Benchmark Results - ScanNet Benchmark

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

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

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

PonderV2 ScanNet200	0.346 3	0.552 5	0.270 5	0.175 4	0.497 5	0.070 9	0.239 5	0.000 1	0.000 3	0.000 1	0.232 12	0.412 5	0.584 2	0.842 3	0.804 4	0.212 5	0.540 5	0.000 3	0.433 11	0.106 7	0.000 6	0.590 3	0.290 7	0.548 3	0.243 5	0.000 5	0.356 8	0.000 1	0.000 3	0.062 7	0.398 8	0.441 5	0.000 1	0.104 7	0.000 2	0.888 3	0.076 9	0.682 5	0.030 1	0.094 5	0.491 7	0.351 8	0.869 7	0.000 1	0.063 1	0.403 7	0.700 2	0.000 8	0.660 9	0.881 4	0.761 1	0.050 7	0.186 5	0.852 8	0.000 1	0.007 6	0.570 5	0.100 2	0.565 2	0.326 4	0.641 7	0.431 4	0.290 9	0.621 4	0.259 2	0.408 6	0.622 7	0.125 1	0.082 7	0.950 3	0.179 4	0.000 1	0.263 3	0.424 3	0.193 6	0.558 4	0.880 2	0.545 8	0.375 4	0.727 2	0.445 7	0.499 7	0.000 3	0.000 1	0.475 5	0.002 5	0.034 5	0.083 5	0.000 3	0.924 1	0.290 3	0.636 4	0.115 9	0.400 3	0.874 3	0.186 5	0.000 1	0.611 5	0.128 2	0.113 2	0.000 4	0.000 1	0.000 6	0.584 7	0.636 6	0.103 9	0.385 6	0.843 5	0.283 2	0.603 4	0.080 5	0.825 5	0.000 3	0.377 7	0.000 1	0.000 4	0.000 2	0.457 8	0.000 1	0.000 5	0.000 1	0.574 9	0.608 6	0.481 2	0.792 3	0.394 3	0.000 1	0.357 7	0.503 8	0.261 7	0.817 8	0.504 9	0.304 5	0.472 3	0.115 6	0.000 1	0.750 4	0.677 4	0.202 2	0.000 7	0.509 4	0.729 2	0.000 1	0.519 9	0.000 11	0.000 5	0.000 1	0.620 9	0.000 2	0.000 1	0.660 4	0.560 4	0.486 3	0.384 6	0.346 5	0.952 3	0.247 9	0.667 3	0.436 7	0.269 3	0.691 4	0.000 1	0.010 3	0.787 5	0.889 2	0.880 4	0.000 1	0.810 5	0.336 4	0.860 6	0.000 1	0.606 4	0.009 6	0.248 6	0.681 4	0.392 7
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.
PTv3 ScanNet200	0.393 1	0.592 1	0.330 1	0.216 1	0.520 1	0.109 2	0.108 11	0.000 1	0.337 1	0.000 1	0.310 9	0.394 6	0.494 9	0.753 8	0.848 1	0.256 2	0.717 3	0.000 3	0.842 1	0.192 2	0.065 2	0.449 6	0.346 2	0.546 4	0.190 8	0.000 5	0.384 4	0.000 1	0.000 3	0.218 1	0.505 1	0.791 1	0.000 1	0.136 2	0.000 2	0.903 1	0.073 10	0.687 4	0.000 5	0.168 1	0.551 3	0.387 6	0.941 1	0.000 1	0.000 2	0.397 8	0.654 3	0.000 8	0.714 3	0.759 10	0.752 5	0.118 4	0.264 2	0.926 1	0.000 1	0.048 3	0.575 2	0.000 7	0.597 1	0.366 1	0.755 1	0.469 1	0.474 1	0.798 1	0.140 6	0.617 1	0.692 4	0.000 4	0.592 2	0.971 1	0.188 3	0.000 1	0.133 5	0.593 1	0.349 1	0.650 2	0.717 5	0.699 1	0.455 1	0.790 1	0.523 3	0.636 1	0.301 1	0.000 1	0.622 2	0.000 7	0.017 10	0.259 2	0.000 3	0.921 2	0.337 1	0.733 1	0.210 1	0.514 1	0.860 6	0.407 1	0.000 1	0.688 1	0.109 6	0.000 10	0.000 4	0.000 1	0.151 2	0.671 4	0.782 1	0.115 8	0.641 1	0.903 1	0.349 1	0.616 2	0.088 4	0.832 3	0.000 3	0.480 2	0.000 1	0.428 1	0.000 2	0.497 7	0.000 1	0.000 5	0.000 1	0.662 2	0.690 1	0.612 1	0.828 1	0.575 1	0.000 1	0.404 4	0.644 1	0.325 4	0.887 2	0.728 1	0.009 11	0.134 5	0.026 12	0.000 1	0.761 1	0.731 1	0.172 4	0.077 2	0.528 3	0.727 3	0.000 1	0.603 4	0.220 2	0.022 2	0.000 1	0.740 1	0.000 2	0.000 1	0.661 2	0.586 1	0.566 1	0.436 4	0.531 2	0.978 1	0.457 1	0.708 2	0.583 3	0.141 7	0.748 1	0.000 1	0.026 1	0.822 1	0.871 3	0.879 5	0.000 1	0.851 1	0.405 2	0.914 1	0.000 1	0.682 2	0.000 10	0.281 2	0.738 1	0.463 5
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)
L3DETR-ScanNet_200	0.336 5	0.533 8	0.279 3	0.155 5	0.508 3	0.073 8	0.101 12	0.000 1	0.058 2	0.000 1	0.294 11	0.233 11	0.548 3	0.927 1	0.788 6	0.264 1	0.463 6	0.000 3	0.638 7	0.098 10	0.014 4	0.411 8	0.226 8	0.525 8	0.225 7	0.010 3	0.397 3	0.000 1	0.000 3	0.192 3	0.380 9	0.598 3	0.000 1	0.117 3	0.000 2	0.883 4	0.082 7	0.689 2	0.000 5	0.032 12	0.549 4	0.417 4	0.910 3	0.000 1	0.000 2	0.448 6	0.613 6	0.000 8	0.697 5	0.960 1	0.759 2	0.158 2	0.293 1	0.883 4	0.000 1	0.312 2	0.583 1	0.079 4	0.422 9	0.068 12	0.660 5	0.418 5	0.298 7	0.430 9	0.114 7	0.526 3	0.776 1	0.051 2	0.679 1	0.946 4	0.152 6	0.000 1	0.183 4	0.000 10	0.211 5	0.511 7	0.409 11	0.565 7	0.355 5	0.448 5	0.512 4	0.557 2	0.000 3	0.000 1	0.420 6	0.000 7	0.007 12	0.104 3	0.000 3	0.125 12	0.330 2	0.514 10	0.146 7	0.321 8	0.860 6	0.174 6	0.000 1	0.629 3	0.075 11	0.000 10	0.000 4	0.000 1	0.002 5	0.671 4	0.712 4	0.141 4	0.339 7	0.856 3	0.261 7	0.529 7	0.067 7	0.835 1	0.000 3	0.369 9	0.000 1	0.259 2	0.000 2	0.629 3	0.000 1	0.487 1	0.000 1	0.579 8	0.646 2	0.107 12	0.720 8	0.122 5	0.000 1	0.333 9	0.505 7	0.303 6	0.908 1	0.503 10	0.565 1	0.074 6	0.324 1	0.000 1	0.740 5	0.661 6	0.109 9	0.000 7	0.427 8	0.563 12	0.000 1	0.579 8	0.108 5	0.000 5	0.000 1	0.664 3	0.000 2	0.000 1	0.641 5	0.539 6	0.416 4	0.515 2	0.256 6	0.940 8	0.312 3	0.209 12	0.620 1	0.138 10	0.636 8	0.000 1	0.000 8	0.775 8	0.861 4	0.765 8	0.000 1	0.801 7	0.119 10	0.860 6	0.000 1	0.687 1	0.001 9	0.192 11	0.679 6	0.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
OA-CNN-L_ScanNet200	0.333 6	0.558 2	0.269 6	0.124 8	0.448 10	0.080 6	0.272 3	0.000 1	0.000 3	0.000 1	0.342 5	0.515 2	0.524 5	0.713 12	0.789 5	0.158 8	0.384 7	0.000 3	0.806 3	0.125 4	0.000 6	0.496 4	0.332 4	0.498 11	0.227 6	0.024 2	0.474 1	0.000 1	0.003 2	0.071 6	0.487 2	0.000 6	0.000 1	0.110 5	0.000 2	0.876 5	0.013 12	0.703 1	0.000 5	0.076 7	0.473 8	0.355 7	0.906 4	0.000 1	0.000 2	0.476 5	0.706 1	0.000 8	0.672 8	0.835 8	0.748 6	0.015 11	0.223 4	0.860 6	0.000 1	0.000 8	0.572 4	0.000 7	0.509 6	0.313 5	0.662 2	0.398 9	0.396 3	0.411 10	0.276 1	0.527 2	0.711 3	0.000 4	0.076 8	0.946 4	0.166 5	0.000 1	0.022 6	0.160 4	0.183 8	0.493 8	0.699 6	0.637 3	0.403 3	0.330 9	0.406 8	0.526 5	0.024 2	0.000 1	0.392 8	0.000 7	0.016 11	0.000 7	0.196 2	0.915 4	0.112 7	0.557 6	0.197 2	0.352 7	0.877 2	0.000 7	0.000 1	0.592 9	0.103 8	0.000 10	0.067 1	0.000 1	0.089 3	0.735 3	0.625 7	0.130 7	0.568 4	0.836 6	0.271 3	0.534 6	0.043 10	0.799 6	0.001 2	0.445 3	0.000 1	0.000 4	0.024 1	0.661 2	0.000 1	0.262 2	0.000 1	0.591 5	0.517 10	0.373 6	0.788 5	0.021 6	0.000 1	0.455 1	0.517 6	0.320 5	0.823 7	0.200 12	0.001 12	0.150 4	0.100 7	0.000 1	0.736 6	0.668 5	0.103 10	0.052 4	0.662 1	0.720 4	0.000 1	0.602 5	0.112 4	0.002 4	0.000 1	0.637 6	0.000 2	0.000 1	0.621 7	0.569 2	0.398 6	0.412 5	0.234 7	0.949 4	0.363 2	0.492 10	0.495 6	0.251 4	0.665 6	0.000 1	0.001 7	0.805 3	0.833 5	0.794 7	0.000 1	0.821 3	0.314 5	0.843 8	0.000 1	0.560 6	0.245 2	0.262 4	0.713 2	0.370 9

PPT-SpUNet-F.T.	0.332 7	0.556 3	0.270 4	0.123 9	0.519 2	0.091 4	0.349 2	0.000 1	0.000 3	0.000 1	0.339 6	0.383 7	0.498 8	0.833 4	0.807 3	0.241 3	0.584 4	0.000 3	0.755 4	0.124 5	0.000 6	0.608 2	0.330 5	0.530 7	0.314 1	0.000 5	0.374 5	0.000 1	0.000 3	0.197 2	0.459 4	0.000 6	0.000 1	0.117 3	0.000 2	0.876 5	0.095 2	0.682 5	0.000 5	0.086 6	0.518 5	0.433 2	0.930 2	0.000 1	0.000 2	0.563 3	0.542 9	0.077 5	0.715 2	0.858 6	0.756 3	0.008 12	0.171 7	0.874 5	0.000 1	0.039 4	0.550 6	0.000 7	0.545 4	0.256 6	0.657 6	0.453 3	0.351 5	0.449 8	0.213 3	0.392 7	0.611 8	0.000 4	0.037 10	0.946 4	0.138 9	0.000 1	0.000 8	0.063 6	0.308 2	0.537 5	0.796 3	0.673 2	0.323 8	0.392 7	0.400 9	0.509 6	0.000 3	0.000 1	0.649 1	0.000 7	0.023 7	0.000 7	0.000 3	0.914 5	0.002 11	0.506 11	0.163 6	0.359 6	0.872 4	0.000 7	0.000 1	0.623 4	0.112 4	0.001 9	0.000 4	0.000 1	0.021 4	0.753 1	0.565 11	0.150 2	0.579 2	0.806 8	0.267 4	0.616 2	0.042 11	0.783 8	0.000 3	0.374 8	0.000 1	0.000 4	0.000 2	0.620 5	0.000 1	0.000 5	0.000 1	0.572 10	0.634 3	0.350 7	0.792 3	0.000 7	0.000 1	0.376 6	0.535 4	0.378 3	0.855 4	0.672 2	0.074 8	0.000 7	0.185 5	0.000 1	0.727 7	0.660 7	0.076 12	0.000 7	0.432 7	0.646 6	0.000 1	0.594 6	0.006 10	0.000 5	0.000 1	0.658 4	0.000 2	0.000 1	0.661 2	0.549 5	0.300 9	0.291 8	0.045 9	0.942 7	0.304 4	0.600 6	0.572 4	0.135 11	0.695 3	0.000 1	0.008 5	0.793 4	0.942 1	0.899 2	0.000 1	0.816 4	0.181 7	0.897 2	0.000 1	0.679 3	0.223 3	0.264 3	0.691 3	0.345 10
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormer ScanNet200	0.326 8	0.539 7	0.265 7	0.131 7	0.499 4	0.110 1	0.522 1	0.000 1	0.000 3	0.000 1	0.318 8	0.427 4	0.455 10	0.743 10	0.765 8	0.175 7	0.842 1	0.000 3	0.828 2	0.204 1	0.033 3	0.429 7	0.335 3	0.601 1	0.312 2	0.000 5	0.357 7	0.000 1	0.000 3	0.047 8	0.423 6	0.000 6	0.000 1	0.105 6	0.000 2	0.873 7	0.079 8	0.670 8	0.000 5	0.117 3	0.471 9	0.432 3	0.829 8	0.000 1	0.000 2	0.584 2	0.417 12	0.089 4	0.684 7	0.837 7	0.705 11	0.021 10	0.178 6	0.892 3	0.000 1	0.028 5	0.505 8	0.000 7	0.457 7	0.200 9	0.662 2	0.412 7	0.244 10	0.496 6	0.000 12	0.451 5	0.626 6	0.000 4	0.102 6	0.943 7	0.138 9	0.000 1	0.000 8	0.149 5	0.291 3	0.534 6	0.722 4	0.632 4	0.331 7	0.253 11	0.453 6	0.487 8	0.000 3	0.000 1	0.479 4	0.000 7	0.022 8	0.000 7	0.000 3	0.900 6	0.128 6	0.684 2	0.164 5	0.413 2	0.854 8	0.000 7	0.000 1	0.512 11	0.074 12	0.003 8	0.000 4	0.000 1	0.000 6	0.469 10	0.613 8	0.132 6	0.529 5	0.871 2	0.227 11	0.582 5	0.026 12	0.787 7	0.000 3	0.339 10	0.000 1	0.000 4	0.000 2	0.626 4	0.000 1	0.029 4	0.000 1	0.587 6	0.612 5	0.411 5	0.724 7	0.000 7	0.000 1	0.407 3	0.552 3	0.513 1	0.849 5	0.655 3	0.408 2	0.000 7	0.296 2	0.000 1	0.686 10	0.645 9	0.145 6	0.022 5	0.414 9	0.633 7	0.000 1	0.637 1	0.224 1	0.000 5	0.000 1	0.650 5	0.000 2	0.000 1	0.622 6	0.535 7	0.343 7	0.483 3	0.230 8	0.943 6	0.289 5	0.618 5	0.596 2	0.140 8	0.679 5	0.000 1	0.022 2	0.783 6	0.620 9	0.906 1	0.000 1	0.806 6	0.137 9	0.865 3	0.000 1	0.378 8	0.000 10	0.168 12	0.680 5	0.227 11
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CeCo	0.340 4	0.551 6	0.247 8	0.181 3	0.475 8	0.057 12	0.142 9	0.000 1	0.000 3	0.000 1	0.387 3	0.463 3	0.499 7	0.924 2	0.774 7	0.213 4	0.257 8	0.000 3	0.546 10	0.100 8	0.006 5	0.615 1	0.177 12	0.534 5	0.246 4	0.000 5	0.400 2	0.000 1	0.338 1	0.006 11	0.484 3	0.609 2	0.000 1	0.083 8	0.000 2	0.873 7	0.089 5	0.661 9	0.000 5	0.048 11	0.560 2	0.408 5	0.892 5	0.000 1	0.000 2	0.586 1	0.616 5	0.000 8	0.692 6	0.900 3	0.721 7	0.162 1	0.228 3	0.860 6	0.000 1	0.000 8	0.575 2	0.083 3	0.550 3	0.347 2	0.624 8	0.410 8	0.360 4	0.740 2	0.109 8	0.321 10	0.660 5	0.000 4	0.121 4	0.939 8	0.143 7	0.000 1	0.400 1	0.003 8	0.190 7	0.564 3	0.652 7	0.615 6	0.421 2	0.304 10	0.579 1	0.547 4	0.000 3	0.000 1	0.296 9	0.000 7	0.030 6	0.096 4	0.000 3	0.916 3	0.037 8	0.551 7	0.171 4	0.376 5	0.865 5	0.286 3	0.000 1	0.633 2	0.102 9	0.027 6	0.011 3	0.000 1	0.000 6	0.474 9	0.742 2	0.133 5	0.311 8	0.824 7	0.242 8	0.503 9	0.068 6	0.828 4	0.000 3	0.429 4	0.000 1	0.063 3	0.000 2	0.781 1	0.000 1	0.000 5	0.000 1	0.665 1	0.633 4	0.450 4	0.818 2	0.000 7	0.000 1	0.429 2	0.532 5	0.226 8	0.825 6	0.510 8	0.377 3	0.709 1	0.079 9	0.000 1	0.753 3	0.683 3	0.102 11	0.063 3	0.401 11	0.620 9	0.000 1	0.619 2	0.000 11	0.000 5	0.000 1	0.595 10	0.000 2	0.000 1	0.345 9	0.564 3	0.411 5	0.603 1	0.384 4	0.945 5	0.266 6	0.643 4	0.367 9	0.304 1	0.663 7	0.000 1	0.010 3	0.726 10	0.767 6	0.898 3	0.000 1	0.784 8	0.435 1	0.861 5	0.000 1	0.447 7	0.000 10	0.257 5	0.656 8	0.377 8
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
AWCS	0.305 9	0.508 9	0.225 9	0.142 6	0.463 9	0.063 10	0.195 7	0.000 1	0.000 3	0.000 1	0.467 2	0.551 1	0.504 6	0.773 6	0.764 9	0.142 9	0.029 12	0.000 3	0.626 8	0.100 8	0.000 6	0.360 9	0.179 10	0.507 10	0.137 10	0.006 4	0.300 9	0.000 1	0.000 3	0.172 5	0.364 10	0.512 4	0.000 1	0.056 9	0.000 2	0.865 9	0.093 4	0.634 12	0.000 5	0.071 9	0.396 10	0.296 11	0.876 6	0.000 1	0.000 2	0.373 9	0.436 11	0.063 7	0.749 1	0.877 5	0.721 7	0.131 3	0.124 9	0.804 10	0.000 1	0.000 8	0.515 7	0.010 6	0.452 8	0.252 7	0.578 9	0.417 6	0.179 12	0.484 7	0.171 4	0.337 9	0.606 9	0.000 4	0.115 5	0.937 9	0.142 8	0.000 1	0.008 7	0.000 10	0.157 11	0.484 9	0.402 12	0.501 10	0.339 6	0.553 4	0.529 2	0.478 9	0.000 3	0.000 1	0.404 7	0.001 6	0.022 8	0.077 6	0.000 3	0.894 8	0.219 4	0.628 5	0.093 10	0.305 9	0.886 1	0.233 4	0.000 1	0.603 6	0.112 4	0.023 7	0.000 4	0.000 1	0.000 6	0.741 2	0.664 5	0.097 10	0.253 9	0.782 9	0.264 6	0.523 8	0.154 1	0.707 11	0.000 3	0.411 5	0.000 1	0.000 4	0.000 2	0.332 11	0.000 1	0.000 5	0.000 1	0.602 4	0.595 7	0.185 10	0.656 11	0.159 4	0.000 1	0.355 8	0.424 10	0.154 10	0.729 10	0.516 7	0.220 7	0.620 2	0.084 8	0.000 1	0.707 9	0.651 8	0.173 3	0.014 6	0.381 12	0.582 10	0.000 1	0.619 2	0.049 9	0.000 5	0.000 1	0.702 2	0.000 2	0.000 1	0.302 11	0.489 10	0.317 8	0.334 7	0.392 3	0.922 9	0.254 8	0.533 9	0.394 8	0.129 12	0.613 10	0.000 1	0.000 8	0.820 2	0.649 8	0.749 9	0.000 1	0.782 9	0.282 6	0.863 4	0.000 1	0.288 11	0.006 7	0.220 8	0.633 9	0.542 2

LGround	0.272 10	0.485 10	0.184 10	0.106 10	0.476 7	0.077 7	0.218 6	0.000 1	0.000 3	0.000 1	0.547 1	0.295 8	0.540 4	0.746 9	0.745 10	0.058 11	0.112 11	0.005 1	0.658 6	0.077 12	0.000 6	0.322 10	0.178 11	0.512 9	0.190 8	0.199 1	0.277 10	0.000 1	0.000 3	0.173 4	0.399 7	0.000 6	0.000 1	0.039 11	0.000 2	0.858 10	0.085 6	0.676 7	0.002 3	0.103 4	0.498 6	0.323 9	0.703 9	0.000 1	0.000 2	0.296 10	0.549 7	0.216 1	0.702 4	0.768 9	0.718 9	0.028 8	0.092 11	0.786 11	0.000 1	0.000 8	0.453 11	0.022 5	0.251 12	0.252 7	0.572 10	0.348 10	0.321 6	0.514 5	0.063 10	0.279 11	0.552 10	0.000 4	0.019 11	0.932 10	0.132 11	0.000 1	0.000 8	0.000 10	0.156 12	0.457 10	0.623 8	0.518 9	0.265 11	0.358 8	0.381 10	0.395 10	0.000 3	0.000 1	0.127 12	0.012 4	0.051 1	0.000 7	0.000 3	0.886 9	0.014 9	0.437 12	0.179 3	0.244 10	0.826 10	0.000 7	0.000 1	0.599 7	0.136 1	0.085 3	0.000 4	0.000 1	0.000 6	0.565 8	0.612 9	0.143 3	0.207 10	0.566 10	0.232 10	0.446 10	0.127 2	0.708 10	0.000 3	0.384 6	0.000 1	0.000 4	0.000 2	0.402 9	0.000 1	0.059 3	0.000 1	0.525 12	0.566 8	0.229 9	0.659 10	0.000 7	0.000 1	0.265 10	0.446 9	0.147 11	0.720 12	0.597 5	0.066 9	0.000 7	0.187 4	0.000 1	0.726 8	0.467 12	0.134 8	0.000 7	0.413 10	0.629 8	0.000 1	0.363 11	0.055 7	0.022 2	0.000 1	0.626 8	0.000 2	0.000 1	0.323 10	0.479 12	0.154 11	0.117 10	0.028 11	0.901 10	0.243 10	0.415 11	0.295 12	0.143 6	0.610 11	0.000 1	0.000 8	0.777 7	0.397 12	0.324 11	0.000 1	0.778 10	0.179 8	0.702 11	0.000 1	0.274 12	0.404 1	0.233 7	0.622 10	0.398 6
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrain	0.249 12	0.455 12	0.171 11	0.079 12	0.418 11	0.059 11	0.186 8	0.000 1	0.000 3	0.000 1	0.335 7	0.250 10	0.316 11	0.766 7	0.697 12	0.142 9	0.170 9	0.003 2	0.553 9	0.112 6	0.097 1	0.201 12	0.186 9	0.476 12	0.081 11	0.000 5	0.216 12	0.000 1	0.000 3	0.001 12	0.314 12	0.000 6	0.000 1	0.055 10	0.000 2	0.832 12	0.094 3	0.659 10	0.002 3	0.076 7	0.310 12	0.293 12	0.664 11	0.000 1	0.000 2	0.175 12	0.634 4	0.130 2	0.552 12	0.686 12	0.700 12	0.076 6	0.110 10	0.770 12	0.000 1	0.000 8	0.430 12	0.000 7	0.319 10	0.166 10	0.542 12	0.327 11	0.205 11	0.332 11	0.052 11	0.375 8	0.444 12	0.000 4	0.012 12	0.930 12	0.203 2	0.000 1	0.000 8	0.046 7	0.175 9	0.413 11	0.592 9	0.471 11	0.299 10	0.152 12	0.340 11	0.247 12	0.000 3	0.000 1	0.225 10	0.058 3	0.037 3	0.000 7	0.207 1	0.862 11	0.014 9	0.548 8	0.033 11	0.233 11	0.816 11	0.000 7	0.000 1	0.542 10	0.123 3	0.121 1	0.019 2	0.000 1	0.000 6	0.463 11	0.454 12	0.045 12	0.128 12	0.557 11	0.235 9	0.441 11	0.063 8	0.484 12	0.000 3	0.308 12	0.000 1	0.000 4	0.000 2	0.318 12	0.000 1	0.000 5	0.000 1	0.545 11	0.543 9	0.164 11	0.734 6	0.000 7	0.000 1	0.215 12	0.371 11	0.198 9	0.743 9	0.205 11	0.062 10	0.000 7	0.079 9	0.000 1	0.683 11	0.547 11	0.142 7	0.000 7	0.441 6	0.579 11	0.000 1	0.464 10	0.098 6	0.041 1	0.000 1	0.590 11	0.000 2	0.000 1	0.373 8	0.494 9	0.174 10	0.105 11	0.001 12	0.895 11	0.222 11	0.537 8	0.307 11	0.180 5	0.625 9	0.000 1	0.000 8	0.591 12	0.609 10	0.398 10	0.000 1	0.766 12	0.014 12	0.638 12	0.000 1	0.377 9	0.004 8	0.206 10	0.609 12	0.465 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34D	0.253 11	0.463 11	0.154 12	0.102 11	0.381 12	0.084 5	0.134 10	0.000 1	0.000 3	0.000 1	0.386 4	0.141 12	0.279 12	0.737 11	0.703 11	0.014 12	0.164 10	0.000 3	0.663 5	0.092 11	0.000 6	0.224 11	0.291 6	0.531 6	0.056 12	0.000 5	0.242 11	0.000 1	0.000 3	0.013 10	0.331 11	0.000 6	0.000 1	0.035 12	0.001 1	0.858 10	0.059 11	0.650 11	0.000 5	0.056 10	0.353 11	0.299 10	0.670 10	0.000 1	0.000 2	0.284 11	0.484 10	0.071 6	0.594 11	0.720 11	0.710 10	0.027 9	0.068 12	0.813 9	0.000 1	0.005 7	0.492 9	0.164 1	0.274 11	0.111 11	0.571 11	0.307 12	0.293 8	0.307 12	0.150 5	0.163 12	0.531 11	0.002 3	0.545 3	0.932 10	0.093 12	0.000 1	0.000 8	0.002 9	0.159 10	0.368 12	0.581 10	0.440 12	0.228 12	0.406 6	0.282 12	0.294 11	0.000 3	0.000 1	0.189 11	0.060 2	0.036 4	0.000 7	0.000 3	0.897 7	0.000 12	0.525 9	0.025 12	0.205 12	0.771 12	0.000 7	0.000 1	0.593 8	0.108 7	0.044 4	0.000 4	0.000 1	0.000 6	0.282 12	0.589 10	0.094 11	0.169 11	0.466 12	0.227 11	0.419 12	0.125 3	0.757 9	0.002 1	0.334 11	0.000 1	0.000 4	0.000 2	0.357 10	0.000 1	0.000 5	0.000 1	0.582 7	0.513 11	0.337 8	0.612 12	0.000 7	0.000 1	0.250 11	0.352 12	0.136 12	0.724 11	0.655 3	0.280 6	0.000 7	0.046 11	0.000 1	0.606 12	0.559 10	0.159 5	0.102 1	0.445 5	0.655 5	0.000 1	0.310 12	0.117 3	0.000 5	0.000 1	0.581 12	0.026 1	0.000 1	0.265 12	0.483 11	0.084 12	0.097 12	0.044 10	0.865 12	0.142 12	0.588 7	0.351 10	0.272 2	0.596 12	0.000 1	0.003 6	0.622 11	0.720 7	0.096 12	0.000 1	0.771 11	0.016 11	0.772 10	0.000 1	0.302 10	0.194 4	0.214 9	0.621 11	0.197 12
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019

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

Method	avg ap 50%	head ap 50%	common ap 50%	tail ap 50%	backpack	bag	ball	bar	basket	bathroom cabinet	bathroom stall	bathroom stall door	bathroom vanity	bathtub	bed	bench	bicycle	bin	blackboard	blanket	blinds	board	book	bookshelf	bottle	bowl	box	broom	bucket	bulletin board	cabinet	calendar	candle	cart	case of water bottles	ceiling	ceiling light	chair	clock	closet	closet rod	clothes	clothes dryer	coat rack	coffee kettle	coffee maker	coffee table	column	computer tower	copier	couch	counter	cup	curtain	cushion	decoration	desk	dining table	dish rack	dishwasher	door	doorframe	dresser	dumbbell	end table	fan	file cabinet	fire alarm	fire extinguisher	folded chair	hat	headphones	ironing board	jacket	keyboard	keyboard piano	kitchen cabinet	kitchen counter	ladder	lamp	laptop	laundry basket	laundry detergent	laundry hamper	ledge	light	light switch	machine	mailbox	mat	microwave	mini fridge	mirror	monitor	mouse	music stand	nightstand	object	office chair	oven	paper	paper bag	paper cutter	paper towel dispenser	paper towel roll	person	piano	picture	pillow	pipe	plant	plate	plunger	poster	power outlet	power strip	printer	projector	projector screen	rack	radiator	range hood	recycling bin	refrigerator	scale	seat	shelf	shoe	shower	shower curtain	shower curtain rod	shower floor	shower head	shower wall	sign	sink	soap dispenser	sofa chair	speaker	stair rail	stairs	stand	stool	storage bin	storage container	storage organizer	stove	structure	stuffed animal	suitcase	table	telephone	tissue box	toaster	toilet	toilet paper	toilet paper dispenser	towel	trash bin	trash can	tray	tube	tv	tv stand	vacuum cleaner	vent	wardrobe	washing machine	water bottle	water cooler	water pitcher	whiteboard	window	windowsill

TD3D Scannet200	0.320 2	0.501 2	0.264 2	0.164 2	0.506 3	0.062 2	0.500 1	0.000 1	0.000 1	0.000 1	0.208 1	0.431 2	0.252 3	1.000 1	0.733 3	0.587 2	0.000 2	0.008 2	0.000 3	0.106 1	0.000 2	0.356 1	0.123 4	0.686 1	0.101 2	0.000 1	0.152 2	0.000 1	0.000 2	0.226 1	0.280 3	0.000 2	0.000 1	0.250 1	0.000 1	0.619 2	0.061 3	0.841 1	0.000 1	0.000 2	0.167 1	0.194 1	0.333 2	0.000 2	0.000 1	0.667 2	0.820 1	0.250 3	0.790 4	1.000 1	0.879 2	0.077 1	0.094 3	0.708 1	0.217 2	0.049 2	0.634 1	0.792 1	0.331 4	0.033 5	0.716 2	0.159 2	0.396 2	0.331 4	0.099 2	0.415 1	0.842 1	0.000 2	0.458 1	0.542 1	0.000 1	0.101 2	0.000 1	0.218 1	0.513 2	0.500 2	0.458 2	0.104 2	0.516 1	0.456 1	0.268 4	0.000 1	0.000 1	0.400 1	0.022 1	0.233 2	0.143 2	0.000 1	0.677 1	0.400 1	0.504 5	0.095 3	0.083 5	0.890 2	0.061 2	0.000 1	0.906 1	0.076 2	0.231 1	0.125 2	0.000 2	0.003 2	0.792 3	0.881 1	0.000 2	0.098 3	0.125 4	0.498 5	0.459 2	0.063 1	0.715 1	0.000 2	0.241 4	0.000 1	0.396 2	0.063 1	0.605 1	0.000 1	0.000 2	0.000 1	0.448 5	0.629 3	0.202 2	0.967 1	0.250 2	0.038 1	0.192 1	0.185 2	0.083 4	1.000 1	1.000 1	0.857 2	0.000 2	0.470 2	0.012 1	0.565 3	0.798 1	0.621 1	0.111 1	0.500 1	1.000 1	0.017 2	0.509 1	0.000 1	0.008 1	1.000 1	0.525 2	0.000 1	0.000 1	0.332 3	0.679 1	0.264 2	0.333 2	0.267 1	1.000 1	0.549 1	0.299 5	0.387 2	0.328 3	0.744 4	0.000 1	0.000 2	0.435 5	1.000 1	0.283 4	0.000 1	0.196 1	0.817 1	0.000 1	0.472 1	0.222 3	0.123 4	0.560 2	0.156 2
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
Mask3D Scannet200	0.388 1	0.542 1	0.357 1	0.237 1	0.610 1	0.091 1	0.125 5	0.000 1	0.000 1	0.000 1	0.065 3	0.668 1	0.451 1	1.000 1	0.955 1	0.640 1	0.500 1	0.039 1	0.125 2	0.063 2	0.409 1	0.311 2	0.291 1	0.609 3	0.266 1	0.000 1	0.163 1	0.000 1	0.008 1	0.044 2	0.496 1	1.000 1	0.000 1	0.018 2	0.000 1	0.756 1	0.573 1	0.808 2	0.000 1	0.010 1	0.042 3	0.130 3	0.552 1	0.042 1	0.000 1	1.000 1	0.725 4	0.750 1	0.883 1	1.000 1	0.832 4	0.024 2	0.107 1	0.614 3	0.226 1	0.250 1	0.628 2	0.792 1	0.677 2	0.400 1	0.741 1	0.278 1	0.511 1	0.077 5	0.111 1	0.313 2	0.715 2	0.302 1	0.017 3	0.200 2	0.000 1	0.188 1	0.000 1	0.178 2	0.736 1	1.000 1	0.615 1	0.514 1	0.409 2	0.380 5	0.600 1	0.000 1	0.000 1	0.400 1	0.013 2	0.254 1	0.381 1	0.000 1	0.123 4	0.400 1	0.839 1	0.258 1	0.463 1	0.926 1	0.265 1	0.000 1	0.857 2	0.099 1	0.021 2	0.500 1	0.027 1	0.028 1	1.000 1	0.502 5	0.016 1	0.076 4	0.500 1	0.612 1	0.578 1	0.005 2	0.597 2	0.194 1	0.497 1	0.000 1	0.500 1	0.000 2	0.323 4	0.000 1	1.000 1	0.000 1	0.748 1	0.708 2	0.050 4	0.890 2	1.000 1	0.008 2	0.151 3	0.301 1	1.000 1	1.000 1	0.792 3	0.945 1	1.000 1	0.511 1	0.004 2	0.753 1	0.776 2	0.287 2	0.020 2	0.003 4	0.974 3	0.033 1	0.412 5	0.000 1	0.000 2	0.000 2	0.667 1	0.000 1	0.000 1	0.491 1	0.676 2	0.352 1	0.335 1	0.060 2	0.822 5	0.527 2	1.000 1	0.517 1	0.606 1	0.853 1	0.000 1	0.004 1	0.806 1	1.000 1	0.727 1	0.000 1	0.042 2	0.739 2	0.000 1	0.399 3	0.391 1	0.504 1	0.591 1	0.571 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
Minkowski 34D Inst.	0.203 5	0.369 4	0.134 5	0.078 5	0.479 4	0.003 4	0.500 1	0.000 1	0.000 1	0.000 1	0.100 2	0.371 3	0.300 2	0.667 4	0.746 2	0.400 3	0.000 2	0.000 3	0.000 3	0.031 3	0.000 2	0.074 4	0.165 3	0.413 5	0.000 4	0.000 1	0.070 4	0.000 1	0.000 2	0.000 3	0.221 5	0.000 2	0.000 1	0.000 3	0.000 1	0.372 5	0.070 2	0.706 4	0.000 1	0.000 2	0.000 5	0.123 4	0.033 5	0.000 2	0.000 1	0.422 5	0.732 3	0.000 4	0.778 5	1.000 1	0.845 3	0.000 3	0.090 4	0.636 2	0.000 3	0.000 3	0.158 4	0.000 3	0.250 5	0.050 4	0.693 3	0.123 4	0.051 5	0.385 3	0.009 4	0.118 5	0.406 5	0.000 2	0.000 4	0.200 2	0.000 1	0.000 3	0.000 1	0.133 4	0.307 5	0.500 2	0.251 4	0.000 4	0.281 3	0.402 4	0.317 2	0.000 1	0.000 1	0.000 3	0.000 3	0.060 4	0.000 3	0.000 1	0.396 2	0.200 3	0.669 2	0.021 4	0.218 4	0.720 5	0.000 3	0.000 1	0.696 3	0.025 4	0.000 3	0.000 3	0.000 2	0.000 3	0.125 5	0.596 2	0.000 2	0.191 1	0.500 1	0.595 2	0.369 4	0.000 3	0.500 4	0.000 2	0.143 5	0.000 1	0.000 3	0.000 2	0.226 5	0.000 1	0.000 2	0.000 1	0.701 2	0.511 4	0.000 5	0.851 4	0.000 3	0.000 3	0.150 4	0.052 5	0.100 3	0.981 3	0.500 4	0.286 3	0.000 2	0.000 5	0.000 3	0.545 4	0.522 5	0.250 3	0.000 3	0.000 5	0.522 5	0.000 3	0.500 2	0.000 1	0.000 2	0.000 2	0.282 5	0.000 1	0.000 1	0.178 5	0.382 4	0.018 5	0.056 4	0.000 3	0.997 3	0.107 5	0.677 2	0.313 4	0.000 4	0.726 5	0.000 1	0.000 2	0.583 4	0.903 4	0.200 5	0.000 1	0.000 3	0.333 4	0.000 1	0.442 2	0.083 4	0.109 5	0.387 4	0.000 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.	0.209 4	0.361 5	0.157 4	0.085 4	0.506 2	0.007 3	0.500 1	0.000 1	0.000 1	0.000 1	0.000 5	0.093 5	0.221 4	0.667 4	0.524 5	0.400 3	0.000 2	0.000 3	0.000 3	0.004 4	0.000 2	0.000 5	0.109 5	0.589 4	0.000 4	0.000 1	0.059 5	0.000 1	0.000 2	0.000 3	0.322 2	0.000 2	0.000 1	0.000 3	0.000 1	0.405 3	0.055 4	0.700 5	0.000 1	0.000 2	0.028 4	0.091 5	0.083 3	0.000 2	0.000 1	0.667 2	0.768 2	0.000 4	0.807 3	1.000 1	0.776 5	0.000 3	0.000 5	0.340 5	0.000 3	0.000 3	0.103 5	0.000 3	0.750 1	0.200 3	0.634 5	0.053 5	0.246 3	0.677 2	0.006 5	0.198 3	0.432 4	0.000 2	0.000 4	0.050 4	0.000 1	0.000 3	0.000 1	0.111 5	0.356 4	0.500 2	0.188 5	0.000 4	0.220 4	0.448 2	0.050 5	0.000 1	0.000 1	0.000 3	0.000 3	0.032 5	0.000 3	0.000 1	0.396 2	0.000 4	0.573 4	0.000 5	0.228 3	0.747 4	0.000 3	0.000 1	0.573 5	0.021 5	0.000 3	0.000 3	0.000 2	0.000 3	0.500 4	0.573 3	0.000 2	0.000 5	0.125 4	0.592 3	0.364 5	0.000 3	0.450 5	0.000 2	0.364 2	0.000 1	0.000 3	0.000 2	0.340 3	0.000 1	0.000 2	0.000 1	0.610 3	0.833 1	0.221 1	0.702 5	0.000 3	0.000 3	0.135 5	0.094 4	0.125 2	0.571 4	0.500 4	0.143 5	0.000 2	0.125 3	0.000 3	0.618 2	0.667 4	0.115 5	0.000 3	0.125 2	1.000 1	0.000 3	0.500 2	0.000 1	0.000 2	0.000 2	0.502 4	0.000 1	0.000 1	0.312 4	0.248 5	0.050 4	0.000 5	0.000 3	0.997 3	0.420 3	0.500 4	0.149 5	0.451 2	0.748 2	0.000 1	0.000 2	0.636 3	0.667 5	0.600 2	0.000 1	0.000 3	0.278 5	0.000 1	0.333 4	0.000 5	0.294 2	0.381 5	0.110 3
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.	0.246 3	0.413 3	0.170 3	0.130 3	0.455 5	0.003 5	0.500 1	0.000 1	0.000 1	0.000 1	0.017 4	0.333 4	0.111 5	1.000 1	0.681 4	0.400 3	0.000 2	0.000 3	1.000 1	0.003 5	0.000 2	0.167 3	0.190 2	0.637 2	0.067 3	0.000 1	0.081 3	0.000 1	0.000 2	0.000 3	0.264 4	0.000 2	0.000 1	0.000 3	0.000 1	0.387 4	0.031 5	0.754 3	0.000 1	0.000 2	0.151 2	0.135 2	0.056 4	0.000 2	0.000 1	0.582 4	0.589 5	0.500 2	0.815 2	1.000 1	0.903 1	0.000 3	0.097 2	0.588 4	0.000 3	0.000 3	0.234 3	0.000 3	0.500 3	0.400 1	0.682 4	0.156 3	0.159 4	0.750 1	0.046 3	0.125 4	0.660 3	0.000 2	0.200 2	0.000 5	0.000 1	0.000 3	0.000 1	0.164 3	0.402 3	0.500 2	0.373 3	0.025 3	0.143 5	0.426 3	0.317 2	0.000 1	0.000 1	0.000 3	0.000 3	0.063 3	0.000 3	0.000 1	0.000 5	0.000 4	0.575 3	0.250 2	0.241 2	0.772 3	0.000 3	0.000 1	0.653 4	0.034 3	0.000 3	0.000 3	0.000 2	0.000 3	1.000 1	0.561 4	0.000 2	0.100 2	0.500 1	0.541 4	0.452 3	0.000 3	0.581 3	0.000 2	0.364 2	0.000 1	0.000 3	0.000 2	0.571 2	0.000 1	0.000 2	0.000 1	0.568 4	0.511 4	0.167 3	0.857 3	0.000 3	0.000 3	0.164 2	0.112 3	0.000 5	0.530 5	1.000 1	0.286 3	0.000 2	0.125 3	0.000 3	0.464 5	0.706 3	0.208 4	0.000 3	0.125 2	0.744 4	0.000 3	0.500 2	0.000 1	0.000 2	0.000 2	0.511 3	0.000 1	0.000 1	0.344 2	0.541 3	0.068 3	0.333 2	0.000 3	1.000 1	0.196 4	0.533 3	0.318 3	0.000 4	0.748 3	0.000 1	0.000 2	0.690 2	1.000 1	0.400 3	0.000 1	0.000 3	0.667 3	0.000 1	0.333 4	0.333 2	0.270 3	0.399 3	0.083 4
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.

ScanNet Benchmark

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

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

PTv3 ScanNet	0.794 1	0.941 3	0.813 18	0.851 7	0.782 6	0.890 2	0.597 1	0.916 2	0.696 8	0.713 3	0.979 1	0.635 1	0.384 2	0.793 2	0.907 8	0.821 4	0.790 30	0.696 11	0.967 3	0.903 1	0.805 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)
PonderV2	0.785 2	0.978 1	0.800 26	0.833 22	0.788 4	0.853 16	0.545 16	0.910 5	0.713 1	0.705 4	0.979 1	0.596 7	0.390 1	0.769 11	0.832 41	0.821 4	0.792 29	0.730 1	0.975 1	0.897 4	0.785 4
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 3	0.964 2	0.855 1	0.843 16	0.781 7	0.858 12	0.575 6	0.831 32	0.685 14	0.714 2	0.979 1	0.594 8	0.310 26	0.801 1	0.892 16	0.841 2	0.819 4	0.723 4	0.940 13	0.887 6	0.725 23
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 4	0.861 20	0.818 14	0.836 19	0.790 3	0.875 4	0.576 5	0.905 6	0.704 5	0.739 1	0.969 10	0.611 2	0.349 10	0.756 21	0.958 1	0.702 44	0.805 14	0.708 7	0.916 31	0.898 3	0.801 2

TTT-KD	0.773 5	0.646 90	0.818 14	0.809 34	0.774 9	0.878 3	0.581 2	0.943 1	0.687 12	0.704 5	0.978 4	0.607 5	0.336 15	0.775 8	0.912 6	0.838 3	0.823 2	0.694 12	0.967 3	0.899 2	0.794 3
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 6	0.939 4	0.824 6	0.854 6	0.771 10	0.840 30	0.564 10	0.900 8	0.686 13	0.677 11	0.961 16	0.537 30	0.348 11	0.769 11	0.903 10	0.785 10	0.815 6	0.676 21	0.939 14	0.880 11	0.772 8

PPT-SpUNet-Joint	0.766 7	0.932 5	0.794 32	0.829 24	0.751 22	0.854 14	0.540 20	0.903 7	0.630 33	0.672 14	0.963 14	0.565 21	0.357 8	0.788 3	0.900 12	0.737 25	0.802 15	0.685 16	0.950 7	0.887 6	0.780 5
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 7	0.925 7	0.808 22	0.849 9	0.786 5	0.846 26	0.566 9	0.876 14	0.690 10	0.674 13	0.960 17	0.576 17	0.226 66	0.753 23	0.904 9	0.777 12	0.815 6	0.722 5	0.923 27	0.877 13	0.776 7
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net	0.764 9	0.924 8	0.819 12	0.840 17	0.757 17	0.853 16	0.580 3	0.848 25	0.709 3	0.643 23	0.958 20	0.587 12	0.295 32	0.753 23	0.884 20	0.758 19	0.815 6	0.725 3	0.927 24	0.867 21	0.743 14

OccuSeg+Semantic	0.764 9	0.758 58	0.796 30	0.839 18	0.746 24	0.907 1	0.562 11	0.850 24	0.680 16	0.672 14	0.978 4	0.610 3	0.335 17	0.777 6	0.819 44	0.847 1	0.830 1	0.691 14	0.972 2	0.885 8	0.727 21

O-CNN	0.762 11	0.924 8	0.823 7	0.844 15	0.770 11	0.852 18	0.577 4	0.847 27	0.711 2	0.640 27	0.958 20	0.592 9	0.217 72	0.762 16	0.888 17	0.758 19	0.813 10	0.726 2	0.932 22	0.868 20	0.744 13
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
DTC	0.757 12	0.843 26	0.820 10	0.847 12	0.791 2	0.862 10	0.511 32	0.870 16	0.707 4	0.652 19	0.954 34	0.604 6	0.279 43	0.760 17	0.942 2	0.734 26	0.766 43	0.701 10	0.884 53	0.874 18	0.736 15

OA-CNN-L_ScanNet20	0.756 13	0.783 44	0.826 5	0.858 4	0.776 8	0.837 33	0.548 15	0.896 11	0.649 25	0.675 12	0.962 15	0.586 13	0.335 17	0.771 10	0.802 48	0.770 15	0.787 32	0.691 14	0.936 17	0.880 11	0.761 10

ConDaFormer	0.755 14	0.927 6	0.822 8	0.836 19	0.801 1	0.849 21	0.516 30	0.864 21	0.651 24	0.680 10	0.958 20	0.584 15	0.282 40	0.759 19	0.855 31	0.728 28	0.802 15	0.678 18	0.880 58	0.873 19	0.756 11
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
PNE	0.755 14	0.786 42	0.835 4	0.834 21	0.758 15	0.849 21	0.570 8	0.836 31	0.648 26	0.668 16	0.978 4	0.581 16	0.367 6	0.683 34	0.856 29	0.804 6	0.801 19	0.678 18	0.961 5	0.889 5	0.716 28
P. Hermosilla: Point Neighborhood Embeddings.
DMF-Net	0.752 16	0.906 12	0.793 34	0.802 40	0.689 39	0.825 45	0.556 12	0.867 17	0.681 15	0.602 43	0.960 17	0.555 26	0.365 7	0.779 5	0.859 26	0.747 22	0.795 26	0.717 6	0.917 30	0.856 29	0.764 9
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
PointTransformerV2	0.752 16	0.742 66	0.809 21	0.872 1	0.758 15	0.860 11	0.552 13	0.891 12	0.610 40	0.687 6	0.960 17	0.559 24	0.304 29	0.766 14	0.926 4	0.767 16	0.797 22	0.644 32	0.942 11	0.876 16	0.722 25
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer	0.749 18	0.793 40	0.790 35	0.807 36	0.750 23	0.856 13	0.524 26	0.881 13	0.588 52	0.642 26	0.977 8	0.591 10	0.274 46	0.781 4	0.929 3	0.804 6	0.796 23	0.642 33	0.947 9	0.885 8	0.715 29
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNet	0.749 18	0.909 10	0.818 14	0.811 32	0.752 20	0.839 32	0.485 46	0.842 28	0.673 17	0.644 22	0.957 24	0.528 36	0.305 28	0.773 9	0.859 26	0.788 8	0.818 5	0.693 13	0.916 31	0.856 29	0.723 24
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP	0.748 20	0.623 93	0.804 24	0.859 3	0.745 25	0.824 47	0.501 36	0.912 4	0.690 10	0.685 8	0.956 25	0.567 20	0.320 23	0.768 13	0.918 5	0.720 33	0.802 15	0.676 21	0.921 28	0.881 10	0.779 6

StratifiedFormer	0.747 21	0.901 13	0.803 25	0.845 14	0.757 17	0.846 26	0.512 31	0.825 35	0.696 8	0.645 21	0.956 25	0.576 17	0.262 57	0.744 28	0.861 25	0.742 23	0.770 41	0.705 8	0.899 43	0.860 26	0.734 16
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 22	0.870 18	0.838 2	0.858 4	0.729 30	0.850 20	0.501 36	0.874 15	0.587 53	0.658 18	0.956 25	0.564 22	0.299 30	0.765 15	0.900 12	0.716 36	0.812 11	0.631 38	0.939 14	0.858 27	0.709 30
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 22	0.771 52	0.819 12	0.848 11	0.702 36	0.865 9	0.397 84	0.899 9	0.699 6	0.664 17	0.948 54	0.588 11	0.330 19	0.746 27	0.851 35	0.764 17	0.796 23	0.704 9	0.935 18	0.866 22	0.728 19
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
Retro-FPN	0.744 24	0.842 27	0.800 26	0.767 54	0.740 26	0.836 35	0.541 18	0.914 3	0.672 18	0.626 31	0.958 20	0.552 27	0.272 48	0.777 6	0.886 19	0.696 45	0.801 19	0.674 24	0.941 12	0.858 27	0.717 26
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 25	0.620 94	0.799 29	0.849 9	0.730 29	0.822 49	0.493 43	0.897 10	0.664 19	0.681 9	0.955 28	0.562 23	0.378 3	0.760 17	0.903 10	0.738 24	0.801 19	0.673 25	0.907 35	0.877 13	0.745 12
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT	0.742 26	0.860 21	0.765 48	0.819 27	0.769 12	0.848 23	0.533 22	0.829 33	0.663 20	0.631 30	0.955 28	0.586 13	0.274 46	0.753 23	0.896 14	0.729 27	0.760 49	0.666 27	0.921 28	0.855 31	0.733 17

LRPNet	0.742 26	0.816 35	0.806 23	0.807 36	0.752 20	0.828 43	0.575 6	0.839 30	0.699 6	0.637 28	0.954 34	0.520 39	0.320 23	0.755 22	0.834 39	0.760 18	0.772 38	0.676 21	0.915 33	0.862 24	0.717 26

LargeKernel3D	0.739 28	0.909 10	0.820 10	0.806 38	0.740 26	0.852 18	0.545 16	0.826 34	0.594 51	0.643 23	0.955 28	0.541 29	0.263 56	0.723 32	0.858 28	0.775 14	0.767 42	0.678 18	0.933 20	0.848 36	0.694 35
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
MinkowskiNet	0.736 29	0.859 22	0.818 14	0.832 23	0.709 34	0.840 30	0.521 28	0.853 23	0.660 22	0.643 23	0.951 44	0.544 28	0.286 38	0.731 30	0.893 15	0.675 54	0.772 38	0.683 17	0.874 65	0.852 34	0.727 21
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
RPN	0.736 29	0.776 48	0.790 35	0.851 7	0.754 19	0.854 14	0.491 45	0.866 19	0.596 50	0.686 7	0.955 28	0.536 31	0.342 13	0.624 49	0.869 22	0.787 9	0.802 15	0.628 39	0.927 24	0.875 17	0.704 32

IPCA	0.731 31	0.890 14	0.837 3	0.864 2	0.726 31	0.873 5	0.530 25	0.824 36	0.489 86	0.647 20	0.978 4	0.609 4	0.336 15	0.624 49	0.733 57	0.758 19	0.776 36	0.570 64	0.949 8	0.877 13	0.728 19

SparseConvNet	0.725 32	0.647 89	0.821 9	0.846 13	0.721 32	0.869 6	0.533 22	0.754 57	0.603 46	0.614 35	0.955 28	0.572 19	0.325 21	0.710 33	0.870 21	0.724 31	0.823 2	0.628 39	0.934 19	0.865 23	0.683 38

PointTransformer++	0.725 32	0.727 74	0.811 20	0.819 27	0.765 13	0.841 29	0.502 35	0.814 41	0.621 36	0.623 33	0.955 28	0.556 25	0.284 39	0.620 51	0.866 23	0.781 11	0.757 53	0.648 30	0.932 22	0.862 24	0.709 30

MatchingNet	0.724 34	0.812 37	0.812 19	0.810 33	0.735 28	0.834 37	0.495 42	0.860 22	0.572 60	0.602 43	0.954 34	0.512 41	0.280 42	0.757 20	0.845 37	0.725 30	0.780 34	0.606 49	0.937 16	0.851 35	0.700 34

INS-Conv-semantic	0.717 35	0.751 61	0.759 51	0.812 31	0.704 35	0.868 7	0.537 21	0.842 28	0.609 42	0.608 39	0.953 38	0.534 33	0.293 33	0.616 52	0.864 24	0.719 35	0.793 27	0.640 34	0.933 20	0.845 40	0.663 44

PointMetaBase	0.714 36	0.835 28	0.785 37	0.821 25	0.684 41	0.846 26	0.531 24	0.865 20	0.614 37	0.596 47	0.953 38	0.500 44	0.246 62	0.674 35	0.888 17	0.692 46	0.764 45	0.624 41	0.849 80	0.844 41	0.675 40

contrastBoundary	0.705 37	0.769 55	0.775 42	0.809 34	0.687 40	0.820 52	0.439 72	0.812 42	0.661 21	0.591 49	0.945 62	0.515 40	0.171 90	0.633 46	0.856 29	0.720 33	0.796 23	0.668 26	0.889 50	0.847 37	0.689 36
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic	0.703 38	0.774 50	0.800 26	0.793 45	0.760 14	0.847 25	0.471 50	0.802 45	0.463 93	0.634 29	0.968 12	0.491 47	0.271 50	0.726 31	0.910 7	0.706 40	0.815 6	0.551 76	0.878 59	0.833 42	0.570 76

RFCR	0.702 39	0.889 15	0.745 62	0.813 30	0.672 44	0.818 56	0.493 43	0.815 40	0.623 34	0.610 37	0.947 56	0.470 56	0.249 61	0.594 55	0.848 36	0.705 41	0.779 35	0.646 31	0.892 48	0.823 48	0.611 59
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 40	0.825 32	0.796 30	0.723 61	0.716 33	0.832 39	0.433 74	0.816 38	0.634 31	0.609 38	0.969 10	0.418 82	0.344 12	0.559 67	0.833 40	0.715 37	0.808 13	0.560 70	0.902 40	0.847 37	0.680 39

JSENet	0.699 41	0.881 17	0.762 49	0.821 25	0.667 45	0.800 68	0.522 27	0.792 48	0.613 38	0.607 40	0.935 82	0.492 46	0.205 77	0.576 60	0.853 33	0.691 48	0.758 51	0.652 29	0.872 68	0.828 45	0.649 48
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 42	0.743 65	0.794 32	0.655 84	0.684 41	0.822 49	0.497 41	0.719 67	0.622 35	0.617 34	0.977 8	0.447 69	0.339 14	0.750 26	0.664 73	0.703 43	0.790 30	0.596 54	0.946 10	0.855 31	0.647 49
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 43	0.732 70	0.772 43	0.786 46	0.677 43	0.866 8	0.517 29	0.848 25	0.509 79	0.626 31	0.952 42	0.536 31	0.225 68	0.545 73	0.704 64	0.689 51	0.810 12	0.564 69	0.903 39	0.854 33	0.729 18
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNet	0.690 44	0.884 16	0.754 55	0.795 43	0.647 52	0.818 56	0.422 76	0.802 45	0.612 39	0.604 41	0.945 62	0.462 59	0.189 85	0.563 66	0.853 33	0.726 29	0.765 44	0.632 37	0.904 37	0.821 51	0.606 63
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 45	0.704 79	0.741 66	0.754 58	0.656 47	0.829 41	0.501 36	0.741 62	0.609 42	0.548 57	0.950 48	0.522 38	0.371 4	0.633 46	0.756 52	0.715 37	0.771 40	0.623 42	0.861 76	0.814 54	0.658 45
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 46	0.866 19	0.748 59	0.819 27	0.645 54	0.794 71	0.450 62	0.802 45	0.587 53	0.604 41	0.945 62	0.464 58	0.201 80	0.554 69	0.840 38	0.723 32	0.732 63	0.602 52	0.907 35	0.822 50	0.603 66

KP-FCNN	0.684 47	0.847 25	0.758 53	0.784 48	0.647 52	0.814 59	0.473 49	0.772 51	0.605 44	0.594 48	0.935 82	0.450 67	0.181 88	0.587 56	0.805 47	0.690 49	0.785 33	0.614 45	0.882 55	0.819 52	0.632 55
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 47	0.728 73	0.757 54	0.776 51	0.690 37	0.804 66	0.464 55	0.816 38	0.577 59	0.587 50	0.945 62	0.508 43	0.276 45	0.671 36	0.710 62	0.663 59	0.750 57	0.589 59	0.881 56	0.832 44	0.653 47

DGNet	0.684 47	0.712 78	0.784 38	0.782 50	0.658 46	0.835 36	0.499 40	0.823 37	0.641 28	0.597 46	0.950 48	0.487 49	0.281 41	0.575 61	0.619 77	0.647 67	0.764 45	0.620 44	0.871 71	0.846 39	0.688 37

PointContrast_LA_SEM	0.683 50	0.757 59	0.784 38	0.786 46	0.639 56	0.824 47	0.408 79	0.775 50	0.604 45	0.541 59	0.934 86	0.532 34	0.269 52	0.552 70	0.777 50	0.645 70	0.793 27	0.640 34	0.913 34	0.824 47	0.671 41

Superpoint Network	0.683 50	0.851 24	0.728 70	0.800 42	0.653 49	0.806 64	0.468 52	0.804 43	0.572 60	0.602 43	0.946 59	0.453 66	0.239 65	0.519 78	0.822 42	0.689 51	0.762 48	0.595 56	0.895 46	0.827 46	0.630 56

VI-PointConv	0.676 52	0.770 54	0.754 55	0.783 49	0.621 60	0.814 59	0.552 13	0.758 55	0.571 62	0.557 55	0.954 34	0.529 35	0.268 54	0.530 76	0.682 68	0.675 54	0.719 66	0.603 51	0.888 51	0.833 42	0.665 43
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 53	0.789 41	0.748 59	0.763 56	0.635 58	0.814 59	0.407 81	0.747 59	0.581 57	0.573 52	0.950 48	0.484 50	0.271 50	0.607 53	0.754 53	0.649 64	0.774 37	0.596 54	0.883 54	0.823 48	0.606 63

SALANet	0.670 54	0.816 35	0.770 46	0.768 53	0.652 50	0.807 63	0.451 59	0.747 59	0.659 23	0.545 58	0.924 92	0.473 55	0.149 100	0.571 63	0.811 46	0.635 73	0.746 58	0.623 42	0.892 48	0.794 67	0.570 76

O3DSeg	0.668 55	0.822 33	0.771 45	0.496 104	0.651 51	0.833 38	0.541 18	0.761 54	0.555 68	0.611 36	0.966 13	0.489 48	0.370 5	0.388 98	0.580 80	0.776 13	0.751 55	0.570 64	0.956 6	0.817 53	0.646 50

PointConv	0.666 56	0.781 45	0.759 51	0.699 69	0.644 55	0.822 49	0.475 48	0.779 49	0.564 65	0.504 75	0.953 38	0.428 76	0.203 79	0.586 58	0.754 53	0.661 60	0.753 54	0.588 60	0.902 40	0.813 56	0.642 51
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNL	0.666 56	0.703 80	0.781 40	0.751 60	0.655 48	0.830 40	0.471 50	0.769 52	0.474 89	0.537 61	0.951 44	0.475 54	0.279 43	0.635 44	0.698 67	0.675 54	0.751 55	0.553 75	0.816 87	0.806 58	0.703 33
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PPCNN++	0.663 58	0.746 63	0.708 73	0.722 62	0.638 57	0.820 52	0.451 59	0.566 95	0.599 48	0.541 59	0.950 48	0.510 42	0.313 25	0.648 41	0.819 44	0.616 78	0.682 81	0.590 58	0.869 72	0.810 57	0.656 46
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
MVF-GNN	0.658 59	0.558 101	0.751 57	0.655 84	0.690 37	0.722 93	0.453 58	0.867 17	0.579 58	0.576 51	0.893 104	0.523 37	0.293 33	0.733 29	0.571 82	0.692 46	0.659 88	0.606 49	0.875 62	0.804 60	0.668 42

DCM-Net	0.658 59	0.778 46	0.702 76	0.806 38	0.619 61	0.813 62	0.468 52	0.693 75	0.494 82	0.524 67	0.941 74	0.449 68	0.298 31	0.510 80	0.821 43	0.675 54	0.727 65	0.568 67	0.826 85	0.803 61	0.637 53
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN	0.656 61	0.698 82	0.743 64	0.650 86	0.564 78	0.820 52	0.505 34	0.758 55	0.631 32	0.479 79	0.945 62	0.480 52	0.226 66	0.572 62	0.774 51	0.690 49	0.735 61	0.614 45	0.853 79	0.776 82	0.597 69
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 62	0.752 60	0.734 68	0.664 82	0.583 73	0.815 58	0.399 83	0.754 57	0.639 29	0.535 63	0.942 72	0.470 56	0.309 27	0.665 37	0.539 84	0.650 63	0.708 71	0.635 36	0.857 78	0.793 69	0.642 51
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 63	0.778 46	0.731 69	0.699 69	0.577 74	0.829 41	0.446 64	0.736 63	0.477 88	0.523 69	0.945 62	0.454 63	0.269 52	0.484 88	0.749 56	0.618 76	0.738 59	0.599 53	0.827 84	0.792 72	0.621 58

PointConv-SFPN	0.641 64	0.776 48	0.703 75	0.721 63	0.557 81	0.826 44	0.451 59	0.672 80	0.563 66	0.483 78	0.943 71	0.425 79	0.162 95	0.644 42	0.726 58	0.659 61	0.709 70	0.572 63	0.875 62	0.786 77	0.559 82

MVPNet	0.641 64	0.831 29	0.715 71	0.671 79	0.590 69	0.781 77	0.394 85	0.679 77	0.642 27	0.553 56	0.937 79	0.462 59	0.256 58	0.649 40	0.406 98	0.626 74	0.691 78	0.666 27	0.877 60	0.792 72	0.608 62
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet	0.640 66	0.717 77	0.701 77	0.692 72	0.576 75	0.801 67	0.467 54	0.716 68	0.563 66	0.459 85	0.953 38	0.429 75	0.169 92	0.581 59	0.854 32	0.605 79	0.710 68	0.550 77	0.894 47	0.793 69	0.575 74

FPConv	0.639 67	0.785 43	0.760 50	0.713 67	0.603 64	0.798 69	0.392 86	0.534 100	0.603 46	0.524 67	0.948 54	0.457 61	0.250 60	0.538 74	0.723 60	0.598 83	0.696 76	0.614 45	0.872 68	0.799 62	0.567 79
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 68	0.797 39	0.769 47	0.641 92	0.590 69	0.820 52	0.461 56	0.537 99	0.637 30	0.536 62	0.947 56	0.388 89	0.206 76	0.656 38	0.668 71	0.647 67	0.732 63	0.585 61	0.868 73	0.793 69	0.473 102

PointSPNet	0.637 69	0.734 69	0.692 84	0.714 66	0.576 75	0.797 70	0.446 64	0.743 61	0.598 49	0.437 90	0.942 72	0.403 85	0.150 99	0.626 48	0.800 49	0.649 64	0.697 75	0.557 73	0.846 81	0.777 81	0.563 80

SConv	0.636 70	0.830 30	0.697 80	0.752 59	0.572 77	0.780 79	0.445 66	0.716 68	0.529 72	0.530 64	0.951 44	0.446 70	0.170 91	0.507 83	0.666 72	0.636 72	0.682 81	0.541 83	0.886 52	0.799 62	0.594 70

Supervoxel-CNN	0.635 71	0.656 87	0.711 72	0.719 64	0.613 62	0.757 88	0.444 69	0.765 53	0.534 71	0.566 53	0.928 90	0.478 53	0.272 48	0.636 43	0.531 86	0.664 58	0.645 92	0.508 90	0.864 75	0.792 72	0.611 59

joint point-based	0.634 72	0.614 95	0.778 41	0.667 81	0.633 59	0.825 45	0.420 77	0.804 43	0.467 91	0.561 54	0.951 44	0.494 45	0.291 35	0.566 64	0.458 93	0.579 89	0.764 45	0.559 72	0.838 82	0.814 54	0.598 68
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 73	0.731 71	0.688 87	0.675 76	0.591 68	0.784 76	0.444 69	0.565 96	0.610 40	0.492 76	0.949 52	0.456 62	0.254 59	0.587 56	0.706 63	0.599 82	0.665 87	0.612 48	0.868 73	0.791 75	0.579 73

3DSM_DMMF	0.631 74	0.626 92	0.745 62	0.801 41	0.607 63	0.751 89	0.506 33	0.729 66	0.565 64	0.491 77	0.866 107	0.434 71	0.197 83	0.595 54	0.630 76	0.709 39	0.705 73	0.560 70	0.875 62	0.740 92	0.491 97

PointNet2-SFPN	0.631 74	0.771 52	0.692 84	0.672 77	0.524 86	0.837 33	0.440 71	0.706 73	0.538 70	0.446 87	0.944 68	0.421 81	0.219 71	0.552 70	0.751 55	0.591 85	0.737 60	0.543 82	0.901 42	0.768 84	0.557 83

APCF-Net	0.631 74	0.742 66	0.687 89	0.672 77	0.557 81	0.792 74	0.408 79	0.665 81	0.545 69	0.508 72	0.952 42	0.428 76	0.186 86	0.634 45	0.702 65	0.620 75	0.706 72	0.555 74	0.873 66	0.798 64	0.581 72
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv	0.630 77	0.604 97	0.741 66	0.766 55	0.590 69	0.747 90	0.501 36	0.734 64	0.503 81	0.527 65	0.919 96	0.454 63	0.323 22	0.550 72	0.420 97	0.678 53	0.688 79	0.544 80	0.896 45	0.795 66	0.627 57
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 78	0.800 38	0.625 100	0.719 64	0.545 83	0.806 64	0.445 66	0.597 89	0.448 96	0.519 70	0.938 78	0.481 51	0.328 20	0.489 87	0.499 91	0.657 62	0.759 50	0.592 57	0.881 56	0.797 65	0.634 54

SegGroup_sem	0.627 79	0.818 34	0.747 61	0.701 68	0.602 65	0.764 85	0.385 90	0.629 86	0.490 84	0.508 72	0.931 89	0.409 84	0.201 80	0.564 65	0.725 59	0.618 76	0.692 77	0.539 84	0.873 66	0.794 67	0.548 86
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 80	0.830 30	0.694 82	0.757 57	0.563 79	0.772 83	0.448 63	0.647 84	0.520 75	0.509 71	0.949 52	0.431 74	0.191 84	0.496 85	0.614 78	0.647 67	0.672 85	0.535 86	0.876 61	0.783 78	0.571 75

dtc_net	0.625 80	0.703 80	0.751 57	0.794 44	0.535 84	0.848 23	0.480 47	0.676 79	0.528 73	0.469 82	0.944 68	0.454 63	0.004 113	0.464 90	0.636 75	0.704 42	0.758 51	0.548 79	0.924 26	0.787 76	0.492 96

HPEIN	0.618 82	0.729 72	0.668 90	0.647 88	0.597 67	0.766 84	0.414 78	0.680 76	0.520 75	0.525 66	0.946 59	0.432 72	0.215 73	0.493 86	0.599 79	0.638 71	0.617 97	0.570 64	0.897 44	0.806 58	0.605 65
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 83	0.858 23	0.772 43	0.489 105	0.532 85	0.792 74	0.404 82	0.643 85	0.570 63	0.507 74	0.935 82	0.414 83	0.046 110	0.510 80	0.702 65	0.602 81	0.705 73	0.549 78	0.859 77	0.773 83	0.534 89
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 84	0.760 57	0.667 91	0.649 87	0.521 87	0.793 72	0.457 57	0.648 83	0.528 73	0.434 92	0.947 56	0.401 86	0.153 98	0.454 91	0.721 61	0.648 66	0.717 67	0.536 85	0.904 37	0.765 85	0.485 98
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 85	0.634 91	0.743 64	0.697 71	0.601 66	0.781 77	0.437 73	0.585 92	0.493 83	0.446 87	0.933 87	0.394 87	0.011 112	0.654 39	0.661 74	0.603 80	0.733 62	0.526 87	0.832 83	0.761 87	0.480 99

LAP-D	0.594 86	0.720 75	0.692 84	0.637 93	0.456 97	0.773 82	0.391 88	0.730 65	0.587 53	0.445 89	0.940 76	0.381 90	0.288 36	0.434 94	0.453 95	0.591 85	0.649 90	0.581 62	0.777 91	0.749 91	0.610 61

DPC	0.592 87	0.720 75	0.700 78	0.602 97	0.480 93	0.762 87	0.380 91	0.713 71	0.585 56	0.437 90	0.940 76	0.369 92	0.288 36	0.434 94	0.509 90	0.590 87	0.639 95	0.567 68	0.772 93	0.755 89	0.592 71
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 88	0.766 56	0.659 95	0.683 74	0.470 96	0.740 92	0.387 89	0.620 88	0.490 84	0.476 80	0.922 94	0.355 95	0.245 63	0.511 79	0.511 89	0.571 90	0.643 93	0.493 94	0.872 68	0.762 86	0.600 67

ROSMRF	0.580 89	0.772 51	0.707 74	0.681 75	0.563 79	0.764 85	0.362 93	0.515 101	0.465 92	0.465 84	0.936 81	0.427 78	0.207 75	0.438 92	0.577 81	0.536 93	0.675 84	0.486 95	0.723 99	0.779 79	0.524 92

SD-DETR	0.576 90	0.746 63	0.609 104	0.445 109	0.517 88	0.643 104	0.366 92	0.714 70	0.456 94	0.468 83	0.870 106	0.432 72	0.264 55	0.558 68	0.674 69	0.586 88	0.688 79	0.482 96	0.739 97	0.733 94	0.537 88

SQN_0.1%	0.569 91	0.676 84	0.696 81	0.657 83	0.497 89	0.779 80	0.424 75	0.548 97	0.515 77	0.376 97	0.902 103	0.422 80	0.357 8	0.379 99	0.456 94	0.596 84	0.659 88	0.544 80	0.685 102	0.665 105	0.556 84

TextureNet	0.566 92	0.672 86	0.664 92	0.671 79	0.494 91	0.719 94	0.445 66	0.678 78	0.411 102	0.396 95	0.935 82	0.356 94	0.225 68	0.412 96	0.535 85	0.565 91	0.636 96	0.464 98	0.794 90	0.680 102	0.568 78
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 93	0.648 88	0.700 78	0.770 52	0.586 72	0.687 98	0.333 97	0.650 82	0.514 78	0.475 81	0.906 100	0.359 93	0.223 70	0.340 101	0.442 96	0.422 104	0.668 86	0.501 91	0.708 100	0.779 79	0.534 89

Pointnet++ & Feature	0.557 94	0.735 68	0.661 94	0.686 73	0.491 92	0.744 91	0.392 86	0.539 98	0.451 95	0.375 98	0.946 59	0.376 91	0.205 77	0.403 97	0.356 101	0.553 92	0.643 93	0.497 92	0.824 86	0.756 88	0.515 93

GMLPs	0.538 95	0.495 106	0.693 83	0.647 88	0.471 95	0.793 72	0.300 100	0.477 102	0.505 80	0.358 100	0.903 102	0.327 98	0.081 107	0.472 89	0.529 87	0.448 102	0.710 68	0.509 88	0.746 95	0.737 93	0.554 85

PanopticFusion-label	0.529 96	0.491 107	0.688 87	0.604 96	0.386 102	0.632 105	0.225 110	0.705 74	0.434 99	0.293 106	0.815 108	0.348 96	0.241 64	0.499 84	0.669 70	0.507 95	0.649 90	0.442 104	0.796 89	0.602 109	0.561 81
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 97	0.676 84	0.591 107	0.609 94	0.442 98	0.774 81	0.335 96	0.597 89	0.422 101	0.357 101	0.932 88	0.341 97	0.094 106	0.298 103	0.528 88	0.473 100	0.676 83	0.495 93	0.602 108	0.721 97	0.349 109

Online SegFusion	0.515 98	0.607 96	0.644 98	0.579 99	0.434 99	0.630 106	0.353 94	0.628 87	0.440 97	0.410 93	0.762 112	0.307 100	0.167 93	0.520 77	0.403 99	0.516 94	0.565 100	0.447 102	0.678 103	0.701 99	0.514 94
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 99	0.558 101	0.608 105	0.424 111	0.478 94	0.690 97	0.246 106	0.586 91	0.468 90	0.450 86	0.911 98	0.394 87	0.160 96	0.438 92	0.212 108	0.432 103	0.541 106	0.475 97	0.742 96	0.727 95	0.477 100

PCNN	0.498 100	0.559 100	0.644 98	0.560 101	0.420 101	0.711 96	0.229 108	0.414 103	0.436 98	0.352 102	0.941 74	0.324 99	0.155 97	0.238 108	0.387 100	0.493 96	0.529 107	0.509 88	0.813 88	0.751 90	0.504 95

Weakly-Openseg v3	0.489 101	0.749 62	0.664 92	0.646 90	0.496 90	0.559 110	0.122 113	0.577 93	0.257 113	0.364 99	0.805 109	0.198 111	0.096 105	0.510 80	0.496 92	0.361 108	0.563 101	0.359 111	0.777 91	0.644 106	0.532 91

3DMV	0.484 102	0.484 108	0.538 109	0.643 91	0.424 100	0.606 109	0.310 98	0.574 94	0.433 100	0.378 96	0.796 110	0.301 101	0.214 74	0.537 75	0.208 109	0.472 101	0.507 110	0.413 107	0.693 101	0.602 109	0.539 87
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 103	0.577 99	0.611 103	0.356 113	0.321 110	0.715 95	0.299 102	0.376 107	0.328 109	0.319 104	0.944 68	0.285 103	0.164 94	0.216 111	0.229 106	0.484 98	0.545 105	0.456 100	0.755 94	0.709 98	0.475 101
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 104	0.679 83	0.604 106	0.578 100	0.380 103	0.682 99	0.291 103	0.106 113	0.483 87	0.258 111	0.920 95	0.258 107	0.025 111	0.231 110	0.325 102	0.480 99	0.560 103	0.463 99	0.725 98	0.666 104	0.231 113
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproduce	0.446 105	0.474 109	0.623 101	0.463 107	0.366 105	0.651 102	0.310 98	0.389 106	0.349 107	0.330 103	0.937 79	0.271 105	0.126 102	0.285 104	0.224 107	0.350 110	0.577 99	0.445 103	0.625 106	0.723 96	0.394 105
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	0.442 106	0.548 103	0.548 108	0.597 98	0.363 106	0.628 107	0.300 100	0.292 108	0.374 104	0.307 105	0.881 105	0.268 106	0.186 86	0.238 108	0.204 110	0.407 105	0.506 111	0.449 101	0.667 104	0.620 108	0.462 103

SurfaceConvPF	0.442 106	0.505 105	0.622 102	0.380 112	0.342 108	0.654 101	0.227 109	0.397 105	0.367 105	0.276 108	0.924 92	0.240 108	0.198 82	0.359 100	0.262 104	0.366 106	0.581 98	0.435 105	0.640 105	0.668 103	0.398 104
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutions	0.438 108	0.437 111	0.646 97	0.474 106	0.369 104	0.645 103	0.353 94	0.258 110	0.282 111	0.279 107	0.918 97	0.298 102	0.147 101	0.283 105	0.294 103	0.487 97	0.562 102	0.427 106	0.619 107	0.633 107	0.352 108
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 109	0.525 104	0.647 96	0.522 102	0.324 109	0.488 113	0.077 114	0.712 72	0.353 106	0.401 94	0.636 114	0.281 104	0.176 89	0.340 101	0.565 83	0.175 114	0.551 104	0.398 108	0.370 114	0.602 109	0.361 107

SPLAT Net	0.393 110	0.472 110	0.511 110	0.606 95	0.311 111	0.656 100	0.245 107	0.405 104	0.328 109	0.197 112	0.927 91	0.227 110	0.000 115	0.001 115	0.249 105	0.271 113	0.510 108	0.383 110	0.593 109	0.699 100	0.267 111
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	0.383 111	0.297 113	0.491 111	0.432 110	0.358 107	0.612 108	0.274 104	0.116 112	0.411 102	0.265 109	0.904 101	0.229 109	0.079 108	0.250 106	0.185 111	0.320 111	0.510 108	0.385 109	0.548 110	0.597 112	0.394 105

PointNet++	0.339 112	0.584 98	0.478 112	0.458 108	0.256 113	0.360 114	0.250 105	0.247 111	0.278 112	0.261 110	0.677 113	0.183 112	0.117 103	0.212 112	0.145 113	0.364 107	0.346 114	0.232 114	0.548 110	0.523 113	0.252 112
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNet	0.308 113	0.353 112	0.290 114	0.278 114	0.166 114	0.553 111	0.169 112	0.286 109	0.147 114	0.148 114	0.908 99	0.182 113	0.064 109	0.023 114	0.018 115	0.354 109	0.363 112	0.345 112	0.546 112	0.685 101	0.278 110

ScanNet	0.306 114	0.203 114	0.366 113	0.501 103	0.311 111	0.524 112	0.211 111	0.002 115	0.342 108	0.189 113	0.786 111	0.145 114	0.102 104	0.245 107	0.152 112	0.318 112	0.348 113	0.300 113	0.460 113	0.437 114	0.182 114
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 115	0.000 115	0.041 115	0.172 115	0.030 115	0.062 115	0.001 115	0.035 114	0.004 115	0.051 115	0.143 115	0.019 115	0.003 114	0.041 113	0.050 114	0.003 115	0.054 115	0.018 115	0.005 115	0.264 115	0.082 115

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

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

Spherical Mask(CtoF)	0.812 1	1.000 1	0.973 4	0.852 11	0.718 4	0.917 5	0.574 4	0.677 27	0.748 9	0.729 8	0.715 5	0.795 2	0.809 2	1.000 1	0.831 2	0.854 7	0.787 8	1.000 1	0.638 4

SIM3D	0.803 2	1.000 1	0.964 5	0.841 14	0.683 14	0.924 4	0.539 8	0.724 21	0.670 16	0.717 9	0.685 10	0.806 1	0.824 1	1.000 1	0.800 6	0.851 10	0.778 12	1.000 1	0.641 3

OneFormer3D	0.801 3	1.000 1	0.973 3	0.909 5	0.698 10	0.928 2	0.582 3	0.668 31	0.685 14	0.780 2	0.687 9	0.698 14	0.702 12	1.000 1	0.794 8	0.900 2	0.784 10	0.986 48	0.635 5
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
UniPerception	0.800 4	1.000 1	0.930 7	0.872 9	0.727 3	0.862 20	0.454 14	0.764 13	0.820 1	0.746 6	0.706 7	0.750 4	0.772 8	0.926 41	0.764 14	0.818 24	0.826 1	0.997 36	0.660 2

InsSSM	0.799 5	1.000 1	0.915 9	0.710 37	0.729 2	0.925 3	0.664 1	0.670 29	0.770 6	0.766 3	0.739 2	0.737 5	0.700 13	1.000 1	0.792 9	0.829 18	0.815 3	0.997 36	0.625 7

TST3D	0.795 6	1.000 1	0.929 8	0.918 4	0.709 7	0.884 15	0.596 2	0.704 24	0.769 7	0.734 7	0.644 16	0.699 13	0.751 10	1.000 1	0.794 7	0.876 4	0.757 18	0.997 36	0.550 28

MG-Former	0.791 7	1.000 1	0.980 2	0.837 15	0.626 22	0.897 8	0.543 7	0.759 15	0.800 5	0.766 4	0.659 12	0.769 3	0.697 16	1.000 1	0.791 10	0.707 44	0.791 7	1.000 1	0.610 13

ExtMask3D	0.789 8	1.000 1	0.988 1	0.756 29	0.706 8	0.912 6	0.429 15	0.647 36	0.806 4	0.755 5	0.673 11	0.689 15	0.772 9	1.000 1	0.789 11	0.852 8	0.811 4	1.000 1	0.617 10

Queryformer	0.787 9	1.000 1	0.933 6	0.601 46	0.754 1	0.886 13	0.558 6	0.661 33	0.767 8	0.665 15	0.716 4	0.639 21	0.808 4	1.000 1	0.844 1	0.897 3	0.804 5	1.000 1	0.624 8

MAFT	0.786 10	1.000 1	0.894 14	0.807 19	0.694 12	0.893 11	0.486 10	0.674 28	0.740 10	0.786 1	0.704 8	0.727 7	0.739 11	1.000 1	0.707 20	0.849 11	0.756 19	1.000 1	0.685 1

Mask3D	0.780 11	1.000 1	0.786 38	0.716 35	0.696 11	0.885 14	0.500 9	0.714 22	0.810 3	0.672 14	0.715 5	0.679 17	0.809 2	1.000 1	0.831 2	0.833 16	0.787 8	1.000 1	0.602 16
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SPFormer	0.770 12	0.903 52	0.903 11	0.806 20	0.609 28	0.886 12	0.568 5	0.815 6	0.705 13	0.711 10	0.655 13	0.652 20	0.685 20	1.000 1	0.789 12	0.809 25	0.776 14	1.000 1	0.583 21
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SoftGroup++	0.769 13	1.000 1	0.803 31	0.937 1	0.684 13	0.865 17	0.213 31	0.870 2	0.664 18	0.571 21	0.758 1	0.702 11	0.807 5	1.000 1	0.653 27	0.902 1	0.792 6	1.000 1	0.626 6

SoftGroup	0.761 14	1.000 1	0.808 27	0.845 12	0.716 5	0.862 19	0.243 28	0.824 4	0.655 20	0.620 16	0.734 3	0.699 12	0.791 7	0.981 35	0.716 18	0.844 12	0.769 15	1.000 1	0.594 19
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
ISBNet	0.757 15	1.000 1	0.904 10	0.731 33	0.678 15	0.895 9	0.458 12	0.644 38	0.670 17	0.710 11	0.620 22	0.732 6	0.650 22	1.000 1	0.756 15	0.778 28	0.779 11	1.000 1	0.614 11
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
TD3D	0.751 16	1.000 1	0.774 39	0.867 10	0.621 24	0.934 1	0.404 17	0.706 23	0.812 2	0.605 19	0.633 19	0.626 22	0.690 18	1.000 1	0.640 29	0.820 21	0.777 13	1.000 1	0.612 12
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
PBNet	0.747 17	1.000 1	0.818 23	0.837 16	0.713 6	0.844 22	0.457 13	0.647 36	0.711 12	0.614 17	0.617 24	0.657 19	0.650 22	1.000 1	0.692 21	0.822 20	0.765 17	1.000 1	0.595 18
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
EV3D	0.747 17	1.000 1	0.696 56	0.755 30	0.675 16	0.909 7	0.420 16	0.724 20	0.599 24	0.683 12	0.631 20	0.689 16	0.689 19	1.000 1	0.822 5	0.842 13	0.699 23	1.000 1	0.605 14

GraphCut	0.732 19	1.000 1	0.788 36	0.724 34	0.642 21	0.859 21	0.248 27	0.787 11	0.618 23	0.596 20	0.653 15	0.722 9	0.583 43	1.000 1	0.766 13	0.861 5	0.825 2	1.000 1	0.504 34

IPCA-Inst	0.731 20	1.000 1	0.788 37	0.884 8	0.698 9	0.788 38	0.252 26	0.760 14	0.646 21	0.511 29	0.637 18	0.665 18	0.804 6	1.000 1	0.644 28	0.778 29	0.747 21	1.000 1	0.561 25

TopoSeg	0.725 21	1.000 1	0.806 30	0.933 2	0.668 18	0.758 42	0.272 25	0.734 19	0.630 22	0.549 25	0.654 14	0.606 23	0.697 17	0.966 38	0.612 33	0.839 14	0.754 20	1.000 1	0.573 22

DKNet	0.718 22	1.000 1	0.814 24	0.782 23	0.619 25	0.872 16	0.224 29	0.751 17	0.569 28	0.677 13	0.585 28	0.724 8	0.633 33	0.981 35	0.515 43	0.819 22	0.736 22	1.000 1	0.617 9
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
SSEC	0.707 23	1.000 1	0.850 16	0.924 3	0.648 19	0.747 45	0.162 33	0.862 3	0.572 27	0.520 27	0.624 21	0.549 26	0.649 31	1.000 1	0.560 38	0.706 45	0.768 16	1.000 1	0.591 20

HAIS	0.699 24	1.000 1	0.849 17	0.820 17	0.675 17	0.808 32	0.279 23	0.757 16	0.465 34	0.517 28	0.596 26	0.559 25	0.600 37	1.000 1	0.654 26	0.767 31	0.676 27	0.994 44	0.560 26
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNet	0.698 25	1.000 1	0.697 55	0.888 7	0.556 35	0.803 33	0.387 18	0.626 40	0.417 39	0.556 24	0.585 29	0.702 10	0.600 37	1.000 1	0.824 4	0.720 43	0.692 25	1.000 1	0.509 33
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
DualGroup	0.694 26	1.000 1	0.799 33	0.811 18	0.622 23	0.817 27	0.376 19	0.805 9	0.590 26	0.487 33	0.568 32	0.525 30	0.650 22	0.835 51	0.600 34	0.829 17	0.655 30	1.000 1	0.526 30

DANCENET	0.680 27	1.000 1	0.807 28	0.733 32	0.600 29	0.768 41	0.375 20	0.543 48	0.538 29	0.610 18	0.599 25	0.498 31	0.632 35	0.981 35	0.739 17	0.856 6	0.633 36	0.882 59	0.454 43

SphereSeg	0.680 27	1.000 1	0.856 15	0.744 31	0.618 26	0.893 10	0.151 34	0.651 35	0.713 11	0.537 26	0.579 31	0.430 40	0.651 21	1.000 1	0.389 54	0.744 38	0.697 24	0.991 46	0.601 17

Box2Mask	0.677 29	1.000 1	0.847 18	0.771 25	0.509 44	0.816 28	0.277 24	0.558 47	0.482 31	0.562 23	0.640 17	0.448 36	0.700 13	1.000 1	0.666 22	0.852 9	0.578 43	0.997 36	0.488 38
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
OccuSeg+instance	0.672 30	1.000 1	0.758 47	0.682 39	0.576 33	0.842 23	0.477 11	0.504 54	0.524 30	0.567 22	0.585 30	0.451 35	0.557 45	1.000 1	0.751 16	0.797 26	0.563 46	1.000 1	0.467 42
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group	0.664 31	1.000 1	0.822 22	0.764 28	0.616 27	0.815 29	0.139 38	0.694 26	0.597 25	0.459 37	0.566 33	0.599 24	0.600 37	0.516 61	0.715 19	0.819 23	0.635 34	1.000 1	0.603 15
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
INS-Conv-instance	0.657 32	1.000 1	0.760 45	0.667 41	0.581 31	0.863 18	0.323 21	0.655 34	0.477 32	0.473 35	0.549 35	0.432 39	0.650 22	1.000 1	0.655 25	0.738 39	0.585 42	0.944 51	0.472 41

CSC-Pretrained	0.648 33	1.000 1	0.810 25	0.768 26	0.523 42	0.813 30	0.143 37	0.819 5	0.389 42	0.422 46	0.511 39	0.443 37	0.650 22	1.000 1	0.624 31	0.732 40	0.634 35	1.000 1	0.375 50

PE	0.645 34	1.000 1	0.773 41	0.798 22	0.538 37	0.786 39	0.088 46	0.799 10	0.350 46	0.435 44	0.547 36	0.545 27	0.646 32	0.933 40	0.562 37	0.761 34	0.556 51	0.997 36	0.501 36
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN	0.643 35	1.000 1	0.758 46	0.582 52	0.539 36	0.826 26	0.046 51	0.765 12	0.372 44	0.436 43	0.588 27	0.539 29	0.650 22	1.000 1	0.577 35	0.750 36	0.653 32	0.997 36	0.495 37
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
Dyco3D	0.641 36	1.000 1	0.841 19	0.893 6	0.531 39	0.802 34	0.115 43	0.588 45	0.448 36	0.438 41	0.537 38	0.430 41	0.550 46	0.857 43	0.534 41	0.764 33	0.657 29	0.987 47	0.568 23
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN	0.638 37	1.000 1	0.895 13	0.800 21	0.480 48	0.676 50	0.144 36	0.737 18	0.354 45	0.447 38	0.400 52	0.365 47	0.700 13	1.000 1	0.569 36	0.836 15	0.599 38	1.000 1	0.473 40

PointGroup	0.636 38	1.000 1	0.765 42	0.624 43	0.505 46	0.797 35	0.116 42	0.696 25	0.384 43	0.441 39	0.559 34	0.476 33	0.596 40	1.000 1	0.666 22	0.756 35	0.556 50	0.997 36	0.513 32
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
DD-UNet+Group	0.635 39	0.667 54	0.797 35	0.714 36	0.562 34	0.774 40	0.146 35	0.810 8	0.429 38	0.476 34	0.546 37	0.399 43	0.633 33	1.000 1	0.632 30	0.722 42	0.609 37	1.000 1	0.514 31
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
Mask3D_evaluation	0.631 40	1.000 1	0.829 21	0.606 45	0.646 20	0.836 24	0.068 47	0.511 52	0.462 35	0.507 30	0.619 23	0.389 45	0.610 36	1.000 1	0.432 49	0.828 19	0.673 28	0.788 63	0.552 27

DENet	0.629 41	1.000 1	0.797 34	0.608 44	0.589 30	0.627 54	0.219 30	0.882 1	0.310 48	0.402 51	0.383 54	0.396 44	0.650 22	1.000 1	0.663 24	0.543 62	0.691 26	1.000 1	0.568 24

3D-MPA	0.611 42	1.000 1	0.833 20	0.765 27	0.526 41	0.756 43	0.136 40	0.588 45	0.470 33	0.438 42	0.432 48	0.358 49	0.650 22	0.857 43	0.429 50	0.765 32	0.557 49	1.000 1	0.430 45
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
OSIS	0.605 43	1.000 1	0.801 32	0.599 47	0.535 38	0.728 47	0.286 22	0.436 58	0.679 15	0.491 31	0.433 46	0.256 51	0.404 58	0.857 43	0.620 32	0.724 41	0.510 56	1.000 1	0.539 29

AOIA	0.601 44	1.000 1	0.761 44	0.687 38	0.485 47	0.828 25	0.008 58	0.663 32	0.405 41	0.405 50	0.425 49	0.490 32	0.596 40	0.714 54	0.553 40	0.779 27	0.597 39	0.992 45	0.424 47

PCJC	0.578 45	1.000 1	0.810 26	0.583 51	0.449 51	0.813 31	0.042 52	0.603 43	0.341 47	0.490 32	0.465 43	0.410 42	0.650 22	0.835 51	0.264 60	0.694 49	0.561 47	0.889 56	0.504 35

SSEN	0.575 46	1.000 1	0.761 43	0.473 54	0.477 49	0.795 36	0.066 48	0.529 50	0.658 19	0.460 36	0.461 44	0.380 46	0.331 60	0.859 42	0.401 53	0.692 51	0.653 31	1.000 1	0.348 52
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RWSeg	0.567 47	0.528 64	0.708 54	0.626 42	0.580 32	0.745 46	0.063 49	0.627 39	0.240 52	0.400 52	0.497 40	0.464 34	0.515 47	1.000 1	0.475 45	0.745 37	0.571 44	1.000 1	0.429 46

NeuralBF	0.555 48	0.667 54	0.896 12	0.843 13	0.517 43	0.751 44	0.029 53	0.519 51	0.414 40	0.439 40	0.465 42	0.000 70	0.484 49	0.857 43	0.287 58	0.693 50	0.651 33	1.000 1	0.485 39
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
MTML	0.549 49	1.000 1	0.807 29	0.588 50	0.327 56	0.647 52	0.004 60	0.815 7	0.180 55	0.418 47	0.364 56	0.182 54	0.445 52	1.000 1	0.442 48	0.688 52	0.571 45	1.000 1	0.396 48
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
ClickSeg_Instance	0.539 50	1.000 1	0.621 59	0.300 57	0.530 40	0.698 48	0.127 41	0.533 49	0.222 53	0.430 45	0.400 51	0.365 47	0.574 44	0.938 39	0.472 46	0.659 54	0.543 52	0.944 51	0.347 53

One_Thing_One_Click	0.529 51	0.667 54	0.718 50	0.777 24	0.399 52	0.683 49	0.000 63	0.669 30	0.138 58	0.391 53	0.374 55	0.539 28	0.360 59	0.641 58	0.556 39	0.774 30	0.593 40	0.997 36	0.251 58
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Sparse R-CNN	0.515 52	1.000 1	0.538 64	0.282 58	0.468 50	0.790 37	0.173 32	0.345 60	0.429 37	0.413 49	0.484 41	0.176 55	0.595 42	0.591 59	0.522 42	0.668 53	0.476 57	0.986 49	0.327 54

Occipital-SCS	0.512 53	1.000 1	0.716 51	0.509 53	0.506 45	0.611 55	0.092 45	0.602 44	0.177 56	0.346 56	0.383 53	0.165 56	0.442 53	0.850 50	0.386 55	0.618 58	0.543 53	0.889 56	0.389 49

3D-BoNet	0.488 54	1.000 1	0.672 58	0.590 49	0.301 58	0.484 65	0.098 44	0.620 41	0.306 49	0.341 57	0.259 60	0.125 58	0.434 55	0.796 53	0.402 52	0.499 64	0.513 55	0.909 55	0.439 44
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
PanopticFusion-inst	0.478 55	0.667 54	0.712 53	0.595 48	0.259 61	0.550 61	0.000 63	0.613 42	0.175 57	0.250 62	0.434 45	0.437 38	0.411 57	0.857 43	0.485 44	0.591 61	0.267 67	0.944 51	0.359 51
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
SPG_WSIS	0.470 56	0.667 54	0.685 57	0.677 40	0.372 54	0.562 59	0.000 63	0.482 55	0.244 51	0.316 59	0.298 57	0.052 65	0.442 54	0.857 43	0.267 59	0.702 46	0.559 48	1.000 1	0.287 56

SALoss-ResNet	0.459 57	1.000 1	0.737 49	0.159 68	0.259 60	0.587 57	0.138 39	0.475 56	0.217 54	0.416 48	0.408 50	0.128 57	0.315 61	0.714 54	0.411 51	0.536 63	0.590 41	0.873 60	0.304 55
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
MASC	0.447 58	0.528 64	0.555 62	0.381 55	0.382 53	0.633 53	0.002 61	0.509 53	0.260 50	0.361 55	0.432 47	0.327 50	0.451 51	0.571 60	0.367 56	0.639 56	0.386 58	0.980 50	0.276 57
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_ins	0.445 59	0.667 54	0.773 40	0.185 65	0.317 57	0.656 51	0.000 63	0.407 59	0.134 59	0.381 54	0.267 59	0.217 53	0.476 50	0.714 54	0.452 47	0.629 57	0.514 54	1.000 1	0.222 61
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
3D-SIS	0.382 60	1.000 1	0.432 67	0.245 60	0.190 62	0.577 58	0.013 57	0.263 62	0.033 65	0.320 58	0.240 61	0.075 61	0.422 56	0.857 43	0.117 65	0.699 47	0.271 66	0.883 58	0.235 60
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3D	0.323 61	0.667 54	0.542 63	0.264 59	0.157 65	0.550 60	0.000 63	0.205 65	0.009 67	0.270 61	0.218 62	0.075 61	0.500 48	0.688 57	0.007 71	0.698 48	0.301 63	0.459 68	0.200 62
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone	0.319 62	0.667 54	0.715 52	0.233 61	0.189 63	0.479 66	0.008 58	0.218 63	0.067 64	0.201 64	0.173 63	0.107 59	0.123 66	0.438 62	0.150 62	0.615 59	0.355 59	0.916 54	0.093 70

R-PointNet	0.306 63	0.500 66	0.405 68	0.311 56	0.348 55	0.589 56	0.054 50	0.068 68	0.126 60	0.283 60	0.290 58	0.028 66	0.219 64	0.214 65	0.331 57	0.396 68	0.275 64	0.821 62	0.245 59

Region-18class	0.284 64	0.250 70	0.751 48	0.228 63	0.270 59	0.521 62	0.000 63	0.468 57	0.008 69	0.205 63	0.127 64	0.000 70	0.068 68	0.070 69	0.262 61	0.652 55	0.323 61	0.740 64	0.173 63

SemRegionNet-20cls	0.250 65	0.333 67	0.613 60	0.229 62	0.163 64	0.493 63	0.000 63	0.304 61	0.107 61	0.147 67	0.100 66	0.052 64	0.231 62	0.119 67	0.039 67	0.445 66	0.325 60	0.654 65	0.141 66

3D-BEVIS	0.248 66	0.667 54	0.566 61	0.076 69	0.035 71	0.394 69	0.027 55	0.035 70	0.098 62	0.099 69	0.030 70	0.025 67	0.098 67	0.375 64	0.126 64	0.604 60	0.181 69	0.854 61	0.171 64
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
tmp	0.248 66	0.667 54	0.437 66	0.188 64	0.153 66	0.491 64	0.000 63	0.208 64	0.094 63	0.153 66	0.099 67	0.057 63	0.217 65	0.119 67	0.039 67	0.466 65	0.302 62	0.640 66	0.140 67

Sem_Recon_ins	0.227 68	0.764 53	0.486 65	0.069 70	0.098 68	0.426 68	0.017 56	0.067 69	0.015 66	0.172 65	0.100 65	0.096 60	0.054 70	0.183 66	0.135 63	0.366 69	0.260 68	0.614 67	0.168 65

ASIS	0.199 69	0.333 67	0.253 70	0.167 67	0.140 67	0.438 67	0.000 63	0.177 66	0.008 68	0.121 68	0.069 68	0.004 69	0.231 63	0.429 63	0.036 69	0.445 67	0.273 65	0.333 70	0.119 69

Sgpn_scannet	0.143 70	0.208 71	0.390 69	0.169 66	0.065 69	0.275 70	0.029 54	0.069 67	0.000 70	0.087 70	0.043 69	0.014 68	0.027 71	0.000 70	0.112 66	0.351 70	0.168 70	0.438 69	0.138 68

MaskRCNN 2d->3d Proj	0.058 71	0.333 67	0.002 71	0.000 71	0.053 70	0.002 71	0.002 62	0.021 71	0.000 70	0.045 71	0.024 71	0.238 52	0.065 69	0.000 70	0.014 70	0.107 71	0.020 71	0.110 71	0.006 71

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