	0.179 6	0.019 15	0.218 8	0.000 1	0.597 7	0.274 16	0.565 12	0.000 1	0.012 5	0.000 11	0.039 15	0.022 3	0.000 9	0.117 14	0.000 11	0.000 7	0.000 11	0.000 2	0.000 3	0.324 15	0.000 1	0.384 9	0.000 1	0.000 12	0.251 16	0.000 1	0.566 11	0.000 1	0.000 1	0.066 12	0.404 1	0.886 12	0.199 2	0.000 8	0.000 1	0.059 3	0.000 1	0.136 1	0.540 6	0.127 16	0.295 10	0.085 7	0.143 7	0.514 6	0.413 14	0.000 12	0.000 1	0.498 9	0.000 2	0.000 2	0.000 11	0.623 11	0.000 2	0.000 1	0.000 1	0.132 14	0.000 8	0.000 4	0.000 10	0.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
GSTran	0.339 7	0.536 10	0.273 6	0.169 7	0.811 7	0.690 5	0.949 5	0.506 12	0.690 4	0.765 2	0.397 12	0.235 15	0.480 13	0.014 8	0.788 9	0.593 7	0.746 8	0.282 5	0.696 5	0.913 13	0.538 7	0.853 11	0.889 6	0.286 11	0.670 3	0.310 12	0.682 13	0.445 9	0.638 5	0.598 4	0.358 10	0.841 2	0.643 4	0.061 8	0.373 7	0.614 4	0.000 1	0.786 11	0.876 8	0.754 8	0.357 1	0.000 7	0.535 8	0.071 12	0.491 9	0.369 4	0.487 11	0.698 11	0.317 3	0.202 3	0.659 16	0.666 8	0.086 8	0.832 1	0.461 15	0.597 13	0.455 12	0.731 3	0.156 13	0.000 3	0.316 1	0.318 13	0.784 13	0.348 10	0.896 7	0.000 4	0.084 14	0.648 8	0.514 5	0.470 11	0.368 6	0.000 1	0.441 8	0.705 6	0.000 4	0.079 3	0.000 1	0.021 3	0.872 2	0.872 3	0.621 9	0.589 8	0.144 15	0.129 11	0.648 12	0.459 6	0.000 3	0.000 7	0.000 1	0.022 10	0.289 2	0.096 5	0.667 13	0.000 1	0.000 10	0.000 10	0.834 5	0.682 5	0.178 16	0.033 15	0.256 5	0.196 8	0.000 14	0.473 6	0.279 8	0.079 15	0.008 4	0.495 1	0.425 8	0.000 1	0.228 12	0.009 14	0.564 3	0.410 4	0.366 13	0.665 6	0.161 10	0.615 2	0.365 3	0.000 1	0.609 6	0.386 10	0.681 7	0.000 1	0.000 8	0.199 7	0.093 11	0.497 1	0.109 7	0.252 11	0.161 4	0.118 5	0.000 11	0.000 2	0.000 3	0.857 6	0.000 1	0.495 1	0.000 1	0.162 7	0.412 12	0.000 1	0.563 12	0.000 1	0.000 1	0.000 16	0.012 7	0.877 13	0.004 7	0.000 8	0.000 1	0.002 5	0.000 1	0.109 8	0.458 13	0.358 12	0.246 13	0.060 13	0.139 10	0.466 9	0.803 1	0.097 2	0.000 1	0.517 8	0.000 2	0.000 2	0.060 10	0.413 14	0.000 2	0.000 1	0.000 1	0.183 4	0.024 6	0.000 4	0.297 7	0.000 1

Minkowski 34D	0.253 15	0.463 15	0.154 16	0.102 15	0.771 15	0.650 15	0.932 14	0.483 15	0.571 15	0.710 14	0.331 15	0.250 14	0.492 12	0.044 4	0.703 15	0.419 16	0.606 16	0.227 15	0.621 15	0.865 16	0.531 9	0.771 16	0.813 13	0.291 9	0.484 14	0.242 15	0.612 16	0.282 16	0.440 16	0.351 14	0.299 14	0.622 15	0.593 12	0.027 12	0.293 12	0.310 16	0.000 1	0.757 13	0.858 14	0.737 12	0.150 8	0.164 1	0.368 16	0.084 7	0.381 16	0.142 16	0.357 14	0.720 10	0.214 12	0.092 15	0.724 14	0.596 16	0.056 13	0.655 9	0.525 12	0.581 16	0.352 16	0.594 15	0.056 16	0.000 3	0.014 16	0.224 14	0.772 14	0.205 16	0.720 15	0.000 4	0.159 5	0.531 15	0.163 16	0.294 15	0.136 16	0.000 1	0.169 15	0.589 14	0.000 4	0.000 9	0.000 1	0.002 4	0.663 9	0.466 16	0.265 16	0.582 10	0.337 11	0.016 13	0.559 14	0.084 16	0.000 3	0.000 7	0.000 1	0.036 5	0.000 4	0.125 3	0.670 12	0.000 1	0.102 2	0.071 8	0.164 14	0.406 9	0.386 6	0.046 14	0.068 16	0.159 14	0.117 5	0.284 15	0.111 15	0.094 14	0.000 5	0.000 16	0.197 16	0.000 1	0.044 14	0.013 13	0.002 13	0.228 16	0.307 16	0.588 11	0.025 16	0.545 5	0.134 14	0.000 1	0.655 4	0.302 14	0.282 16	0.000 1	0.060 2	0.000 11	0.035 16	0.000 6	0.000 9	0.097 16	0.000 11	0.000 7	0.005 9	0.000 2	0.000 3	0.096 16	0.000 1	0.334 15	0.000 1	0.000 12	0.274 15	0.000 1	0.513 15	0.000 1	0.000 1	0.280 8	0.194 5	0.897 10	0.000 8	0.000 8	0.000 1	0.000 6	0.000 1	0.108 10	0.279 16	0.189 15	0.141 16	0.059 14	0.272 2	0.307 15	0.445 9	0.003 10	0.000 1	0.353 15	0.000 2	0.026 1	0.000 11	0.581 13	0.001 1	0.000 1	0.000 1	0.093 16	0.002 7	0.000 4	0.000 10	0.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain	0.249 16	0.455 16	0.171 15	0.079 16	0.766 16	0.659 14	0.930 16	0.494 13	0.542 16	0.700 16	0.314 16	0.215 16	0.430 16	0.121 1	0.697 16	0.441 15	0.683 15	0.235 13	0.609 16	0.895 15	0.476 15	0.816 15	0.770 16	0.186 13	0.634 5	0.216 16	0.734 8	0.340 15	0.471 15	0.307 15	0.293 16	0.591 16	0.542 14	0.076 7	0.205 15	0.464 13	0.000 1	0.484 16	0.832 16	0.766 7	0.052 14	0.000 7	0.413 15	0.059 15	0.418 15	0.222 15	0.318 16	0.609 14	0.206 13	0.112 10	0.743 12	0.625 13	0.076 10	0.579 15	0.548 11	0.590 15	0.371 15	0.552 16	0.081 15	0.003 2	0.142 13	0.201 15	0.638 16	0.233 15	0.686 16	0.000 4	0.142 8	0.444 16	0.375 12	0.247 16	0.198 13	0.000 1	0.128 16	0.454 16	0.019 2	0.097 1	0.000 1	0.000 6	0.553 13	0.557 15	0.373 12	0.545 15	0.164 14	0.014 14	0.547 15	0.174 14	0.000 3	0.002 5	0.000 1	0.037 4	0.000 4	0.063 10	0.664 14	0.000 1	0.000 10	0.130 2	0.170 13	0.152 16	0.335 10	0.079 12	0.110 14	0.175 13	0.098 9	0.175 16	0.166 14	0.045 16	0.207 2	0.014 13	0.465 5	0.000 1	0.001 16	0.001 16	0.046 11	0.299 14	0.327 15	0.537 12	0.033 15	0.012 16	0.186 10	0.000 1	0.205 15	0.377 13	0.463 15	0.000 1	0.058 3	0.000 11	0.055 14	0.041 2	0.000 9	0.105 15	0.000 11	0.000 7	0.000 11	0.000 2	0.000 3	0.398 14	0.000 1	0.308 16	0.000 1	0.000 12	0.319 14	0.000 1	0.543 13	0.000 1	0.000 1	0.062 13	0.004 11	0.862 15	0.000 8	0.000 8	0.000 1	0.000 6	0.000 1	0.123 4	0.316 15	0.225 14	0.250 12	0.094 4	0.180 6	0.332 14	0.441 10	0.000 12	0.000 1	0.310 16	0.000 2	0.000 2	0.000 11	0.592 12	0.000 2	0.000 1	0.000 1	0.203 2	0.000 8	0.000 4	0.000 10	0.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
DITR	0.409 2	0.616 1	0.351 1	0.215 3	0.831 3	0.791 1	0.947 6	0.619 1	0.730 2	0.762 3	0.494 2	0.571 1	0.597 2	0.000 11	0.853 1	0.625 3	0.796 2	0.301 3	0.723 3	0.959 4	0.617 2	0.862 7	0.917 3	0.573 1	0.562 10	0.591 1	0.784 7	0.504 5	0.757 1	0.737 2	0.429 4	0.853 1	0.662 3	0.135 3	0.459 3	0.558 10	0.000 1	0.913 1	0.878 7	0.687 14	0.008 15	0.000 7	0.615 4	0.238 1	0.651 1	0.370 3	0.742 2	0.925 2	0.360 1	0.167 6	0.938 1	0.752 2	0.118 3	0.827 2	0.670 4	0.723 2	0.614 3	0.628 14	0.372 1	0.000 3	0.143 12	0.175 16	0.873 3	0.652 1	0.991 1	0.340 1	0.148 6	0.814 1	0.656 1	0.524 6	0.491 3	0.000 1	0.743 1	0.752 2	0.000 4	0.000 9	0.000 1	0.399 1	0.865 3	0.953 1	0.833 1	0.694 2	0.444 6	0.000 15	0.688 4	0.609 2	0.000 3	0.053 2	0.000 1	0.022 10	0.000 4	0.053 13	0.940 3	0.000 1	0.186 1	0.093 5	0.854 3	0.877 1	0.534 2	0.404 1	0.270 3	0.191 10	0.198 4	0.461 8	0.375 1	0.152 3	0.921 1	0.132 9	0.235 14	0.000 1	0.617 1	0.330 1	0.896 1	0.399 6	0.431 5	0.597 10	0.759 1	0.554 4	0.400 2	0.000 1	0.559 9	0.699 1	0.852 2	0.000 1	0.000 8	0.091 10	0.385 1	0.000 6	0.000 9	0.478 4	0.077 9	0.000 7	0.140 4	0.000 2	0.000 3	0.670 13	0.000 1	0.452 5	0.000 1	0.263 3	0.361 13	0.000 1	0.643 4	0.000 1	0.000 1	0.357 5	0.005 10	0.928 2	0.362 1	0.496 1	0.000 1	0.000 6	0.000 1	0.072 16	0.585 2	0.587 3	0.476 4	0.037 15	0.191 5	0.410 13	0.629 6	0.118 1	0.000 1	0.479 11	0.000 2	0.000 2	0.107 8	0.839 3	0.000 2	0.000 1	0.000 1	0.139 11	0.036 5	0.000 4	0.247 9	0.000 1

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

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

Mask3D Scannet200	0.445 1	0.653 1	0.392 1	0.254 1	0.844 2	0.746 2	0.818 1	0.888 4	0.556 1	0.262 1	0.890 1	0.025 2	1.000 1	0.608 1	0.930 1	0.694 3	0.721 1	0.930 5	0.686 3	0.966 1	0.615 4	0.440 1	0.725 4	0.201 1	0.890 3	0.414 4	0.827 1	0.552 1	0.158 5	0.806 1	0.924 1	0.042 3	0.512 2	0.412 5	0.226 1	0.604 3	0.830 1	1.000 1	0.125 1	0.792 1	0.815 1	0.097 1	0.648 1	0.551 2	0.354 4	1.000 1	0.630 1	0.241 2	1.000 1	0.853 1	0.204 1	0.974 4	0.841 1	0.778 1	0.358 2	0.927 1	0.300 1	0.045 1	0.640 1	0.363 1	0.745 2	0.710 1	1.000 1	0.000 1	0.330 2	0.943 1	0.315 2	0.600 1	1.000 1	0.027 1	0.080 5	0.556 5	0.500 1	0.409 1	0.000 1	0.194 1	1.000 1	0.500 1	0.493 2	0.761 2	0.053 4	0.042 3	0.780 2	0.454 1	0.009 1	0.333 1	0.050 1	0.321 1	0.000 1	0.084 1	0.552 2	0.008 2	0.027 2	0.750 1	0.500 1	0.442 3	0.657 1	0.765 2	0.120 2	0.183 3	0.021 2	1.000 1	0.510 2	0.016 1	0.000 1	0.400 1	0.619 1	0.000 1	0.396 1	0.290 1	0.000 1	0.741 1	0.699 1	1.000 1	0.260 1	0.017 3	0.125 5	0.000 1	0.792 4	0.399 4	1.000 1	0.000 1	0.049 3	0.265 1	0.063 3	0.000 3	1.000 1	0.335 2	0.381 1	0.500 1	0.250 1	0.004 2	0.000 1	0.727 2	0.000 1	0.538 3	0.000 1	0.188 1	0.677 2	0.000 1	0.930 1	0.000 1	0.000 1	0.966 1	0.391 1	0.908 2	0.000 1	0.028 1	0.000 1	1.000 1	0.000 1	0.152 1	0.451 2	0.458 1	0.971 1	0.573 1	0.606 1	0.167 5	0.625 1	0.004 1	0.000 1	0.058 5	0.000 1	0.000 1	1.000 1	1.000 1	0.000 1	0.056 1	0.000 2	0.200 3	0.309 1	0.000 2	1.000 1	0.000 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TD3D Scannet200	0.379 2	0.603 2	0.306 2	0.190 2	0.885 1	0.755 1	0.800 2	0.958 1	0.390 2	0.260 2	0.866 2	0.232 1	0.979 2	0.523 3	0.869 3	0.559 5	0.689 2	1.000 1	0.795 1	0.905 2	0.748 1	0.173 5	0.825 1	0.173 2	0.970 1	0.457 1	0.615 2	0.456 2	0.200 1	0.621 4	0.906 2	0.553 1	0.517 1	0.510 1	0.220 2	0.715 1	0.706 2	1.000 1	0.113 2	0.792 1	0.717 2	0.073 2	0.635 2	0.557 1	0.638 1	1.000 1	0.205 5	0.146 3	1.000 1	0.769 5	0.186 2	1.000 1	0.710 5	0.778 1	0.415 1	0.834 4	0.226 2	0.021 2	0.590 2	0.356 2	0.817 1	0.477 5	1.000 1	0.000 1	0.635 1	0.843 2	0.427 1	0.270 4	0.125 2	0.000 2	0.102 3	1.000 1	0.125 2	0.000 2	0.000 1	0.000 2	0.000 3	0.125 4	0.370 3	0.622 5	0.221 1	0.196 2	0.836 1	0.288 2	0.000 2	0.093 2	0.020 2	0.294 2	0.000 1	0.075 2	0.667 1	0.038 1	0.111 1	0.250 4	0.000 4	0.526 2	0.495 3	0.908 1	0.111 3	0.259 1	0.003 3	0.667 2	0.045 5	0.000 2	0.000 1	0.400 1	0.274 3	0.000 1	0.274 2	0.226 2	0.000 1	0.520 2	0.302 5	0.731 2	0.103 3	0.458 1	0.500 1	0.000 1	1.000 1	0.472 1	0.792 3	0.000 1	0.088 2	0.061 2	0.250 1	0.009 2	0.250 2	0.333 3	0.181 2	0.396 2	0.051 2	0.012 1	0.000 1	0.458 4	0.000 1	0.424 5	0.000 1	0.101 2	0.390 5	0.000 1	0.833 2	0.000 1	0.000 1	0.857 2	0.222 3	1.000 1	0.000 1	0.003 2	0.000 1	0.000 2	0.000 1	0.102 2	0.275 5	0.400 2	0.735 2	0.061 3	0.433 3	0.533 3	0.625 1	0.000 2	0.000 1	0.259 4	0.000 1	0.000 1	0.000 2	0.500 2	0.000 1	0.000 2	1.000 1	0.600 1	0.000 2	0.250 1	0.000 2	0.000 1
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
LGround Inst.	0.314 3	0.529 3	0.225 3	0.155 3	0.810 3	0.625 3	0.798 3	0.940 2	0.372 3	0.217 3	0.484 3	0.000 3	0.927 3	0.528 2	0.826 5	0.694 2	0.605 3	1.000 1	0.731 2	0.846 3	0.716 3	0.350 2	0.589 5	0.123 4	0.857 4	0.457 2	0.578 3	0.376 4	0.183 2	0.765 3	0.800 3	0.000 4	0.278 4	0.500 2	0.000 3	0.659 2	0.569 4	1.000 1	0.093 3	0.000 3	0.539 3	0.010 3	0.578 5	0.378 4	0.571 2	1.000 1	0.337 3	0.252 1	0.530 5	0.814 3	0.000 4	0.744 5	0.743 3	0.746 3	0.346 3	0.863 3	0.067 3	0.000 3	0.400 3	0.167 3	0.667 3	0.488 4	1.000 1	0.000 1	0.208 4	0.783 3	0.166 4	0.375 2	0.071 5	0.000 2	0.200 1	0.607 4	0.000 3	0.000 2	0.000 1	0.000 2	1.000 1	0.500 1	0.517 1	0.716 4	0.221 2	0.000 4	0.706 3	0.085 5	0.000 2	0.000 3	0.000 3	0.077 4	0.000 1	0.063 3	0.278 3	0.000 3	0.000 3	0.500 2	0.083 3	0.181 5	0.515 2	0.286 3	0.144 1	0.219 2	0.042 1	0.582 4	0.400 3	0.000 2	0.000 1	0.000 5	0.305 2	0.000 1	0.000 4	0.036 3	0.000 1	0.413 3	0.500 2	0.533 5	0.250 2	0.200 2	0.500 1	0.000 1	1.000 1	0.472 1	1.000 1	0.000 1	0.000 4	0.000 3	0.250 1	0.000 3	0.000 3	0.333 3	0.000 3	0.000 3	0.000 3	0.000 3	0.000 1	0.600 3	0.000 1	0.594 2	0.000 1	0.000 3	0.500 3	0.000 1	0.647 5	0.000 1	0.000 1	0.429 3	0.333 2	0.500 5	0.000 1	0.000 3	0.000 1	0.000 2	0.000 1	0.069 3	0.696 1	0.050 5	0.556 3	0.031 5	0.042 5	0.750 1	0.250 4	0.000 2	0.000 1	0.630 1	0.000 1	0.000 1	0.000 2	0.500 2	0.000 1	0.000 2	0.000 2	0.400 2	0.000 2	0.000 2	0.000 2	0.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.	0.280 4	0.488 4	0.192 5	0.124 4	0.804 4	0.518 4	0.772 5	0.904 3	0.337 5	0.191 4	0.443 4	0.000 3	0.861 4	0.502 4	0.868 4	0.669 4	0.587 4	0.997 3	0.467 5	0.828 5	0.732 2	0.342 3	0.745 3	0.119 5	0.918 2	0.404 5	0.419 4	0.398 3	0.172 3	0.618 5	0.743 4	0.167 2	0.077 5	0.500 2	0.000 3	0.568 4	0.506 5	1.000 1	0.044 4	0.000 3	0.502 4	0.010 4	0.593 4	0.284 5	0.305 5	0.903 5	0.213 4	0.142 4	0.981 3	0.790 4	0.000 4	1.000 1	0.715 4	0.538 5	0.346 4	0.830 5	0.067 3	0.000 3	0.400 3	0.074 4	0.333 4	0.551 2	1.000 1	0.000 1	0.292 3	0.777 4	0.118 5	0.317 3	0.100 4	0.000 2	0.191 2	0.648 3	0.000 3	0.000 2	0.000 1	0.000 2	0.000 3	0.500 1	0.213 5	0.825 1	0.021 5	0.333 1	0.648 5	0.098 4	0.000 2	0.000 3	0.000 3	0.077 3	0.000 1	0.000 5	0.150 5	0.000 3	0.000 3	0.000 5	0.225 2	0.281 4	0.447 4	0.000 5	0.090 4	0.148 4	0.000 4	0.479 5	0.542 1	0.000 2	0.000 1	0.200 3	0.131 5	0.000 1	0.250 3	0.000 4	0.000 1	0.159 5	0.396 4	0.677 3	0.021 4	0.000 4	0.500 1	0.000 1	1.000 1	0.442 3	0.125 5	0.000 1	0.000 4	0.000 3	0.000 4	0.333 1	0.000 3	0.528 1	0.000 3	0.000 3	0.000 3	0.000 3	0.000 1	0.200 5	0.000 1	0.516 4	0.000 1	0.000 3	0.500 3	0.000 1	0.833 2	0.000 1	0.000 1	0.286 4	0.083 4	0.750 3	0.000 1	0.000 3	0.000 1	0.000 2	0.000 1	0.059 5	0.445 3	0.200 3	0.535 4	0.070 2	0.167 4	0.385 4	0.375 3	0.000 2	0.000 1	0.333 3	0.000 1	0.000 1	0.000 2	0.500 2	0.000 1	0.000 2	0.000 2	0.200 3	0.000 2	0.000 2	0.000 2	0.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.	0.275 5	0.466 5	0.218 4	0.110 5	0.783 5	0.383 5	0.783 4	0.829 5	0.367 4	0.168 5	0.305 5	0.000 3	0.661 5	0.413 5	0.869 2	0.719 1	0.546 5	0.997 3	0.685 4	0.841 4	0.555 5	0.277 4	0.768 2	0.132 3	0.779 5	0.448 3	0.364 5	0.212 5	0.161 4	0.768 2	0.692 5	0.000 4	0.395 3	0.500 2	0.000 3	0.450 5	0.591 3	1.000 1	0.020 5	0.000 3	0.423 5	0.007 5	0.625 3	0.420 3	0.505 3	1.000 1	0.353 2	0.119 5	0.571 4	0.819 2	0.014 3	1.000 1	0.774 2	0.689 4	0.311 5	0.866 2	0.067 3	0.000 3	0.400 3	0.000 5	0.278 5	0.501 3	1.000 1	0.000 1	0.162 5	0.584 5	0.286 3	0.206 5	0.125 2	0.000 2	0.084 4	0.649 2	0.000 3	0.000 2	0.000 1	0.000 2	0.000 3	0.125 4	0.312 4	0.727 3	0.221 2	0.000 4	0.667 4	0.114 3	0.000 2	0.000 3	0.000 3	0.065 5	0.000 1	0.004 4	0.278 3	0.000 3	0.000 3	0.500 2	0.000 4	0.571 1	0.000 5	0.250 4	0.019 5	0.145 5	0.000 4	0.667 2	0.200 4	0.000 2	0.000 1	0.200 3	0.258 4	0.000 1	0.000 4	0.000 4	0.000 1	0.369 4	0.429 3	0.613 4	0.000 5	0.000 4	0.500 1	0.000 1	0.500 5	0.333 5	0.500 4	0.000 1	0.106 1	0.000 3	0.000 4	0.000 3	0.000 3	0.333 3	0.000 3	0.000 3	0.000 3	0.000 3	0.000 1	0.918 1	0.000 1	0.638 1	0.000 1	0.000 3	0.750 1	0.000 1	0.833 2	0.000 1	0.000 1	0.143 5	0.000 5	0.750 3	0.000 1	0.000 3	0.000 1	0.000 2	0.000 1	0.063 4	0.377 4	0.200 3	0.222 5	0.055 4	0.500 2	0.677 2	0.250 4	0.000 2	0.000 1	0.500 2	0.000 1	0.000 1	0.000 2	0.500 2	0.000 1	0.000 2	0.000 2	0.115 5	0.000 2	0.000 2	0.000 2	0.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021

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

PTv3-PPT-ALC	0.798 1	0.911 10	0.812 21	0.854 7	0.770 12	0.856 14	0.555 15	0.943 1	0.660 24	0.735 2	0.979 1	0.606 7	0.492 1	0.792 4	0.934 3	0.841 2	0.819 5	0.716 8	0.947 10	0.906 1	0.822 1

PTv3 ScanNet	0.794 2	0.941 3	0.813 20	0.851 9	0.782 6	0.890 3	0.597 1	0.916 5	0.696 9	0.713 5	0.979 1	0.635 2	0.384 3	0.793 3	0.907 10	0.821 5	0.790 33	0.696 13	0.967 3	0.903 2	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)
DITR ScanNet	0.793 3	0.811 39	0.852 2	0.889 1	0.774 9	0.907 1	0.592 2	0.927 3	0.719 1	0.718 3	0.961 17	0.652 1	0.348 12	0.817 1	0.927 5	0.795 9	0.824 2	0.749 1	0.948 9	0.887 7	0.771 11

PonderV2	0.785 4	0.978 1	0.800 29	0.833 26	0.788 4	0.853 19	0.545 19	0.910 8	0.713 2	0.705 6	0.979 1	0.596 9	0.390 2	0.769 15	0.832 44	0.821 5	0.792 32	0.730 2	0.975 1	0.897 5	0.785 6
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 5	0.964 2	0.855 1	0.843 18	0.781 7	0.858 13	0.575 7	0.831 36	0.685 15	0.714 4	0.979 1	0.594 10	0.310 29	0.801 2	0.892 18	0.841 2	0.819 5	0.723 5	0.940 15	0.887 7	0.725 27
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 6	0.861 21	0.818 15	0.836 23	0.790 3	0.875 5	0.576 6	0.905 9	0.704 6	0.739 1	0.969 11	0.611 3	0.349 11	0.756 25	0.958 1	0.702 48	0.805 16	0.708 9	0.916 35	0.898 4	0.801 3

TTT-KD	0.773 7	0.646 94	0.818 15	0.809 38	0.774 9	0.878 4	0.581 3	0.943 1	0.687 13	0.704 7	0.978 5	0.607 6	0.336 18	0.775 11	0.912 8	0.838 4	0.823 3	0.694 14	0.967 3	0.899 3	0.794 5
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 8	0.939 4	0.824 7	0.854 7	0.771 11	0.840 33	0.564 11	0.900 11	0.686 14	0.677 14	0.961 17	0.537 34	0.348 12	0.769 15	0.903 12	0.785 13	0.815 8	0.676 25	0.939 16	0.880 13	0.772 10

PPT-SpUNet-Joint	0.766 9	0.932 5	0.794 35	0.829 28	0.751 25	0.854 17	0.540 23	0.903 10	0.630 37	0.672 17	0.963 15	0.565 24	0.357 9	0.788 5	0.900 14	0.737 28	0.802 17	0.685 19	0.950 7	0.887 7	0.780 7
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormer	0.766 9	0.925 7	0.808 25	0.849 11	0.786 5	0.846 29	0.566 10	0.876 18	0.690 11	0.674 16	0.960 19	0.576 20	0.226 70	0.753 27	0.904 11	0.777 15	0.815 8	0.722 6	0.923 30	0.877 16	0.776 9
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net	0.764 11	0.924 8	0.819 13	0.840 20	0.757 20	0.853 19	0.580 4	0.848 29	0.709 4	0.643 27	0.958 23	0.587 15	0.295 36	0.753 27	0.884 22	0.758 22	0.815 8	0.725 4	0.927 26	0.867 25	0.743 18

OccuSeg+Semantic	0.764 11	0.758 60	0.796 33	0.839 21	0.746 28	0.907 1	0.562 12	0.850 28	0.680 17	0.672 17	0.978 5	0.610 4	0.335 20	0.777 9	0.819 48	0.847 1	0.830 1	0.691 16	0.972 2	0.885 10	0.727 25

O-CNN	0.762 13	0.924 8	0.823 8	0.844 17	0.770 12	0.852 21	0.577 5	0.847 31	0.711 3	0.640 31	0.958 23	0.592 11	0.217 76	0.762 20	0.888 19	0.758 22	0.813 12	0.726 3	0.932 24	0.868 24	0.744 17
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 14	0.725 77	0.789 40	0.843 18	0.762 16	0.856 14	0.562 12	0.920 4	0.657 27	0.658 21	0.958 23	0.589 13	0.337 17	0.782 6	0.879 23	0.787 11	0.779 38	0.678 21	0.926 28	0.880 13	0.799 4

DTC	0.757 15	0.843 27	0.820 11	0.847 14	0.791 2	0.862 11	0.511 36	0.870 20	0.707 5	0.652 23	0.954 38	0.604 8	0.279 47	0.760 21	0.942 2	0.734 29	0.766 47	0.701 12	0.884 57	0.874 22	0.736 19

OA-CNN-L_ScanNet20	0.756 16	0.783 46	0.826 6	0.858 5	0.776 8	0.837 36	0.548 18	0.896 14	0.649 29	0.675 15	0.962 16	0.586 16	0.335 20	0.771 14	0.802 52	0.770 18	0.787 35	0.691 16	0.936 19	0.880 13	0.761 13

PNE	0.755 17	0.786 44	0.835 5	0.834 25	0.758 18	0.849 24	0.570 9	0.836 35	0.648 30	0.668 19	0.978 5	0.581 19	0.367 7	0.683 38	0.856 32	0.804 7	0.801 21	0.678 21	0.961 5	0.889 6	0.716 32
P. Hermosilla: Point Neighborhood Embeddings.
ConDaFormer	0.755 17	0.927 6	0.822 9	0.836 23	0.801 1	0.849 24	0.516 33	0.864 25	0.651 28	0.680 13	0.958 23	0.584 18	0.282 44	0.759 23	0.855 34	0.728 31	0.802 17	0.678 21	0.880 62	0.873 23	0.756 15
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
PointTransformerV2	0.752 19	0.742 68	0.809 24	0.872 2	0.758 18	0.860 12	0.552 16	0.891 16	0.610 44	0.687 8	0.960 19	0.559 28	0.304 32	0.766 18	0.926 6	0.767 19	0.797 25	0.644 36	0.942 13	0.876 19	0.722 29
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net	0.752 19	0.906 13	0.793 37	0.802 44	0.689 43	0.825 49	0.556 14	0.867 21	0.681 16	0.602 47	0.960 19	0.555 30	0.365 8	0.779 8	0.859 29	0.747 25	0.795 29	0.717 7	0.917 34	0.856 33	0.764 12
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
BPNet	0.749 21	0.909 11	0.818 15	0.811 36	0.752 23	0.839 35	0.485 50	0.842 32	0.673 19	0.644 26	0.957 28	0.528 40	0.305 31	0.773 12	0.859 29	0.788 10	0.818 7	0.693 15	0.916 35	0.856 33	0.723 28
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer	0.749 21	0.793 42	0.790 38	0.807 40	0.750 27	0.856 14	0.524 29	0.881 17	0.588 56	0.642 30	0.977 9	0.591 12	0.274 50	0.781 7	0.929 4	0.804 7	0.796 26	0.642 37	0.947 10	0.885 10	0.715 33
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
MSP	0.748 23	0.623 97	0.804 27	0.859 4	0.745 29	0.824 51	0.501 40	0.912 7	0.690 11	0.685 10	0.956 29	0.567 23	0.320 26	0.768 17	0.918 7	0.720 36	0.802 17	0.676 25	0.921 32	0.881 12	0.779 8

StratifiedFormer	0.747 24	0.901 14	0.803 28	0.845 16	0.757 20	0.846 29	0.512 35	0.825 39	0.696 9	0.645 25	0.956 29	0.576 20	0.262 61	0.744 32	0.861 28	0.742 26	0.770 45	0.705 10	0.899 47	0.860 30	0.734 20
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 25	0.870 19	0.838 3	0.858 5	0.729 34	0.850 23	0.501 40	0.874 19	0.587 57	0.658 21	0.956 29	0.564 25	0.299 34	0.765 19	0.900 14	0.716 39	0.812 13	0.631 42	0.939 16	0.858 31	0.709 34
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 25	0.771 54	0.819 13	0.848 13	0.702 40	0.865 10	0.397 88	0.899 12	0.699 7	0.664 20	0.948 58	0.588 14	0.330 22	0.746 31	0.851 38	0.764 20	0.796 26	0.704 11	0.935 20	0.866 26	0.728 23
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 27	0.725 77	0.814 19	0.837 22	0.751 25	0.831 43	0.514 34	0.896 14	0.674 18	0.684 11	0.960 19	0.564 25	0.303 33	0.773 12	0.820 47	0.713 42	0.798 24	0.690 18	0.923 30	0.875 20	0.757 14

Retro-FPN	0.744 28	0.842 28	0.800 29	0.767 58	0.740 30	0.836 38	0.541 21	0.914 6	0.672 20	0.626 35	0.958 23	0.552 31	0.272 52	0.777 9	0.886 21	0.696 49	0.801 21	0.674 28	0.941 14	0.858 31	0.717 30
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 29	0.620 98	0.799 32	0.849 11	0.730 33	0.822 53	0.493 47	0.897 13	0.664 21	0.681 12	0.955 32	0.562 27	0.378 4	0.760 21	0.903 12	0.738 27	0.801 21	0.673 29	0.907 39	0.877 16	0.745 16
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet	0.742 30	0.816 36	0.806 26	0.807 40	0.752 23	0.828 47	0.575 7	0.839 34	0.699 7	0.637 32	0.954 38	0.520 43	0.320 26	0.755 26	0.834 42	0.760 21	0.772 42	0.676 25	0.915 37	0.862 28	0.717 30

SAT	0.742 30	0.860 22	0.765 52	0.819 31	0.769 14	0.848 26	0.533 25	0.829 37	0.663 22	0.631 34	0.955 32	0.586 16	0.274 50	0.753 27	0.896 16	0.729 30	0.760 53	0.666 31	0.921 32	0.855 35	0.733 21

LargeKernel3D	0.739 32	0.909 11	0.820 11	0.806 42	0.740 30	0.852 21	0.545 19	0.826 38	0.594 55	0.643 27	0.955 32	0.541 33	0.263 60	0.723 36	0.858 31	0.775 17	0.767 46	0.678 21	0.933 22	0.848 40	0.694 39
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
MinkowskiNet	0.736 33	0.859 23	0.818 15	0.832 27	0.709 38	0.840 33	0.521 31	0.853 27	0.660 24	0.643 27	0.951 48	0.544 32	0.286 42	0.731 34	0.893 17	0.675 58	0.772 42	0.683 20	0.874 69	0.852 38	0.727 25
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
RPN	0.736 33	0.776 50	0.790 38	0.851 9	0.754 22	0.854 17	0.491 49	0.866 23	0.596 54	0.686 9	0.955 32	0.536 35	0.342 15	0.624 53	0.869 25	0.787 11	0.802 17	0.628 43	0.927 26	0.875 20	0.704 36

IPCA	0.731 35	0.890 15	0.837 4	0.864 3	0.726 35	0.873 6	0.530 28	0.824 40	0.489 90	0.647 24	0.978 5	0.609 5	0.336 18	0.624 53	0.733 61	0.758 22	0.776 40	0.570 68	0.949 8	0.877 16	0.728 23

PointTransformer++	0.725 36	0.727 76	0.811 23	0.819 31	0.765 15	0.841 32	0.502 39	0.814 45	0.621 40	0.623 37	0.955 32	0.556 29	0.284 43	0.620 55	0.866 26	0.781 14	0.757 57	0.648 34	0.932 24	0.862 28	0.709 34

SparseConvNet	0.725 36	0.647 93	0.821 10	0.846 15	0.721 36	0.869 7	0.533 25	0.754 61	0.603 50	0.614 39	0.955 32	0.572 22	0.325 24	0.710 37	0.870 24	0.724 34	0.823 3	0.628 43	0.934 21	0.865 27	0.683 42

MatchingNet	0.724 38	0.812 38	0.812 21	0.810 37	0.735 32	0.834 40	0.495 46	0.860 26	0.572 64	0.602 47	0.954 38	0.512 45	0.280 46	0.757 24	0.845 40	0.725 33	0.780 37	0.606 53	0.937 18	0.851 39	0.700 38

INS-Conv-semantic	0.717 39	0.751 63	0.759 55	0.812 35	0.704 39	0.868 8	0.537 24	0.842 32	0.609 46	0.608 43	0.953 42	0.534 37	0.293 37	0.616 56	0.864 27	0.719 38	0.793 30	0.640 38	0.933 22	0.845 44	0.663 48

PointMetaBase	0.714 40	0.835 29	0.785 41	0.821 29	0.684 45	0.846 29	0.531 27	0.865 24	0.614 41	0.596 51	0.953 42	0.500 48	0.246 66	0.674 39	0.888 19	0.692 50	0.764 49	0.624 45	0.849 84	0.844 45	0.675 44

contrastBoundary	0.705 41	0.769 57	0.775 46	0.809 38	0.687 44	0.820 56	0.439 76	0.812 46	0.661 23	0.591 53	0.945 66	0.515 44	0.171 94	0.633 50	0.856 32	0.720 36	0.796 26	0.668 30	0.889 54	0.847 41	0.689 40
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic	0.703 42	0.774 52	0.800 29	0.793 49	0.760 17	0.847 28	0.471 54	0.802 49	0.463 97	0.634 33	0.968 13	0.491 51	0.271 54	0.726 35	0.910 9	0.706 44	0.815 8	0.551 80	0.878 63	0.833 46	0.570 80

RFCR	0.702 43	0.889 16	0.745 66	0.813 34	0.672 48	0.818 60	0.493 47	0.815 44	0.623 38	0.610 41	0.947 60	0.470 60	0.249 65	0.594 59	0.848 39	0.705 45	0.779 38	0.646 35	0.892 52	0.823 52	0.611 63
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 44	0.825 33	0.796 33	0.723 65	0.716 37	0.832 42	0.433 78	0.816 42	0.634 35	0.609 42	0.969 11	0.418 86	0.344 14	0.559 71	0.833 43	0.715 40	0.808 15	0.560 74	0.902 44	0.847 41	0.680 43

JSENet	0.699 45	0.881 18	0.762 53	0.821 29	0.667 49	0.800 72	0.522 30	0.792 52	0.613 42	0.607 44	0.935 86	0.492 50	0.205 81	0.576 64	0.853 36	0.691 52	0.758 55	0.652 33	0.872 72	0.828 49	0.649 52
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 46	0.743 67	0.794 35	0.655 88	0.684 45	0.822 53	0.497 45	0.719 71	0.622 39	0.617 38	0.977 9	0.447 73	0.339 16	0.750 30	0.664 77	0.703 47	0.790 33	0.596 58	0.946 12	0.855 35	0.647 53
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 47	0.732 72	0.772 47	0.786 50	0.677 47	0.866 9	0.517 32	0.848 29	0.509 83	0.626 35	0.952 46	0.536 35	0.225 72	0.545 77	0.704 68	0.689 55	0.810 14	0.564 73	0.903 43	0.854 37	0.729 22
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNet	0.690 48	0.884 17	0.754 59	0.795 47	0.647 56	0.818 60	0.422 80	0.802 49	0.612 43	0.604 45	0.945 66	0.462 63	0.189 89	0.563 70	0.853 36	0.726 32	0.765 48	0.632 41	0.904 41	0.821 55	0.606 67
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 49	0.704 83	0.741 70	0.754 62	0.656 51	0.829 45	0.501 40	0.741 66	0.609 46	0.548 61	0.950 52	0.522 42	0.371 5	0.633 50	0.756 56	0.715 40	0.771 44	0.623 46	0.861 80	0.814 58	0.658 49
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 50	0.866 20	0.748 63	0.819 31	0.645 58	0.794 75	0.450 66	0.802 49	0.587 57	0.604 45	0.945 66	0.464 62	0.201 84	0.554 73	0.840 41	0.723 35	0.732 67	0.602 56	0.907 39	0.822 54	0.603 70

KP-FCNN	0.684 51	0.847 26	0.758 57	0.784 52	0.647 56	0.814 63	0.473 53	0.772 55	0.605 48	0.594 52	0.935 86	0.450 71	0.181 92	0.587 60	0.805 51	0.690 53	0.785 36	0.614 49	0.882 59	0.819 56	0.632 59
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 51	0.728 75	0.757 58	0.776 55	0.690 41	0.804 70	0.464 59	0.816 42	0.577 63	0.587 54	0.945 66	0.508 47	0.276 49	0.671 40	0.710 66	0.663 63	0.750 61	0.589 63	0.881 60	0.832 48	0.653 51

DGNet	0.684 51	0.712 82	0.784 42	0.782 54	0.658 50	0.835 39	0.499 44	0.823 41	0.641 32	0.597 50	0.950 52	0.487 53	0.281 45	0.575 65	0.619 81	0.647 71	0.764 49	0.620 48	0.871 75	0.846 43	0.688 41

PointContrast_LA_SEM	0.683 54	0.757 61	0.784 42	0.786 50	0.639 60	0.824 51	0.408 83	0.775 54	0.604 49	0.541 63	0.934 90	0.532 38	0.269 56	0.552 74	0.777 54	0.645 74	0.793 30	0.640 38	0.913 38	0.824 51	0.671 45

Superpoint Network	0.683 54	0.851 25	0.728 74	0.800 46	0.653 53	0.806 68	0.468 56	0.804 47	0.572 64	0.602 47	0.946 63	0.453 70	0.239 69	0.519 82	0.822 45	0.689 55	0.762 52	0.595 60	0.895 50	0.827 50	0.630 60

VI-PointConv	0.676 56	0.770 56	0.754 59	0.783 53	0.621 64	0.814 63	0.552 16	0.758 59	0.571 66	0.557 59	0.954 38	0.529 39	0.268 58	0.530 80	0.682 72	0.675 58	0.719 70	0.603 55	0.888 55	0.833 46	0.665 47
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 57	0.789 43	0.748 63	0.763 60	0.635 62	0.814 63	0.407 85	0.747 63	0.581 61	0.573 56	0.950 52	0.484 54	0.271 54	0.607 57	0.754 57	0.649 68	0.774 41	0.596 58	0.883 58	0.823 52	0.606 67

SALANet	0.670 58	0.816 36	0.770 50	0.768 57	0.652 54	0.807 67	0.451 63	0.747 63	0.659 26	0.545 62	0.924 96	0.473 59	0.149 104	0.571 67	0.811 50	0.635 77	0.746 62	0.623 46	0.892 52	0.794 71	0.570 80

O3DSeg	0.668 59	0.822 34	0.771 49	0.496 108	0.651 55	0.833 41	0.541 21	0.761 58	0.555 72	0.611 40	0.966 14	0.489 52	0.370 6	0.388 102	0.580 84	0.776 16	0.751 59	0.570 68	0.956 6	0.817 57	0.646 54

PointASNL	0.666 60	0.703 84	0.781 44	0.751 64	0.655 52	0.830 44	0.471 54	0.769 56	0.474 93	0.537 65	0.951 48	0.475 58	0.279 47	0.635 48	0.698 71	0.675 58	0.751 59	0.553 79	0.816 91	0.806 62	0.703 37
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PointConv	0.666 60	0.781 47	0.759 55	0.699 73	0.644 59	0.822 53	0.475 52	0.779 53	0.564 69	0.504 79	0.953 42	0.428 80	0.203 83	0.586 62	0.754 57	0.661 64	0.753 58	0.588 64	0.902 44	0.813 60	0.642 55
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++	0.663 62	0.746 65	0.708 77	0.722 66	0.638 61	0.820 56	0.451 63	0.566 99	0.599 52	0.541 63	0.950 52	0.510 46	0.313 28	0.648 45	0.819 48	0.616 82	0.682 85	0.590 62	0.869 76	0.810 61	0.656 50
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 63	0.778 48	0.702 80	0.806 42	0.619 65	0.813 66	0.468 56	0.693 79	0.494 86	0.524 71	0.941 78	0.449 72	0.298 35	0.510 84	0.821 46	0.675 58	0.727 69	0.568 71	0.826 89	0.803 65	0.637 57
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 63	0.558 105	0.751 61	0.655 88	0.690 41	0.722 97	0.453 62	0.867 21	0.579 62	0.576 55	0.893 108	0.523 41	0.293 37	0.733 33	0.571 86	0.692 50	0.659 92	0.606 53	0.875 66	0.804 64	0.668 46

HPGCNN	0.656 65	0.698 86	0.743 68	0.650 90	0.564 82	0.820 56	0.505 38	0.758 59	0.631 36	0.479 83	0.945 66	0.480 56	0.226 70	0.572 66	0.774 55	0.690 53	0.735 65	0.614 49	0.853 83	0.776 86	0.597 73
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 66	0.752 62	0.734 72	0.664 86	0.583 77	0.815 62	0.399 87	0.754 61	0.639 33	0.535 67	0.942 76	0.470 60	0.309 30	0.665 41	0.539 88	0.650 67	0.708 75	0.635 40	0.857 82	0.793 73	0.642 55
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 67	0.778 48	0.731 73	0.699 73	0.577 78	0.829 45	0.446 68	0.736 67	0.477 92	0.523 73	0.945 66	0.454 67	0.269 56	0.484 92	0.749 60	0.618 80	0.738 63	0.599 57	0.827 88	0.792 76	0.621 62

PointConv-SFPN	0.641 68	0.776 50	0.703 79	0.721 67	0.557 85	0.826 48	0.451 63	0.672 84	0.563 70	0.483 82	0.943 75	0.425 83	0.162 99	0.644 46	0.726 62	0.659 65	0.709 74	0.572 67	0.875 66	0.786 81	0.559 86

MVPNet	0.641 68	0.831 30	0.715 75	0.671 83	0.590 73	0.781 81	0.394 89	0.679 81	0.642 31	0.553 60	0.937 83	0.462 63	0.256 62	0.649 44	0.406 102	0.626 78	0.691 82	0.666 31	0.877 64	0.792 76	0.608 66
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet	0.640 70	0.717 81	0.701 81	0.692 76	0.576 79	0.801 71	0.467 58	0.716 72	0.563 70	0.459 89	0.953 42	0.429 79	0.169 96	0.581 63	0.854 35	0.605 83	0.710 72	0.550 81	0.894 51	0.793 73	0.575 78

FPConv	0.639 71	0.785 45	0.760 54	0.713 71	0.603 68	0.798 73	0.392 90	0.534 104	0.603 50	0.524 71	0.948 58	0.457 65	0.250 64	0.538 78	0.723 64	0.598 87	0.696 80	0.614 49	0.872 72	0.799 66	0.567 83
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 72	0.797 41	0.769 51	0.641 96	0.590 73	0.820 56	0.461 60	0.537 103	0.637 34	0.536 66	0.947 60	0.388 93	0.206 80	0.656 42	0.668 75	0.647 71	0.732 67	0.585 65	0.868 77	0.793 73	0.473 106

PointSPNet	0.637 73	0.734 71	0.692 88	0.714 70	0.576 79	0.797 74	0.446 68	0.743 65	0.598 53	0.437 94	0.942 76	0.403 89	0.150 103	0.626 52	0.800 53	0.649 68	0.697 79	0.557 77	0.846 85	0.777 85	0.563 84

SConv	0.636 74	0.830 31	0.697 84	0.752 63	0.572 81	0.780 83	0.445 70	0.716 72	0.529 76	0.530 68	0.951 48	0.446 74	0.170 95	0.507 87	0.666 76	0.636 76	0.682 85	0.541 87	0.886 56	0.799 66	0.594 74

Supervoxel-CNN	0.635 75	0.656 91	0.711 76	0.719 68	0.613 66	0.757 92	0.444 73	0.765 57	0.534 75	0.566 57	0.928 94	0.478 57	0.272 52	0.636 47	0.531 90	0.664 62	0.645 96	0.508 94	0.864 79	0.792 76	0.611 63

joint point-based	0.634 76	0.614 99	0.778 45	0.667 85	0.633 63	0.825 49	0.420 81	0.804 47	0.467 95	0.561 58	0.951 48	0.494 49	0.291 39	0.566 68	0.458 97	0.579 93	0.764 49	0.559 76	0.838 86	0.814 58	0.598 72
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 77	0.731 73	0.688 91	0.675 80	0.591 72	0.784 80	0.444 73	0.565 100	0.610 44	0.492 80	0.949 56	0.456 66	0.254 63	0.587 60	0.706 67	0.599 86	0.665 91	0.612 52	0.868 77	0.791 79	0.579 77

3DSM_DMMF	0.631 78	0.626 96	0.745 66	0.801 45	0.607 67	0.751 93	0.506 37	0.729 70	0.565 68	0.491 81	0.866 111	0.434 75	0.197 87	0.595 58	0.630 80	0.709 43	0.705 77	0.560 74	0.875 66	0.740 96	0.491 101

PointNet2-SFPN	0.631 78	0.771 54	0.692 88	0.672 81	0.524 90	0.837 36	0.440 75	0.706 77	0.538 74	0.446 91	0.944 72	0.421 85	0.219 75	0.552 74	0.751 59	0.591 89	0.737 64	0.543 86	0.901 46	0.768 88	0.557 87

APCF-Net	0.631 78	0.742 68	0.687 93	0.672 81	0.557 85	0.792 78	0.408 83	0.665 85	0.545 73	0.508 76	0.952 46	0.428 80	0.186 90	0.634 49	0.702 69	0.620 79	0.706 76	0.555 78	0.873 70	0.798 68	0.581 76
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv	0.630 81	0.604 101	0.741 70	0.766 59	0.590 73	0.747 94	0.501 40	0.734 68	0.503 85	0.527 69	0.919 100	0.454 67	0.323 25	0.550 76	0.420 101	0.678 57	0.688 83	0.544 84	0.896 49	0.795 70	0.627 61
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 82	0.800 40	0.625 104	0.719 68	0.545 87	0.806 68	0.445 70	0.597 93	0.448 100	0.519 74	0.938 82	0.481 55	0.328 23	0.489 91	0.499 95	0.657 66	0.759 54	0.592 61	0.881 60	0.797 69	0.634 58

SegGroup_sem	0.627 83	0.818 35	0.747 65	0.701 72	0.602 69	0.764 89	0.385 94	0.629 90	0.490 88	0.508 76	0.931 93	0.409 88	0.201 84	0.564 69	0.725 63	0.618 80	0.692 81	0.539 88	0.873 70	0.794 71	0.548 90
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv	0.625 84	0.830 31	0.694 86	0.757 61	0.563 83	0.772 87	0.448 67	0.647 88	0.520 79	0.509 75	0.949 56	0.431 78	0.191 88	0.496 89	0.614 82	0.647 71	0.672 89	0.535 90	0.876 65	0.783 82	0.571 79

dtc_net	0.625 84	0.703 84	0.751 61	0.794 48	0.535 88	0.848 26	0.480 51	0.676 83	0.528 77	0.469 86	0.944 72	0.454 67	0.004 117	0.464 94	0.636 79	0.704 46	0.758 55	0.548 83	0.924 29	0.787 80	0.492 100

HPEIN	0.618 86	0.729 74	0.668 94	0.647 92	0.597 71	0.766 88	0.414 82	0.680 80	0.520 79	0.525 70	0.946 63	0.432 76	0.215 77	0.493 90	0.599 83	0.638 75	0.617 101	0.570 68	0.897 48	0.806 62	0.605 69
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 87	0.858 24	0.772 47	0.489 109	0.532 89	0.792 78	0.404 86	0.643 89	0.570 67	0.507 78	0.935 86	0.414 87	0.046 114	0.510 84	0.702 69	0.602 85	0.705 77	0.549 82	0.859 81	0.773 87	0.534 93
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 88	0.760 59	0.667 95	0.649 91	0.521 91	0.793 76	0.457 61	0.648 87	0.528 77	0.434 96	0.947 60	0.401 90	0.153 102	0.454 95	0.721 65	0.648 70	0.717 71	0.536 89	0.904 41	0.765 89	0.485 102
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 89	0.634 95	0.743 68	0.697 75	0.601 70	0.781 81	0.437 77	0.585 96	0.493 87	0.446 91	0.933 91	0.394 91	0.011 116	0.654 43	0.661 78	0.603 84	0.733 66	0.526 91	0.832 87	0.761 91	0.480 103

LAP-D	0.594 90	0.720 79	0.692 88	0.637 97	0.456 101	0.773 86	0.391 92	0.730 69	0.587 57	0.445 93	0.940 80	0.381 94	0.288 40	0.434 98	0.453 99	0.591 89	0.649 94	0.581 66	0.777 95	0.749 95	0.610 65

DPC	0.592 91	0.720 79	0.700 82	0.602 101	0.480 97	0.762 91	0.380 95	0.713 75	0.585 60	0.437 94	0.940 80	0.369 96	0.288 40	0.434 98	0.509 94	0.590 91	0.639 99	0.567 72	0.772 97	0.755 93	0.592 75
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 92	0.766 58	0.659 99	0.683 78	0.470 100	0.740 96	0.387 93	0.620 92	0.490 88	0.476 84	0.922 98	0.355 99	0.245 67	0.511 83	0.511 93	0.571 94	0.643 97	0.493 98	0.872 72	0.762 90	0.600 71

ROSMRF	0.580 93	0.772 53	0.707 78	0.681 79	0.563 83	0.764 89	0.362 97	0.515 105	0.465 96	0.465 88	0.936 85	0.427 82	0.207 79	0.438 96	0.577 85	0.536 97	0.675 88	0.486 99	0.723 103	0.779 83	0.524 96

SD-DETR	0.576 94	0.746 65	0.609 108	0.445 113	0.517 92	0.643 108	0.366 96	0.714 74	0.456 98	0.468 87	0.870 110	0.432 76	0.264 59	0.558 72	0.674 73	0.586 92	0.688 83	0.482 100	0.739 101	0.733 98	0.537 92

SQN_0.1%	0.569 95	0.676 88	0.696 85	0.657 87	0.497 93	0.779 84	0.424 79	0.548 101	0.515 81	0.376 101	0.902 107	0.422 84	0.357 9	0.379 103	0.456 98	0.596 88	0.659 92	0.544 84	0.685 106	0.665 109	0.556 88

TextureNet	0.566 96	0.672 90	0.664 96	0.671 83	0.494 95	0.719 98	0.445 70	0.678 82	0.411 106	0.396 99	0.935 86	0.356 98	0.225 72	0.412 100	0.535 89	0.565 95	0.636 100	0.464 102	0.794 94	0.680 106	0.568 82
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 97	0.648 92	0.700 82	0.770 56	0.586 76	0.687 102	0.333 101	0.650 86	0.514 82	0.475 85	0.906 104	0.359 97	0.223 74	0.340 105	0.442 100	0.422 108	0.668 90	0.501 95	0.708 104	0.779 83	0.534 93

Pointnet++ & Feature	0.557 98	0.735 70	0.661 98	0.686 77	0.491 96	0.744 95	0.392 90	0.539 102	0.451 99	0.375 102	0.946 63	0.376 95	0.205 81	0.403 101	0.356 105	0.553 96	0.643 97	0.497 96	0.824 90	0.756 92	0.515 97

GMLPs	0.538 99	0.495 110	0.693 87	0.647 92	0.471 99	0.793 76	0.300 104	0.477 106	0.505 84	0.358 104	0.903 106	0.327 102	0.081 111	0.472 93	0.529 91	0.448 106	0.710 72	0.509 92	0.746 99	0.737 97	0.554 89

PanopticFusion-label	0.529 100	0.491 111	0.688 91	0.604 100	0.386 106	0.632 109	0.225 114	0.705 78	0.434 103	0.293 110	0.815 112	0.348 100	0.241 68	0.499 88	0.669 74	0.507 99	0.649 94	0.442 108	0.796 93	0.602 113	0.561 85
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	0.516 101	0.676 88	0.591 111	0.609 98	0.442 102	0.774 85	0.335 100	0.597 93	0.422 105	0.357 105	0.932 92	0.341 101	0.094 110	0.298 107	0.528 92	0.473 104	0.676 87	0.495 97	0.602 112	0.721 101	0.349 113

Online SegFusion	0.515 102	0.607 100	0.644 102	0.579 103	0.434 103	0.630 110	0.353 98	0.628 91	0.440 101	0.410 97	0.762 116	0.307 104	0.167 97	0.520 81	0.403 103	0.516 98	0.565 104	0.447 106	0.678 107	0.701 103	0.514 98
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	0.501 103	0.558 105	0.608 109	0.424 115	0.478 98	0.690 101	0.246 110	0.586 95	0.468 94	0.450 90	0.911 102	0.394 91	0.160 100	0.438 96	0.212 112	0.432 107	0.541 110	0.475 101	0.742 100	0.727 99	0.477 104

PCNN	0.498 104	0.559 104	0.644 102	0.560 105	0.420 105	0.711 100	0.229 112	0.414 107	0.436 102	0.352 106	0.941 78	0.324 103	0.155 101	0.238 112	0.387 104	0.493 100	0.529 111	0.509 92	0.813 92	0.751 94	0.504 99

Weakly-Openseg v3	0.489 105	0.749 64	0.664 96	0.646 94	0.496 94	0.559 114	0.122 117	0.577 97	0.257 117	0.364 103	0.805 113	0.198 115	0.096 109	0.510 84	0.496 96	0.361 112	0.563 105	0.359 115	0.777 95	0.644 110	0.532 95

3DMV	0.484 106	0.484 112	0.538 113	0.643 95	0.424 104	0.606 113	0.310 102	0.574 98	0.433 104	0.378 100	0.796 114	0.301 105	0.214 78	0.537 79	0.208 113	0.472 105	0.507 114	0.413 111	0.693 105	0.602 113	0.539 91
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 107	0.577 103	0.611 107	0.356 117	0.321 114	0.715 99	0.299 106	0.376 111	0.328 113	0.319 108	0.944 72	0.285 107	0.164 98	0.216 115	0.229 110	0.484 102	0.545 109	0.456 104	0.755 98	0.709 102	0.475 105
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 108	0.679 87	0.604 110	0.578 104	0.380 107	0.682 103	0.291 107	0.106 117	0.483 91	0.258 115	0.920 99	0.258 111	0.025 115	0.231 114	0.325 106	0.480 103	0.560 107	0.463 103	0.725 102	0.666 108	0.231 117
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproduce	0.446 109	0.474 113	0.623 105	0.463 111	0.366 109	0.651 106	0.310 102	0.389 110	0.349 111	0.330 107	0.937 83	0.271 109	0.126 106	0.285 108	0.224 111	0.350 114	0.577 103	0.445 107	0.625 110	0.723 100	0.394 109
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	0.442 110	0.548 107	0.548 112	0.597 102	0.363 110	0.628 111	0.300 104	0.292 112	0.374 108	0.307 109	0.881 109	0.268 110	0.186 90	0.238 112	0.204 114	0.407 109	0.506 115	0.449 105	0.667 108	0.620 112	0.462 107

SurfaceConvPF	0.442 110	0.505 109	0.622 106	0.380 116	0.342 112	0.654 105	0.227 113	0.397 109	0.367 109	0.276 112	0.924 96	0.240 112	0.198 86	0.359 104	0.262 108	0.366 110	0.581 102	0.435 109	0.640 109	0.668 107	0.398 108
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutions	0.438 112	0.437 115	0.646 101	0.474 110	0.369 108	0.645 107	0.353 98	0.258 114	0.282 115	0.279 111	0.918 101	0.298 106	0.147 105	0.283 109	0.294 107	0.487 101	0.562 106	0.427 110	0.619 111	0.633 111	0.352 112
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 113	0.525 108	0.647 100	0.522 106	0.324 113	0.488 117	0.077 118	0.712 76	0.353 110	0.401 98	0.636 118	0.281 108	0.176 93	0.340 105	0.565 87	0.175 118	0.551 108	0.398 112	0.370 118	0.602 113	0.361 111

SPLAT Net	0.393 114	0.472 114	0.511 114	0.606 99	0.311 115	0.656 104	0.245 111	0.405 108	0.328 113	0.197 116	0.927 95	0.227 114	0.000 119	0.001 119	0.249 109	0.271 117	0.510 112	0.383 114	0.593 113	0.699 104	0.267 115
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	0.383 115	0.297 117	0.491 115	0.432 114	0.358 111	0.612 112	0.274 108	0.116 116	0.411 106	0.265 113	0.904 105	0.229 113	0.079 112	0.250 110	0.185 115	0.320 115	0.510 112	0.385 113	0.548 114	0.597 116	0.394 109

PointNet++	0.339 116	0.584 102	0.478 116	0.458 112	0.256 117	0.360 118	0.250 109	0.247 115	0.278 116	0.261 114	0.677 117	0.183 116	0.117 107	0.212 116	0.145 117	0.364 111	0.346 118	0.232 118	0.548 114	0.523 117	0.252 116
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNet	0.308 117	0.353 116	0.290 118	0.278 118	0.166 118	0.553 115	0.169 116	0.286 113	0.147 118	0.148 118	0.908 103	0.182 117	0.064 113	0.023 118	0.018 119	0.354 113	0.363 116	0.345 116	0.546 116	0.685 105	0.278 114

ScanNet	0.306 118	0.203 118	0.366 117	0.501 107	0.311 115	0.524 116	0.211 115	0.002 119	0.342 112	0.189 117	0.786 115	0.145 118	0.102 108	0.245 111	0.152 116	0.318 116	0.348 117	0.300 117	0.460 117	0.437 118	0.182 118
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 119	0.000 119	0.041 119	0.172 119	0.030 119	0.062 119	0.001 119	0.035 118	0.004 119	0.051 119	0.143 119	0.019 119	0.003 118	0.041 117	0.050 118	0.003 119	0.054 119	0.018 119	0.005 119	0.264 119	0.082 119

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

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

PointRel	0.901 1	1.000 1	0.978 22	0.928 3	0.879 1	0.962 4	0.882 3	0.749 35	0.947 3	0.912 1	0.802 3	0.753 16	0.820 2	1.000 1	0.984 4	0.919 5	0.894 3	1.000 1	0.815 13
: Relation3D (PointRel): Enhancing Relation Modeling for Point Cloud Instance Segmentation.
OneFormer3D	0.896 2	1.000 1	1.000 1	0.913 6	0.858 6	0.951 8	0.786 13	0.837 18	0.916 12	0.908 3	0.778 7	0.803 5	0.750 13	1.000 1	0.976 6	0.926 4	0.882 7	0.995 46	0.849 1
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
MG-Former	0.887 3	1.000 1	0.991 13	0.837 24	0.801 22	0.935 17	0.887 2	0.857 10	0.946 4	0.891 9	0.748 16	0.805 4	0.739 15	1.000 1	0.993 2	0.809 56	0.876 14	1.000 1	0.842 3

UniPerception	0.884 4	1.000 1	0.979 19	0.872 16	0.869 3	0.892 26	0.806 10	0.890 6	0.835 28	0.892 8	0.755 12	0.811 1	0.779 10	0.955 46	0.951 7	0.876 22	0.914 1	0.997 38	0.840 4

KmaxOneFormerNet	0.883 5	1.000 1	1.000 1	0.798 38	0.848 10	0.971 1	0.853 4	0.903 3	0.827 31	0.910 2	0.748 15	0.809 3	0.724 17	1.000 1	0.980 5	0.855 38	0.844 22	1.000 1	0.832 5

InsSSM	0.883 5	1.000 1	0.996 5	0.800 37	0.865 4	0.960 5	0.808 9	0.852 15	0.940 6	0.899 7	0.785 4	0.810 2	0.700 20	1.000 1	0.912 18	0.851 41	0.895 2	0.997 38	0.827 7
Lei Yao, Yi Wang, Moyun Liu, Lap-Pui Chau: SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation. TCSVT, 2024
Competitor-SPFormer	0.881 7	1.000 1	1.000 1	0.845 22	0.854 7	0.962 3	0.714 20	0.857 11	0.904 14	0.902 5	0.782 6	0.789 10	0.662 26	1.000 1	0.988 3	0.874 25	0.886 6	0.997 38	0.847 2

TST3D	0.879 8	1.000 1	0.994 8	0.921 5	0.807 21	0.939 14	0.771 14	0.887 7	0.923 10	0.862 16	0.722 21	0.768 13	0.756 12	1.000 1	0.910 28	0.904 7	0.836 25	0.999 37	0.824 9
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
SIM3D	0.878 9	1.000 1	0.972 24	0.863 18	0.817 19	0.952 7	0.821 7	0.783 29	0.890 17	0.902 6	0.735 19	0.797 6	0.799 9	1.000 1	0.931 15	0.893 13	0.853 20	1.000 1	0.792 16

EV3D	0.877 10	1.000 1	0.996 7	0.873 14	0.854 8	0.950 9	0.691 24	0.783 30	0.926 7	0.889 12	0.754 13	0.794 9	0.820 2	1.000 1	0.912 18	0.900 9	0.860 18	1.000 1	0.779 19

Spherical Mask(CtoF)	0.875 11	1.000 1	0.991 14	0.873 14	0.850 9	0.946 11	0.691 24	0.752 34	0.926 7	0.889 11	0.759 10	0.794 8	0.820 2	1.000 1	0.912 18	0.900 9	0.878 11	1.000 1	0.769 21

TD3D	0.875 11	1.000 1	0.976 23	0.877 12	0.783 28	0.970 2	0.889 1	0.828 19	0.945 5	0.803 21	0.713 23	0.720 23	0.709 18	1.000 1	0.936 13	0.934 3	0.873 15	1.000 1	0.791 17
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
Queryformer	0.874 13	1.000 1	0.978 21	0.809 35	0.876 2	0.936 16	0.702 21	0.716 40	0.920 11	0.875 15	0.766 8	0.772 12	0.818 6	1.000 1	0.995 1	0.916 6	0.892 4	1.000 1	0.767 22

SoftGroup++	0.874 13	1.000 1	0.972 25	0.947 1	0.839 13	0.898 25	0.556 39	0.913 2	0.881 20	0.756 23	0.828 2	0.748 18	0.821 1	1.000 1	0.937 12	0.937 1	0.887 5	1.000 1	0.821 10

Mask3D	0.870 15	1.000 1	0.985 16	0.782 45	0.818 18	0.938 15	0.760 15	0.749 35	0.923 9	0.877 14	0.760 9	0.785 11	0.820 2	1.000 1	0.912 18	0.864 34	0.878 11	0.983 52	0.825 8
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
ExtMask3D	0.867 16	1.000 1	1.000 1	0.756 52	0.816 20	0.940 13	0.795 11	0.760 33	0.862 22	0.888 13	0.739 17	0.763 14	0.774 11	1.000 1	0.929 16	0.878 21	0.879 9	1.000 1	0.819 12

SoftGroup	0.865 17	1.000 1	0.969 26	0.860 19	0.860 5	0.913 21	0.558 36	0.899 4	0.911 13	0.760 22	0.828 1	0.736 20	0.802 8	0.981 43	0.919 17	0.875 23	0.877 13	1.000 1	0.820 11
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
MAFT	0.860 18	1.000 1	0.990 15	0.810 34	0.829 14	0.949 10	0.809 8	0.688 46	0.836 27	0.904 4	0.751 14	0.796 7	0.741 14	1.000 1	0.864 38	0.848 43	0.837 23	1.000 1	0.828 6

SPFormer	0.851 19	1.000 1	0.994 9	0.806 36	0.774 30	0.942 12	0.637 28	0.849 16	0.859 24	0.889 10	0.720 22	0.730 21	0.665 25	1.000 1	0.911 25	0.868 32	0.873 16	1.000 1	0.796 15
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
IPCA-Inst	0.851 19	1.000 1	0.968 27	0.884 11	0.842 12	0.862 38	0.693 23	0.812 24	0.888 19	0.677 35	0.783 5	0.698 24	0.807 7	1.000 1	0.911 25	0.865 33	0.865 17	1.000 1	0.757 25

Mask3D_evaluation	0.843 21	1.000 1	0.955 32	0.847 21	0.795 24	0.932 18	0.750 17	0.780 31	0.891 16	0.818 18	0.737 18	0.633 33	0.703 19	1.000 1	0.902 30	0.870 28	0.820 26	0.941 60	0.805 14

ISBNet	0.835 22	1.000 1	0.950 33	0.731 54	0.819 16	0.918 19	0.790 12	0.740 37	0.851 26	0.831 17	0.661 31	0.742 19	0.650 29	1.000 1	0.937 11	0.814 55	0.836 24	1.000 1	0.765 23
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
SphereSeg	0.835 22	1.000 1	0.963 30	0.891 9	0.794 25	0.954 6	0.822 6	0.710 41	0.961 2	0.721 27	0.693 29	0.530 46	0.653 28	1.000 1	0.867 37	0.857 37	0.859 19	0.991 49	0.771 20

GraphCut	0.832 24	1.000 1	0.922 47	0.724 56	0.798 23	0.902 24	0.701 22	0.856 13	0.859 23	0.715 28	0.706 24	0.748 17	0.640 40	1.000 1	0.934 14	0.862 35	0.880 8	1.000 1	0.729 28

TopoSeg	0.832 24	1.000 1	0.981 18	0.933 2	0.819 17	0.826 47	0.524 45	0.841 17	0.811 33	0.681 34	0.759 11	0.687 25	0.727 16	0.981 43	0.911 25	0.883 17	0.853 21	1.000 1	0.756 26

PBNet	0.825 26	1.000 1	0.963 29	0.837 26	0.843 11	0.865 33	0.822 5	0.647 49	0.878 21	0.733 25	0.639 38	0.683 26	0.650 29	1.000 1	0.853 39	0.870 29	0.820 27	1.000 1	0.744 27
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
SSEC	0.820 27	1.000 1	0.983 17	0.924 4	0.826 15	0.817 50	0.415 54	0.899 5	0.793 37	0.673 36	0.731 20	0.636 31	0.653 27	1.000 1	0.939 10	0.804 58	0.878 10	1.000 1	0.780 18

DKNet	0.815 28	1.000 1	0.930 39	0.844 23	0.765 34	0.915 20	0.534 43	0.805 26	0.805 35	0.807 20	0.654 32	0.763 15	0.650 29	1.000 1	0.794 51	0.881 18	0.766 31	1.000 1	0.758 24
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN	0.806 29	1.000 1	0.992 11	0.789 40	0.723 47	0.891 27	0.650 27	0.810 25	0.832 29	0.665 38	0.699 27	0.658 27	0.700 20	1.000 1	0.881 32	0.832 47	0.774 29	0.997 38	0.613 48
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
Box2Mask	0.803 30	1.000 1	0.962 31	0.874 13	0.707 51	0.887 30	0.686 26	0.598 54	0.961 1	0.715 29	0.694 28	0.469 51	0.700 20	1.000 1	0.912 18	0.902 8	0.753 36	0.997 38	0.637 42
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
HAIS	0.803 30	1.000 1	0.994 9	0.820 30	0.759 35	0.855 39	0.554 40	0.882 8	0.827 32	0.615 44	0.676 30	0.638 30	0.646 38	1.000 1	0.912 18	0.797 61	0.767 30	0.994 47	0.726 29
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Mask-Group	0.792 32	1.000 1	0.968 28	0.812 31	0.766 33	0.864 34	0.460 48	0.815 23	0.888 18	0.598 48	0.651 35	0.639 29	0.600 46	0.918 49	0.941 8	0.896 12	0.721 43	1.000 1	0.723 30
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained	0.791 33	1.000 1	0.996 5	0.829 29	0.767 32	0.889 29	0.600 31	0.819 22	0.770 42	0.594 49	0.620 42	0.541 43	0.700 20	1.000 1	0.941 8	0.889 15	0.763 32	1.000 1	0.526 58

SSTNet	0.789 34	1.000 1	0.840 61	0.888 10	0.717 48	0.835 43	0.717 19	0.684 47	0.627 57	0.724 26	0.652 34	0.727 22	0.600 46	1.000 1	0.912 18	0.822 50	0.757 35	1.000 1	0.691 36
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN	0.788 35	1.000 1	0.978 20	0.867 17	0.781 29	0.833 44	0.527 44	0.824 20	0.806 34	0.549 57	0.596 45	0.551 39	0.700 20	1.000 1	0.853 39	0.935 2	0.733 40	1.000 1	0.651 39

DENet	0.786 36	1.000 1	0.929 40	0.736 53	0.750 41	0.720 63	0.755 16	0.934 1	0.794 36	0.590 50	0.561 51	0.537 44	0.650 29	1.000 1	0.882 31	0.804 59	0.789 28	1.000 1	0.719 31

DANCENET	0.786 36	1.000 1	0.936 36	0.783 43	0.737 44	0.852 41	0.742 18	0.647 49	0.765 44	0.811 19	0.624 41	0.579 36	0.632 43	1.000 1	0.909 29	0.898 11	0.696 48	0.944 56	0.601 51

DualGroup	0.782 38	1.000 1	0.927 41	0.811 32	0.772 31	0.853 40	0.631 30	0.805 26	0.773 39	0.613 45	0.611 43	0.610 34	0.650 29	0.835 60	0.881 32	0.879 20	0.750 38	1.000 1	0.675 37

PointGroup	0.778 39	1.000 1	0.900 51	0.798 39	0.715 49	0.863 35	0.493 46	0.706 42	0.895 15	0.569 55	0.701 25	0.576 37	0.639 41	1.000 1	0.880 34	0.851 40	0.719 44	0.997 38	0.709 33
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
PE	0.776 40	1.000 1	0.900 52	0.860 19	0.728 46	0.869 31	0.400 55	0.857 12	0.774 38	0.568 56	0.701 26	0.602 35	0.646 38	0.933 48	0.843 42	0.890 14	0.691 52	0.997 38	0.709 32
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA	0.767 41	1.000 1	0.937 35	0.810 33	0.740 43	0.906 22	0.550 41	0.800 28	0.706 49	0.577 54	0.624 40	0.544 42	0.596 51	0.857 52	0.879 36	0.880 19	0.750 37	0.992 48	0.658 38

DD-UNet+Group	0.764 42	1.000 1	0.897 54	0.837 25	0.753 38	0.830 46	0.459 50	0.824 20	0.699 51	0.629 42	0.653 33	0.438 54	0.650 29	1.000 1	0.880 34	0.858 36	0.690 53	1.000 1	0.650 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
INS-Conv-instance	0.762 43	1.000 1	0.923 44	0.765 48	0.785 27	0.905 23	0.600 31	0.655 48	0.646 56	0.683 33	0.647 36	0.530 45	0.650 29	1.000 1	0.824 44	0.830 48	0.693 51	0.944 56	0.644 41

Dyco3D	0.761 44	1.000 1	0.935 37	0.893 8	0.752 40	0.863 36	0.600 31	0.588 55	0.742 46	0.641 40	0.633 39	0.546 41	0.550 53	0.857 52	0.789 53	0.853 39	0.762 33	0.987 50	0.699 34
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance	0.742 45	1.000 1	0.923 44	0.785 41	0.745 42	0.867 32	0.557 37	0.578 58	0.729 47	0.670 37	0.644 37	0.488 49	0.577 52	1.000 1	0.794 51	0.830 48	0.620 61	1.000 1	0.550 54
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg	0.739 46	1.000 1	0.899 53	0.759 50	0.753 39	0.823 48	0.282 60	0.691 45	0.658 54	0.582 53	0.594 46	0.547 40	0.628 44	1.000 1	0.795 50	0.868 31	0.728 42	1.000 1	0.692 35

3D-MPA	0.737 47	1.000 1	0.933 38	0.785 41	0.794 26	0.831 45	0.279 62	0.588 55	0.695 52	0.616 43	0.559 52	0.556 38	0.650 29	1.000 1	0.809 48	0.875 24	0.696 49	1.000 1	0.608 50
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML	0.731 48	1.000 1	0.992 11	0.779 47	0.609 60	0.746 58	0.308 59	0.867 9	0.601 60	0.607 46	0.539 55	0.519 47	0.550 53	1.000 1	0.824 44	0.869 30	0.729 41	1.000 1	0.616 46
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS	0.725 49	1.000 1	0.885 57	0.653 62	0.657 57	0.801 51	0.576 35	0.695 44	0.828 30	0.698 31	0.534 56	0.457 53	0.500 60	0.857 52	0.831 43	0.841 45	0.627 59	1.000 1	0.619 45

SSEN	0.724 50	1.000 1	0.926 42	0.781 46	0.661 55	0.845 42	0.596 34	0.529 61	0.764 45	0.653 39	0.489 62	0.461 52	0.500 60	0.859 51	0.765 54	0.872 27	0.761 34	1.000 1	0.577 52
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF	0.718 51	1.000 1	0.945 34	0.901 7	0.754 37	0.817 49	0.460 48	0.700 43	0.772 40	0.688 32	0.568 50	0.000 73	0.500 60	0.981 43	0.606 64	0.872 26	0.740 39	1.000 1	0.614 47
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Sparse R-CNN	0.714 52	1.000 1	0.926 43	0.694 57	0.699 53	0.890 28	0.636 29	0.516 62	0.693 53	0.743 24	0.588 47	0.369 58	0.601 45	0.594 66	0.800 49	0.886 16	0.676 54	0.986 51	0.546 55

SALoss-ResNet	0.695 53	1.000 1	0.855 59	0.579 67	0.589 62	0.735 61	0.484 47	0.588 55	0.856 25	0.634 41	0.571 49	0.298 59	0.500 60	1.000 1	0.824 44	0.818 51	0.702 47	0.935 63	0.545 56
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
PanopticFusion-inst	0.693 54	1.000 1	0.852 60	0.655 61	0.616 59	0.788 53	0.334 57	0.763 32	0.771 41	0.457 67	0.555 53	0.652 28	0.518 57	0.857 52	0.765 54	0.732 67	0.631 57	0.944 56	0.577 53
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Occipital-SCS	0.688 55	1.000 1	0.913 48	0.730 55	0.737 45	0.743 60	0.442 51	0.855 14	0.655 55	0.546 58	0.546 54	0.263 61	0.508 59	0.889 50	0.568 65	0.771 64	0.705 46	0.889 66	0.625 44

3D-BoNet	0.687 56	1.000 1	0.887 56	0.836 27	0.587 63	0.643 70	0.550 41	0.620 51	0.724 48	0.522 62	0.501 60	0.243 62	0.512 58	1.000 1	0.751 56	0.807 57	0.661 56	0.909 65	0.612 49
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
ClickSeg_Instance	0.685 57	1.000 1	0.818 63	0.600 65	0.715 50	0.795 52	0.557 37	0.533 60	0.591 62	0.601 47	0.519 58	0.429 56	0.638 42	0.938 47	0.706 59	0.817 53	0.624 60	0.944 56	0.502 60

PCJC	0.684 58	1.000 1	0.895 55	0.757 51	0.659 56	0.862 37	0.189 69	0.739 38	0.606 59	0.712 30	0.581 48	0.515 48	0.650 29	0.857 52	0.357 70	0.785 62	0.631 58	0.889 66	0.635 43

SPG_WSIS	0.678 59	1.000 1	0.880 58	0.836 27	0.701 52	0.727 62	0.273 64	0.607 53	0.706 50	0.541 60	0.515 59	0.174 65	0.600 46	0.857 52	0.716 58	0.846 44	0.711 45	1.000 1	0.506 59

One_Thing_One_Click	0.675 60	1.000 1	0.823 62	0.782 44	0.621 58	0.766 55	0.211 66	0.736 39	0.560 64	0.586 51	0.522 57	0.636 32	0.453 64	0.641 64	0.853 39	0.850 42	0.694 50	0.997 38	0.411 65
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_ins	0.637 61	1.000 1	0.923 46	0.593 66	0.561 64	0.746 59	0.143 71	0.504 63	0.766 43	0.485 65	0.442 63	0.372 57	0.530 56	0.714 61	0.815 47	0.775 63	0.673 55	1.000 1	0.431 64
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASC	0.615 62	0.711 69	0.802 64	0.540 68	0.757 36	0.777 54	0.029 72	0.577 59	0.588 63	0.521 63	0.600 44	0.436 55	0.534 55	0.697 62	0.616 63	0.838 46	0.526 63	0.980 53	0.534 57
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone	0.605 63	1.000 1	0.909 49	0.764 49	0.603 61	0.704 64	0.415 53	0.301 68	0.548 65	0.461 66	0.394 64	0.267 60	0.386 66	0.857 52	0.649 62	0.817 52	0.504 65	0.959 54	0.356 68

3D-SIS	0.558 64	1.000 1	0.773 65	0.614 64	0.503 67	0.691 66	0.200 67	0.412 64	0.498 68	0.546 59	0.311 69	0.103 69	0.600 46	0.857 52	0.382 67	0.799 60	0.445 71	0.938 62	0.371 66
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet	0.544 65	0.500 72	0.655 71	0.661 60	0.663 54	0.765 56	0.432 52	0.214 71	0.612 58	0.584 52	0.499 61	0.204 64	0.286 70	0.429 69	0.655 61	0.650 72	0.539 62	0.950 55	0.499 61

Hier3D	0.540 66	1.000 1	0.727 66	0.626 63	0.467 70	0.693 65	0.200 67	0.412 64	0.480 69	0.528 61	0.318 68	0.077 72	0.600 46	0.688 63	0.382 67	0.768 65	0.472 67	0.941 60	0.350 69
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class	0.497 67	0.250 74	0.902 50	0.689 58	0.540 65	0.747 57	0.276 63	0.610 52	0.268 73	0.489 64	0.348 65	0.000 73	0.243 73	0.220 72	0.663 60	0.814 54	0.459 69	0.928 64	0.496 62

Sem_Recon_ins	0.484 68	0.764 68	0.608 73	0.470 70	0.521 66	0.637 71	0.311 58	0.218 70	0.348 72	0.365 71	0.223 70	0.222 63	0.258 71	0.629 65	0.734 57	0.596 73	0.509 64	0.858 69	0.444 63

tmp	0.474 69	1.000 1	0.727 66	0.433 72	0.481 69	0.673 68	0.022 74	0.380 66	0.517 67	0.436 69	0.338 67	0.128 67	0.343 68	0.429 69	0.291 72	0.728 68	0.473 66	0.833 70	0.300 71

SemRegionNet-20cls	0.470 70	1.000 1	0.727 66	0.447 71	0.481 68	0.678 67	0.024 73	0.380 66	0.518 66	0.440 68	0.339 66	0.128 67	0.350 67	0.429 69	0.212 73	0.711 69	0.465 68	0.833 70	0.290 72

ASIS	0.422 71	0.333 73	0.707 69	0.676 59	0.401 71	0.650 69	0.350 56	0.177 72	0.594 61	0.376 70	0.202 71	0.077 71	0.404 65	0.571 67	0.197 74	0.674 71	0.447 70	0.500 73	0.260 73

3D-BEVIS	0.401 72	0.667 70	0.687 70	0.419 73	0.137 74	0.587 72	0.188 70	0.235 69	0.359 71	0.211 73	0.093 74	0.080 70	0.311 69	0.571 67	0.382 67	0.754 66	0.300 73	0.874 68	0.357 67
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet	0.390 73	0.556 71	0.636 72	0.493 69	0.353 72	0.539 73	0.271 65	0.160 73	0.450 70	0.359 72	0.178 72	0.146 66	0.250 72	0.143 73	0.347 71	0.698 70	0.436 72	0.667 72	0.331 70

MaskRCNN 2d->3d Proj	0.261 74	0.903 67	0.081 74	0.008 74	0.233 73	0.175 74	0.280 61	0.106 74	0.150 74	0.203 74	0.175 73	0.480 50	0.218 74	0.143 73	0.542 66	0.404 74	0.153 74	0.393 74	0.049 74

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 17	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 13	0.769 4	0.656 3	0.567 4	0.931 3	0.395 6	0.390 5	0.700 4	0.534 4	0.689 10	0.770 2	0.574 3	0.865 9	0.831 3	0.675 5
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 14	0.794 4	0.434 16	0.688 1	0.337 8	0.464 12	0.798 3	0.632 5	0.589 3	0.908 8	0.420 2	0.329 12	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 23	0.648 4	0.463 3	0.549 2	0.742 7	0.676 2	0.628 2	0.961 1	0.420 2	0.379 6	0.684 8	0.381 18	0.732 3	0.723 3	0.599 2	0.827 16	0.851 2	0.634 7

CMX	0.613 5	0.681 8	0.725 12	0.502 12	0.634 6	0.297 18	0.478 10	0.830 2	0.651 4	0.537 7	0.924 4	0.375 7	0.315 14	0.686 7	0.451 14	0.714 5	0.543 21	0.504 6	0.894 7	0.823 5	0.688 4

DMMF_3d	0.605 6	0.651 9	0.744 10	0.782 3	0.637 5	0.387 4	0.536 3	0.732 8	0.590 7	0.540 6	0.856 21	0.359 11	0.306 15	0.596 14	0.539 3	0.627 20	0.706 4	0.497 8	0.785 21	0.757 19	0.476 22

EMSANet	0.600 7	0.716 4	0.746 9	0.395 18	0.614 9	0.382 5	0.523 4	0.713 11	0.571 11	0.503 10	0.922 6	0.404 5	0.397 4	0.655 9	0.400 16	0.626 21	0.663 6	0.469 13	0.900 4	0.827 4	0.577 14
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 8	0.533 20	0.756 8	0.746 4	0.590 10	0.334 10	0.506 7	0.670 15	0.587 8	0.500 12	0.905 10	0.366 10	0.352 9	0.601 13	0.506 8	0.669 16	0.648 9	0.501 7	0.839 15	0.769 15	0.516 21

RFBNet	0.592 9	0.616 11	0.758 7	0.659 5	0.581 11	0.330 11	0.469 11	0.655 18	0.543 14	0.524 8	0.924 4	0.355 13	0.336 11	0.572 17	0.479 10	0.671 14	0.648 9	0.480 10	0.814 19	0.814 7	0.614 10

FAN_NV_RVC	0.586 10	0.510 21	0.764 6	0.079 26	0.620 8	0.330 11	0.494 8	0.753 5	0.573 9	0.556 5	0.884 16	0.405 4	0.303 16	0.718 3	0.452 13	0.672 13	0.658 7	0.509 5	0.898 5	0.813 8	0.727 2

DCRedNet	0.583 11	0.682 7	0.723 13	0.542 11	0.510 20	0.310 15	0.451 13	0.668 16	0.549 13	0.520 9	0.920 7	0.375 7	0.446 2	0.528 20	0.417 15	0.670 15	0.577 18	0.478 11	0.862 10	0.806 9	0.628 9

MIX6D_RVC	0.582 12	0.695 5	0.687 17	0.225 21	0.632 7	0.328 13	0.550 1	0.748 6	0.623 6	0.494 15	0.890 14	0.350 15	0.254 23	0.688 6	0.454 12	0.716 4	0.597 17	0.489 9	0.881 8	0.768 16	0.575 15

SSMA	0.577 13	0.695 5	0.716 15	0.439 14	0.563 14	0.314 14	0.444 15	0.719 9	0.551 12	0.503 10	0.887 15	0.346 16	0.348 10	0.603 12	0.353 20	0.709 6	0.600 15	0.457 14	0.901 3	0.786 11	0.599 13
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DMMF	0.567 14	0.623 10	0.767 5	0.238 20	0.571 13	0.347 6	0.413 19	0.719 9	0.472 20	0.418 22	0.895 13	0.357 12	0.260 22	0.696 5	0.523 7	0.666 17	0.642 11	0.437 18	0.895 6	0.793 10	0.603 12

UNIV_CNP_RVC_UE	0.566 15	0.569 19	0.686 19	0.435 15	0.524 17	0.294 19	0.421 18	0.712 12	0.543 14	0.463 17	0.872 17	0.320 17	0.363 8	0.611 11	0.477 11	0.686 11	0.627 12	0.443 17	0.862 10	0.775 14	0.639 6

EMSAFormer	0.564 16	0.581 16	0.736 11	0.564 10	0.546 16	0.219 23	0.517 5	0.675 14	0.486 19	0.427 21	0.904 11	0.352 14	0.320 13	0.589 15	0.528 5	0.708 7	0.464 24	0.413 22	0.847 14	0.786 11	0.611 11

SN_RN152pyrx8_RVC	0.546 17	0.572 17	0.663 21	0.638 7	0.518 18	0.298 17	0.366 24	0.633 21	0.510 17	0.446 19	0.864 19	0.296 20	0.267 19	0.542 19	0.346 21	0.704 8	0.575 19	0.431 19	0.853 13	0.766 17	0.630 8

UDSSEG_RVC	0.545 18	0.610 13	0.661 22	0.588 8	0.556 15	0.268 21	0.482 9	0.642 20	0.572 10	0.475 16	0.836 23	0.312 18	0.367 7	0.630 10	0.189 23	0.639 19	0.495 23	0.452 15	0.826 17	0.756 20	0.541 17

segfomer with 6d	0.542 19	0.594 15	0.687 17	0.146 24	0.579 12	0.308 16	0.515 6	0.703 13	0.472 20	0.498 13	0.868 18	0.369 9	0.282 17	0.589 15	0.390 17	0.701 9	0.556 20	0.416 21	0.860 12	0.759 18	0.539 19

FuseNet	0.535 20	0.570 18	0.681 20	0.182 22	0.512 19	0.290 20	0.431 16	0.659 17	0.504 18	0.495 14	0.903 12	0.308 19	0.428 3	0.523 21	0.365 19	0.676 12	0.621 14	0.470 12	0.762 22	0.779 13	0.541 17
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++	0.503 21	0.613 12	0.722 14	0.418 17	0.358 26	0.337 8	0.370 23	0.479 24	0.443 22	0.368 24	0.907 9	0.207 23	0.213 25	0.464 24	0.525 6	0.618 22	0.657 8	0.450 16	0.788 20	0.721 23	0.408 25
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 22	0.481 24	0.612 23	0.579 9	0.456 22	0.343 7	0.384 21	0.623 22	0.525 16	0.381 23	0.845 22	0.254 22	0.264 21	0.557 18	0.182 24	0.581 24	0.598 16	0.429 20	0.760 23	0.661 25	0.446 24
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVC	0.485 23	0.505 22	0.709 16	0.092 25	0.427 23	0.241 22	0.411 20	0.654 19	0.385 26	0.457 18	0.861 20	0.053 26	0.279 18	0.503 22	0.481 9	0.645 18	0.626 13	0.365 24	0.748 24	0.725 22	0.529 20
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 24	0.490 23	0.581 24	0.289 19	0.507 21	0.067 26	0.379 22	0.610 23	0.417 24	0.435 20	0.822 25	0.278 21	0.267 19	0.503 22	0.228 22	0.616 23	0.533 22	0.375 23	0.820 18	0.729 21	0.560 16

Enet (reimpl)	0.376 25	0.264 26	0.452 26	0.452 13	0.365 24	0.181 24	0.143 26	0.456 25	0.409 25	0.346 25	0.769 26	0.164 24	0.218 24	0.359 25	0.123 26	0.403 26	0.381 26	0.313 26	0.571 25	0.685 24	0.472 23
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 26	0.293 25	0.521 25	0.657 6	0.361 25	0.161 25	0.250 25	0.004 26	0.440 23	0.183 26	0.836 23	0.125 25	0.060 26	0.319 26	0.132 25	0.417 25	0.412 25	0.344 25	0.541 26	0.427 26	0.109 26
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17

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

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

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

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

Presenting the ScanNet200 Benchmark

ScanNet200 Benchmark

ScanNet200 3D Semantic Label Benchmark

ScanNet200 3D Semantic Instance Benchmark

ScanNet Benchmark

3D Semantic Label Benchmark

3D Semantic Instance Benchmark

2D Semantic Label Benchmark

2D Semantic Instance Benchmark

Scene Type Classification Benchmark

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

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

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