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 4	0.551 6	0.247 8	0.181 3	0.784 8	0.661 9	0.939 8	0.564 3	0.624 8	0.721 7	0.484 3	0.429 2	0.575 2	0.027 6	0.774 7	0.503 9	0.753 3	0.242 8	0.656 8	0.945 5	0.534 5	0.865 5	0.860 6	0.177 12	0.616 5	0.400 2	0.818 2	0.579 1	0.615 6	0.367 9	0.408 5	0.726 10	0.633 2	0.162 1	0.360 4	0.619 2	0.000 1	0.828 4	0.873 7	0.924 2	0.109 8	0.083 3	0.564 3	0.057 12	0.475 8	0.266 6	0.781 1	0.767 6	0.257 5	0.100 8	0.825 6	0.663 7	0.048 11	0.620 9	0.551 7	0.595 10	0.532 5	0.692 6	0.246 4	0.000 3	0.213 4	0.615 1	0.861 5	0.376 5	0.900 3	0.000 3	0.102 11	0.660 5	0.321 10	0.547 4	0.226 8	0.000 1	0.311 8	0.742 2	0.011 3	0.006 5	0.000 1	0.000 3	0.546 10	0.824 7	0.345 9	0.665 1	0.450 4	0.435 1	0.683 3	0.411 5	0.338 1	0.000 5	0.000 1	0.030 6	0.000 3	0.068 6	0.892 5	0.000 1	0.063 3	0.000 8	0.257 8	0.304 10	0.387 3	0.079 9	0.228 3	0.190 7	0.000 11	0.586 1	0.347 2	0.133 5	0.000 3	0.037 8	0.377 8	0.000 1	0.384 4	0.006 11	0.003 8	0.421 2	0.410 8	0.643 4	0.171 4	0.121 4	0.142 9	0.000 1	0.510 8	0.447 7	0.474 9	0.000 1	0.000 7	0.286 3	0.083 8	0.000 5	0.000 7	0.603 1	0.096 4	0.063 3	0.000 8	0.000 1	0.000 1	0.898 3	0.000 1	0.429 4	0.000 1	0.400 1	0.550 3	0.000 1	0.633 4	0.000 1	0.000 1	0.377 3	0.000 10	0.916 3	0.000 5	0.000 6	0.000 1	0.000 5	0.000 1	0.102 9	0.499 7	0.296 9	0.463 3	0.089 5	0.304 1	0.740 2	0.401 11	0.010 3	0.000 1	0.560 2	0.000 2	0.000 2	0.709 1	0.652 7	0.000 2	0.000 1	0.000 1	0.143 7	0.000 4	0.000 2	0.609 2	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 7	0.556 3	0.270 4	0.123 9	0.816 4	0.682 5	0.946 4	0.549 5	0.657 6	0.756 3	0.459 4	0.376 6	0.550 6	0.001 9	0.807 3	0.616 2	0.727 7	0.267 4	0.691 3	0.942 7	0.530 7	0.872 4	0.874 5	0.330 5	0.542 9	0.374 5	0.792 3	0.400 9	0.673 2	0.572 4	0.433 2	0.793 4	0.623 4	0.008 12	0.351 5	0.594 6	0.000 1	0.783 8	0.876 5	0.833 4	0.213 3	0.000 7	0.537 5	0.091 4	0.519 2	0.304 4	0.620 5	0.942 1	0.264 3	0.124 5	0.855 4	0.695 3	0.086 6	0.646 6	0.506 11	0.658 4	0.535 4	0.715 2	0.314 1	0.000 3	0.241 3	0.608 2	0.897 2	0.359 6	0.858 6	0.000 3	0.076 12	0.611 8	0.392 7	0.509 6	0.378 3	0.000 1	0.579 2	0.565 11	0.000 4	0.000 6	0.000 1	0.000 3	0.755 4	0.806 8	0.661 2	0.572 10	0.350 7	0.181 7	0.660 7	0.300 9	0.000 3	0.000 5	0.000 1	0.023 7	0.000 3	0.042 11	0.930 2	0.000 1	0.000 7	0.077 5	0.584 4	0.392 7	0.339 6	0.185 5	0.171 7	0.308 2	0.006 10	0.563 3	0.256 6	0.150 2	0.000 3	0.002 11	0.345 10	0.000 1	0.045 9	0.197 2	0.063 6	0.323 8	0.453 3	0.600 6	0.163 6	0.037 10	0.349 2	0.000 1	0.672 2	0.679 3	0.753 1	0.000 1	0.000 7	0.000 7	0.117 3	0.000 5	0.000 7	0.291 8	0.000 7	0.000 4	0.039 4	0.000 1	0.000 1	0.899 2	0.000 1	0.374 8	0.000 1	0.000 8	0.545 4	0.000 1	0.634 3	0.000 1	0.000 1	0.074 8	0.223 3	0.914 5	0.000 5	0.021 4	0.000 1	0.000 5	0.000 1	0.112 4	0.498 8	0.649 1	0.383 7	0.095 2	0.135 11	0.449 8	0.432 7	0.008 5	0.000 1	0.518 5	0.000 2	0.000 2	0.000 7	0.796 3	0.000 2	0.000 1	0.000 1	0.138 9	0.000 4	0.000 2	0.000 6	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
PonderV2 ScanNet200	0.346 3	0.552 5	0.270 5	0.175 4	0.810 5	0.682 5	0.950 3	0.560 4	0.641 7	0.761 1	0.398 8	0.357 7	0.570 5	0.113 2	0.804 4	0.603 4	0.750 4	0.283 2	0.681 4	0.952 3	0.548 3	0.874 3	0.852 8	0.290 7	0.700 2	0.356 8	0.792 3	0.445 7	0.545 8	0.436 7	0.351 8	0.787 5	0.611 5	0.050 7	0.290 9	0.519 9	0.000 1	0.825 5	0.888 3	0.842 3	0.259 2	0.100 2	0.558 4	0.070 9	0.497 5	0.247 9	0.457 8	0.889 2	0.248 6	0.106 7	0.817 8	0.691 4	0.094 5	0.729 2	0.636 4	0.620 9	0.503 8	0.660 9	0.243 5	0.000 3	0.212 5	0.590 3	0.860 6	0.400 3	0.881 4	0.000 3	0.202 2	0.622 7	0.408 6	0.499 7	0.261 7	0.000 1	0.385 6	0.636 6	0.000 4	0.000 6	0.000 1	0.000 3	0.433 11	0.843 5	0.660 4	0.574 9	0.481 2	0.336 4	0.677 4	0.486 3	0.000 3	0.030 1	0.000 1	0.034 5	0.000 3	0.080 5	0.869 7	0.000 1	0.000 7	0.000 8	0.540 5	0.727 2	0.232 12	0.115 6	0.186 5	0.193 6	0.000 11	0.403 7	0.326 4	0.103 9	0.000 3	0.290 3	0.392 7	0.000 1	0.346 5	0.062 7	0.424 3	0.375 4	0.431 4	0.667 3	0.115 9	0.082 7	0.239 5	0.000 1	0.504 9	0.606 4	0.584 7	0.000 1	0.002 5	0.186 5	0.104 7	0.000 5	0.394 3	0.384 6	0.083 5	0.000 4	0.007 6	0.000 1	0.000 1	0.880 4	0.000 1	0.377 7	0.000 1	0.263 3	0.565 2	0.000 1	0.608 6	0.000 1	0.000 1	0.304 5	0.009 6	0.924 1	0.000 5	0.000 6	0.000 1	0.000 5	0.000 1	0.128 2	0.584 2	0.475 5	0.412 5	0.076 9	0.269 3	0.621 4	0.509 4	0.010 3	0.000 1	0.491 7	0.063 1	0.000 2	0.472 3	0.880 2	0.000 2	0.000 1	0.000 1	0.179 4	0.125 1	0.000 2	0.441 5	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 6	0.558 2	0.269 6	0.124 8	0.821 3	0.703 1	0.946 4	0.569 2	0.662 2	0.748 6	0.487 2	0.455 1	0.572 4	0.000 10	0.789 5	0.534 6	0.736 6	0.271 3	0.713 2	0.949 4	0.498 11	0.877 2	0.860 6	0.332 4	0.706 1	0.474 1	0.788 5	0.406 8	0.637 3	0.495 6	0.355 7	0.805 3	0.592 9	0.015 11	0.396 3	0.602 5	0.000 1	0.799 6	0.876 5	0.713 12	0.276 1	0.000 7	0.493 8	0.080 6	0.448 10	0.363 2	0.661 2	0.833 5	0.262 4	0.125 4	0.823 7	0.665 6	0.076 7	0.720 4	0.557 6	0.637 6	0.517 6	0.672 8	0.227 6	0.000 3	0.158 8	0.496 4	0.843 8	0.352 7	0.835 8	0.000 3	0.103 10	0.711 3	0.527 2	0.526 5	0.320 5	0.000 1	0.568 4	0.625 7	0.067 1	0.000 6	0.000 1	0.001 2	0.806 3	0.836 6	0.621 7	0.591 5	0.373 6	0.314 5	0.668 5	0.398 6	0.003 2	0.000 5	0.000 1	0.016 11	0.024 2	0.043 10	0.906 4	0.000 1	0.052 4	0.000 8	0.384 7	0.330 9	0.342 5	0.100 7	0.223 4	0.183 8	0.112 4	0.476 5	0.313 5	0.130 7	0.196 2	0.112 7	0.370 9	0.000 1	0.234 7	0.071 6	0.160 4	0.403 3	0.398 9	0.492 10	0.197 2	0.076 8	0.272 3	0.000 1	0.200 12	0.560 6	0.735 3	0.000 1	0.000 7	0.000 7	0.110 5	0.002 4	0.021 6	0.412 5	0.000 7	0.000 4	0.000 8	0.000 1	0.000 1	0.794 7	0.000 1	0.445 3	0.000 1	0.022 6	0.509 6	0.000 1	0.517 10	0.000 1	0.000 1	0.001 12	0.245 2	0.915 4	0.024 2	0.089 3	0.000 1	0.262 2	0.000 1	0.103 8	0.524 5	0.392 8	0.515 2	0.013 12	0.251 4	0.411 10	0.662 1	0.001 7	0.000 1	0.473 8	0.000 2	0.000 2	0.150 4	0.699 6	0.000 2	0.000 1	0.000 1	0.166 5	0.000 4	0.024 1	0.000 6	0.000 1

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

PTv3 ScanNet200	0.393 1	0.592 1	0.330 1	0.216 1	0.851 1	0.687 4	0.971 1	0.586 1	0.755 1	0.752 5	0.505 1	0.404 4	0.575 2	0.000 10	0.848 1	0.616 2	0.761 1	0.349 1	0.738 1	0.978 1	0.546 4	0.860 6	0.926 1	0.346 2	0.654 3	0.384 4	0.828 1	0.523 3	0.699 1	0.583 3	0.387 6	0.822 1	0.688 1	0.118 4	0.474 1	0.603 4	0.000 1	0.832 3	0.903 1	0.753 8	0.140 6	0.000 7	0.650 2	0.109 2	0.520 1	0.457 1	0.497 7	0.871 3	0.281 2	0.192 2	0.887 2	0.748 1	0.168 1	0.727 3	0.733 1	0.740 1	0.644 1	0.714 3	0.190 8	0.000 3	0.256 2	0.449 6	0.914 1	0.514 1	0.759 10	0.337 1	0.172 4	0.692 4	0.617 1	0.636 1	0.325 4	0.000 1	0.641 1	0.782 1	0.000 4	0.065 2	0.000 1	0.000 3	0.842 1	0.903 1	0.661 2	0.662 2	0.612 1	0.405 2	0.731 1	0.566 1	0.000 3	0.000 5	0.000 1	0.017 10	0.301 1	0.088 4	0.941 1	0.000 1	0.077 2	0.000 8	0.717 3	0.790 1	0.310 9	0.026 12	0.264 2	0.349 1	0.220 2	0.397 8	0.366 1	0.115 8	0.000 3	0.337 1	0.463 5	0.000 1	0.531 2	0.218 1	0.593 1	0.455 1	0.469 1	0.708 2	0.210 1	0.592 2	0.108 11	0.000 1	0.728 1	0.682 2	0.671 4	0.000 1	0.000 7	0.407 1	0.136 2	0.022 2	0.575 1	0.436 4	0.259 2	0.428 1	0.048 3	0.000 1	0.000 1	0.879 5	0.000 1	0.480 2	0.000 1	0.133 5	0.597 1	0.000 1	0.690 1	0.000 1	0.000 1	0.009 11	0.000 10	0.921 2	0.000 5	0.151 2	0.000 1	0.000 5	0.000 1	0.109 6	0.494 9	0.622 2	0.394 6	0.073 10	0.141 7	0.798 1	0.528 3	0.026 1	0.000 1	0.551 3	0.000 2	0.000 2	0.134 5	0.717 5	0.000 2	0.000 1	0.000 1	0.188 3	0.000 4	0.000 2	0.791 1	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 8	0.539 7	0.265 7	0.131 7	0.806 6	0.670 8	0.943 7	0.535 7	0.662 2	0.705 11	0.423 6	0.407 3	0.505 8	0.003 8	0.765 8	0.582 5	0.686 10	0.227 11	0.680 5	0.943 6	0.601 1	0.854 8	0.892 3	0.335 3	0.417 12	0.357 7	0.724 7	0.453 6	0.632 4	0.596 2	0.432 3	0.783 6	0.512 11	0.021 10	0.244 10	0.637 1	0.000 1	0.787 7	0.873 7	0.743 10	0.000 12	0.000 7	0.534 6	0.110 1	0.499 4	0.289 5	0.626 4	0.620 9	0.168 12	0.204 1	0.849 5	0.679 5	0.117 3	0.633 7	0.684 2	0.650 5	0.552 3	0.684 7	0.312 2	0.000 3	0.175 7	0.429 7	0.865 3	0.413 2	0.837 7	0.000 3	0.145 6	0.626 6	0.451 5	0.487 8	0.513 1	0.000 1	0.529 5	0.613 8	0.000 4	0.033 3	0.000 1	0.000 3	0.828 2	0.871 2	0.622 6	0.587 6	0.411 5	0.137 9	0.645 9	0.343 7	0.000 3	0.000 5	0.000 1	0.022 8	0.000 3	0.026 12	0.829 8	0.000 1	0.022 5	0.089 4	0.842 1	0.253 11	0.318 8	0.296 2	0.178 6	0.291 3	0.224 1	0.584 2	0.200 9	0.132 6	0.000 3	0.128 6	0.227 11	0.000 1	0.230 8	0.047 8	0.149 5	0.331 7	0.412 7	0.618 5	0.164 5	0.102 6	0.522 1	0.000 1	0.655 3	0.378 8	0.469 10	0.000 1	0.000 7	0.000 7	0.105 6	0.000 5	0.000 7	0.483 3	0.000 7	0.000 4	0.028 5	0.000 1	0.000 1	0.906 1	0.000 1	0.339 10	0.000 1	0.000 8	0.457 7	0.000 1	0.612 5	0.000 1	0.000 1	0.408 2	0.000 10	0.900 6	0.000 5	0.000 6	0.000 1	0.029 4	0.000 1	0.074 12	0.455 10	0.479 4	0.427 4	0.079 8	0.140 8	0.496 6	0.414 9	0.022 2	0.000 1	0.471 9	0.000 2	0.000 2	0.000 7	0.722 4	0.000 2	0.000 1	0.000 1	0.138 9	0.000 4	0.000 2	0.000 6	0.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
L3DETR-ScanNet_200	0.336 5	0.533 8	0.279 3	0.155 5	0.801 7	0.689 2	0.946 4	0.539 6	0.660 5	0.759 2	0.380 9	0.333 9	0.583 1	0.000 10	0.788 6	0.529 7	0.740 5	0.261 7	0.679 6	0.940 8	0.525 8	0.860 6	0.883 4	0.226 8	0.613 6	0.397 3	0.720 8	0.512 4	0.565 7	0.620 1	0.417 4	0.775 8	0.629 3	0.158 2	0.298 7	0.579 8	0.000 1	0.835 1	0.883 4	0.927 1	0.114 7	0.079 4	0.511 7	0.073 8	0.508 3	0.312 3	0.629 3	0.861 4	0.192 11	0.098 10	0.908 1	0.636 8	0.032 12	0.563 12	0.514 10	0.664 3	0.505 7	0.697 5	0.225 7	0.000 3	0.264 1	0.411 8	0.860 6	0.321 8	0.960 1	0.058 2	0.109 9	0.776 1	0.526 3	0.557 2	0.303 6	0.000 1	0.339 7	0.712 4	0.000 4	0.014 4	0.000 1	0.000 3	0.638 7	0.856 3	0.641 5	0.579 8	0.107 12	0.119 10	0.661 6	0.416 4	0.000 3	0.000 5	0.000 1	0.007 12	0.000 3	0.067 7	0.910 3	0.000 1	0.000 7	0.000 8	0.463 6	0.448 5	0.294 11	0.324 1	0.293 1	0.211 5	0.108 5	0.448 6	0.068 12	0.141 4	0.000 3	0.330 2	0.699 1	0.000 1	0.256 6	0.192 3	0.000 10	0.355 5	0.418 5	0.209 12	0.146 7	0.679 1	0.101 12	0.000 1	0.503 10	0.687 1	0.671 4	0.000 1	0.000 7	0.174 6	0.117 3	0.000 5	0.122 5	0.515 2	0.104 3	0.259 2	0.312 2	0.000 1	0.000 1	0.765 8	0.000 1	0.369 9	0.000 1	0.183 4	0.422 9	0.000 1	0.646 2	0.000 1	0.000 1	0.565 1	0.001 9	0.125 12	0.010 3	0.002 5	0.000 1	0.487 1	0.000 1	0.075 11	0.548 3	0.420 6	0.233 11	0.082 7	0.138 10	0.430 9	0.427 8	0.000 8	0.000 1	0.549 4	0.000 2	0.000 2	0.074 6	0.409 11	0.000 2	0.000 1	0.000 1	0.152 6	0.051 2	0.000 2	0.598 3	0.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
AWCS	0.305 9	0.508 9	0.225 9	0.142 6	0.782 9	0.634 12	0.937 9	0.489 10	0.578 9	0.721 7	0.364 10	0.355 8	0.515 7	0.023 7	0.764 9	0.523 8	0.707 9	0.264 6	0.633 9	0.922 9	0.507 10	0.886 1	0.804 10	0.179 10	0.436 11	0.300 9	0.656 11	0.529 2	0.501 10	0.394 8	0.296 11	0.820 2	0.603 6	0.131 3	0.179 12	0.619 2	0.000 1	0.707 11	0.865 9	0.773 6	0.171 4	0.010 6	0.484 9	0.063 10	0.463 9	0.254 8	0.332 11	0.649 8	0.220 8	0.100 8	0.729 10	0.613 10	0.071 9	0.582 10	0.628 5	0.702 2	0.424 10	0.749 1	0.137 10	0.000 3	0.142 9	0.360 9	0.863 4	0.305 9	0.877 5	0.000 3	0.173 3	0.606 9	0.337 9	0.478 9	0.154 10	0.000 1	0.253 9	0.664 5	0.000 4	0.000 6	0.000 1	0.000 3	0.626 8	0.782 9	0.302 11	0.602 4	0.185 10	0.282 6	0.651 8	0.317 8	0.000 3	0.000 5	0.000 1	0.022 8	0.000 3	0.154 1	0.876 6	0.000 1	0.014 6	0.063 7	0.029 12	0.553 4	0.467 2	0.084 8	0.124 9	0.157 11	0.049 9	0.373 9	0.252 7	0.097 10	0.000 3	0.219 4	0.542 2	0.000 1	0.392 3	0.172 5	0.000 10	0.339 6	0.417 6	0.533 9	0.093 10	0.115 5	0.195 7	0.000 1	0.516 7	0.288 11	0.741 2	0.000 1	0.001 6	0.233 4	0.056 9	0.000 5	0.159 4	0.334 7	0.077 6	0.000 4	0.000 8	0.000 1	0.000 1	0.749 9	0.000 1	0.411 5	0.000 1	0.008 7	0.452 8	0.000 1	0.595 7	0.000 1	0.000 1	0.220 7	0.006 7	0.894 8	0.006 4	0.000 6	0.000 1	0.000 5	0.000 1	0.112 4	0.504 6	0.404 7	0.551 1	0.093 4	0.129 12	0.484 7	0.381 12	0.000 8	0.000 1	0.396 10	0.000 2	0.000 2	0.620 2	0.402 12	0.000 2	0.000 1	0.000 1	0.142 8	0.000 4	0.000 2	0.512 4	0.000 1

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

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

Method	avg ap	head ap	common ap	tail ap	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	0.278 1	0.383 1	0.263 1	0.168 1	0.661 2	0.465 1	0.572 1	0.665 3	0.391 1	0.121 4	0.304 1	0.015 2	0.647 1	0.349 1	0.474 1	0.489 1	0.321 1	0.816 5	0.351 3	0.722 1	0.402 4	0.195 1	0.515 3	0.082 1	0.795 1	0.215 2	0.396 1	0.377 1	0.082 4	0.724 1	0.586 1	0.015 2	0.277 1	0.377 5	0.201 1	0.475 2	0.572 1	0.778 3	0.089 1	0.759 1	0.556 1	0.068 1	0.506 1	0.467 1	0.323 3	0.778 2	0.427 1	0.027 2	0.789 1	0.744 1	0.003 1	0.570 2	0.561 1	0.337 1	0.265 1	0.711 1	0.258 1	0.031 1	0.569 1	0.311 1	0.441 1	0.179 1	1.000 1	0.000 1	0.233 2	0.411 2	0.283 2	0.380 1	0.667 1	0.016 1	0.048 3	0.418 2	0.139 1	0.173 1	0.000 1	0.086 1	0.014 2	0.500 1	0.384 1	0.497 1	0.044 3	0.032 2	0.752 1	0.287 1	0.003 1	0.000 1	0.007 1	0.208 1	0.000 1	0.001 2	0.349 1	0.008 2	0.014 2	0.509 1	0.500 1	0.323 1	0.023 2	0.176 1	0.107 1	0.105 3	0.000 1	0.605 1	0.378 1	0.016 1	0.000 1	0.400 1	0.192 1	0.000 1	0.048 2	0.037 2	0.000 1	0.275 1	0.119 1	0.810 1	0.258 1	0.006 3	0.083 5	0.000 1	0.568 2	0.377 2	0.708 1	0.000 1	0.005 2	0.147 1	0.014 2	0.000 2	0.556 1	0.085 1	0.325 1	0.500 1	0.083 1	0.004 2	0.000 1	0.590 1	0.000 1	0.365 1	0.000 1	0.116 1	0.491 1	0.000 1	0.626 1	0.000 1	0.000 1	0.579 1	0.391 1	0.050 4	0.000 1	0.028 1	0.000 1	0.222 1	0.000 1	0.063 1	0.302 1	0.356 1	0.149 4	0.573 1	0.415 1	0.013 5	0.002 4	0.004 1	0.000 1	0.005 4	0.000 1	0.000 1	0.444 1	0.514 1	0.000 1	0.028 1	0.000 2	0.156 2	0.267 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	0.211 2	0.332 2	0.177 2	0.103 2	0.662 1	0.413 2	0.463 2	0.705 1	0.192 3	0.145 1	0.266 2	0.215 1	0.452 4	0.209 2	0.222 5	0.219 5	0.315 2	0.893 1	0.380 2	0.617 2	0.439 2	0.047 4	0.646 1	0.080 2	0.610 3	0.253 1	0.237 2	0.293 2	0.135 1	0.379 5	0.494 2	0.048 1	0.252 2	0.451 2	0.184 2	0.483 1	0.395 2	0.852 1	0.083 2	0.551 2	0.278 2	0.036 2	0.337 2	0.266 2	0.544 1	0.963 1	0.079 5	0.039 1	0.740 2	0.604 2	0.000 2	0.586 1	0.283 2	0.282 2	0.059 2	0.633 3	0.028 2	0.004 2	0.559 2	0.309 2	0.420 2	0.028 5	1.000 1	0.000 1	0.456 1	0.411 1	0.372 1	0.060 4	0.046 4	0.000 2	0.040 4	0.694 1	0.083 2	0.000 2	0.000 1	0.000 2	0.000 3	0.083 4	0.252 2	0.260 5	0.200 1	0.160 1	0.669 2	0.111 2	0.000 2	0.000 1	0.006 2	0.169 2	0.000 1	0.007 1	0.296 2	0.032 1	0.074 1	0.139 3	0.000 2	0.321 2	0.031 1	0.108 2	0.088 2	0.157 1	0.000 1	0.231 5	0.026 5	0.000 2	0.000 1	0.356 2	0.052 2	0.000 1	0.240 1	0.147 1	0.000 1	0.015 2	0.046 3	0.144 3	0.073 3	0.414 1	0.222 4	0.000 1	0.806 1	0.343 3	0.486 3	0.000 1	0.008 1	0.038 2	0.083 1	0.002 1	0.028 2	0.074 2	0.032 2	0.150 2	0.039 2	0.008 1	0.000 1	0.250 4	0.000 1	0.125 4	0.000 1	0.052 2	0.260 3	0.000 1	0.143 5	0.000 1	0.000 1	0.543 2	0.207 2	0.404 1	0.000 1	0.003 2	0.000 1	0.000 2	0.000 1	0.037 2	0.093 4	0.272 2	0.342 1	0.039 4	0.281 2	0.249 3	0.224 1	0.000 2	0.000 1	0.074 1	0.000 1	0.000 1	0.000 2	0.278 2	0.000 1	0.000 2	0.889 1	0.323 1	0.000 2	0.014 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.	0.154 3	0.275 3	0.108 3	0.060 3	0.573 3	0.381 3	0.434 3	0.654 4	0.190 4	0.141 2	0.097 3	0.000 3	0.503 3	0.180 3	0.252 3	0.242 4	0.242 3	0.881 3	0.448 1	0.494 3	0.429 3	0.078 2	0.364 5	0.024 3	0.654 2	0.213 4	0.222 3	0.239 3	0.099 3	0.616 2	0.363 3	0.000 3	0.092 3	0.444 3	0.000 3	0.383 4	0.209 5	0.815 2	0.030 3	0.000 3	0.166 3	0.002 4	0.295 5	0.099 4	0.364 2	0.778 2	0.177 3	0.001 4	0.427 5	0.585 4	0.000 2	0.470 3	0.268 5	0.205 3	0.045 3	0.642 2	0.007 3	0.000 3	0.333 5	0.148 3	0.407 3	0.130 2	1.000 1	0.000 1	0.156 4	0.189 3	0.097 4	0.169 2	0.000 5	0.000 2	0.056 2	0.400 3	0.000 3	0.000 2	0.000 1	0.000 2	0.556 1	0.278 3	0.203 3	0.323 4	0.019 4	0.000 3	0.402 4	0.026 3	0.000 2	0.000 1	0.000 3	0.044 3	0.000 1	0.000 3	0.037 4	0.000 3	0.000 3	0.181 2	0.000 2	0.127 3	0.006 4	0.028 4	0.023 3	0.115 2	0.000 1	0.327 2	0.267 2	0.000 2	0.000 1	0.000 4	0.028 3	0.000 1	0.000 3	0.000 3	0.000 1	0.003 3	0.048 2	0.135 4	0.222 2	0.089 2	0.278 1	0.000 1	0.514 3	0.333 4	0.611 2	0.000 1	0.000 3	0.000 3	0.000 3	0.000 2	0.000 3	0.037 3	0.000 3	0.000 3	0.000 3	0.000 3	0.000 1	0.322 2	0.000 1	0.209 2	0.000 1	0.000 3	0.278 2	0.000 1	0.302 3	0.000 1	0.000 1	0.143 3	0.148 3	0.000 5	0.000 1	0.000 3	0.000 1	0.000 2	0.000 1	0.015 3	0.064 5	0.000 3	0.272 2	0.031 5	0.000 4	0.257 2	0.028 2	0.000 2	0.000 1	0.041 2	0.000 1	0.000 1	0.000 2	0.222 5	0.000 1	0.000 2	0.000 2	0.000 5	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.	0.130 4	0.246 4	0.083 4	0.043 5	0.547 5	0.236 4	0.415 4	0.672 2	0.141 5	0.133 3	0.067 4	0.000 3	0.521 2	0.114 5	0.238 4	0.289 2	0.232 4	0.883 2	0.182 5	0.373 5	0.486 1	0.076 3	0.488 4	0.022 4	0.529 4	0.199 5	0.110 4	0.217 4	0.100 2	0.460 4	0.319 4	0.000 3	0.025 5	0.472 1	0.000 3	0.394 3	0.210 4	0.537 4	0.004 4	0.000 3	0.083 5	0.000 5	0.299 4	0.061 5	0.201 5	0.761 4	0.084 4	0.008 3	0.720 3	0.557 5	0.000 2	0.317 5	0.280 3	0.094 5	0.020 5	0.564 5	0.000 4	0.000 3	0.400 3	0.048 4	0.259 4	0.101 3	1.000 1	0.000 1	0.190 3	0.142 5	0.094 5	0.137 3	0.089 3	0.000 2	0.101 1	0.355 5	0.000 3	0.000 2	0.000 1	0.000 2	0.000 3	0.444 2	0.082 5	0.384 2	0.000 5	0.000 3	0.334 5	0.004 5	0.000 2	0.000 1	0.000 3	0.041 4	0.000 1	0.000 3	0.026 5	0.000 3	0.000 3	0.000 4	0.000 2	0.082 5	0.022 3	0.000 5	0.021 4	0.088 4	0.000 1	0.241 4	0.033 4	0.000 2	0.000 1	0.067 3	0.000 5	0.000 1	0.000 3	0.000 3	0.000 1	0.000 4	0.026 4	0.262 2	0.016 4	0.000 4	0.278 1	0.000 1	0.500 4	0.394 1	0.028 5	0.000 1	0.000 3	0.000 3	0.000 3	0.000 2	0.000 3	0.019 4	0.000 3	0.000 3	0.000 3	0.000 3	0.000 1	0.156 5	0.000 1	0.032 5	0.000 1	0.000 3	0.194 5	0.000 1	0.248 4	0.000 1	0.000 1	0.099 4	0.019 4	0.308 2	0.000 1	0.000 3	0.000 1	0.000 2	0.000 1	0.007 4	0.122 2	0.000 3	0.175 3	0.063 2	0.000 4	0.271 1	0.000 5	0.000 2	0.000 1	0.000 5	0.000 1	0.000 1	0.000 2	0.278 2	0.000 1	0.000 2	0.000 2	0.111 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.	0.123 5	0.223 5	0.082 5	0.046 4	0.564 4	0.152 5	0.394 5	0.578 5	0.235 2	0.116 5	0.034 5	0.000 3	0.348 5	0.119 4	0.297 2	0.285 3	0.202 5	0.838 4	0.323 4	0.407 4	0.184 5	0.037 5	0.516 2	0.013 5	0.424 5	0.214 3	0.093 5	0.105 5	0.078 5	0.542 3	0.250 5	0.000 3	0.064 4	0.444 3	0.000 3	0.224 5	0.231 3	0.537 4	0.001 5	0.000 3	0.126 4	0.004 3	0.308 3	0.193 3	0.244 4	0.343 5	0.228 2	0.000 5	0.441 4	0.588 3	0.000 2	0.338 4	0.275 4	0.189 4	0.030 4	0.600 4	0.000 4	0.000 3	0.378 4	0.000 5	0.108 5	0.098 4	1.000 1	0.000 1	0.096 5	0.172 4	0.144 3	0.011 5	0.125 2	0.000 2	0.000 5	0.376 4	0.000 3	0.000 2	0.000 1	0.000 2	0.000 3	0.042 5	0.141 4	0.377 3	0.051 2	0.000 3	0.483 3	0.017 4	0.000 2	0.000 1	0.000 3	0.022 5	0.000 1	0.000 3	0.065 3	0.000 3	0.000 3	0.000 4	0.000 2	0.094 4	0.000 5	0.042 3	0.000 5	0.064 5	0.000 1	0.259 3	0.089 3	0.000 2	0.000 1	0.000 4	0.022 4	0.000 1	0.000 3	0.000 3	0.000 1	0.000 4	0.018 5	0.111 5	0.000 5	0.000 4	0.278 1	0.000 1	0.444 5	0.333 4	0.333 4	0.000 1	0.000 3	0.000 3	0.000 3	0.000 2	0.000 3	0.000 5	0.000 3	0.000 3	0.000 3	0.000 3	0.000 1	0.267 3	0.000 1	0.184 3	0.000 1	0.000 3	0.211 4	0.000 1	0.378 2	0.000 1	0.000 1	0.063 5	0.000 5	0.275 3	0.000 1	0.000 3	0.000 1	0.000 2	0.000 1	0.007 5	0.105 3	0.000 3	0.032 5	0.045 3	0.198 3	0.171 4	0.028 2	0.000 2	0.000 1	0.006 3	0.000 1	0.000 1	0.000 2	0.278 2	0.000 1	0.000 2	0.000 2	0.044 4	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 ScanNet	0.794 1	0.941 3	0.813 19	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 31	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 27	0.833 23	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 12	0.832 41	0.821 4	0.792 30	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 33	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 24
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 20	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 22	0.958 1	0.702 45	0.805 14	0.708 7	0.916 32	0.898 3	0.801 2

TTT-KD	0.773 5	0.646 91	0.818 14	0.809 35	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 12	0.961 16	0.537 31	0.348 11	0.769 12	0.903 10	0.785 10	0.815 6	0.676 22	0.939 14	0.880 11	0.772 8

OctFormer	0.766 7	0.925 7	0.808 23	0.849 9	0.786 5	0.846 26	0.566 9	0.876 15	0.690 10	0.674 14	0.960 17	0.576 17	0.226 67	0.753 24	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
PPT-SpUNet-Joint	0.766 7	0.932 5	0.794 33	0.829 25	0.751 22	0.854 14	0.540 20	0.903 7	0.630 34	0.672 15	0.963 14	0.565 21	0.357 8	0.788 3	0.900 12	0.737 25	0.802 15	0.685 17	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
OccuSeg+Semantic	0.764 9	0.758 58	0.796 31	0.839 18	0.746 25	0.907 1	0.562 11	0.850 25	0.680 16	0.672 15	0.978 4	0.610 3	0.335 17	0.777 6	0.819 45	0.847 1	0.830 1	0.691 14	0.972 2	0.885 8	0.727 22

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 26	0.709 3	0.643 24	0.958 21	0.587 12	0.295 33	0.753 24	0.884 20	0.758 19	0.815 6	0.725 3	0.927 24	0.867 22	0.743 15

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 28	0.711 2	0.640 28	0.958 21	0.592 9	0.217 73	0.762 17	0.888 17	0.758 19	0.813 10	0.726 2	0.932 22	0.868 21	0.744 14
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 33	0.870 17	0.707 4	0.652 20	0.954 35	0.604 6	0.279 44	0.760 18	0.942 2	0.734 26	0.766 44	0.701 10	0.884 54	0.874 19	0.736 16

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 26	0.675 13	0.962 15	0.586 13	0.335 17	0.771 11	0.802 49	0.770 15	0.787 33	0.691 14	0.936 17	0.880 11	0.761 10

PNE	0.755 14	0.786 42	0.835 4	0.834 22	0.758 15	0.849 21	0.570 8	0.836 32	0.648 27	0.668 17	0.978 4	0.581 16	0.367 6	0.683 35	0.856 29	0.804 6	0.801 19	0.678 19	0.961 5	0.889 5	0.716 29
P. Hermosilla: Point Neighborhood Embeddings.
ConDaFormer	0.755 14	0.927 6	0.822 8	0.836 20	0.801 1	0.849 21	0.516 30	0.864 22	0.651 25	0.680 11	0.958 21	0.584 15	0.282 41	0.759 20	0.855 31	0.728 28	0.802 15	0.678 19	0.880 59	0.873 20	0.756 12
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
DMF-Net	0.752 16	0.906 12	0.793 35	0.802 41	0.689 40	0.825 46	0.556 12	0.867 18	0.681 15	0.602 44	0.960 17	0.555 27	0.365 7	0.779 5	0.859 26	0.747 22	0.795 27	0.717 6	0.917 31	0.856 30	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 22	0.872 1	0.758 15	0.860 11	0.552 13	0.891 13	0.610 41	0.687 6	0.960 17	0.559 25	0.304 29	0.766 15	0.926 4	0.767 16	0.797 23	0.644 33	0.942 11	0.876 16	0.722 26
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 36	0.807 37	0.750 24	0.856 13	0.524 26	0.881 14	0.588 53	0.642 27	0.977 8	0.591 10	0.274 47	0.781 4	0.929 3	0.804 6	0.796 24	0.642 34	0.947 9	0.885 8	0.715 30
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 33	0.752 20	0.839 32	0.485 47	0.842 29	0.673 18	0.644 23	0.957 25	0.528 37	0.305 28	0.773 9	0.859 26	0.788 8	0.818 5	0.693 13	0.916 32	0.856 30	0.723 25
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 94	0.804 25	0.859 3	0.745 26	0.824 48	0.501 37	0.912 4	0.690 10	0.685 8	0.956 26	0.567 20	0.320 23	0.768 14	0.918 5	0.720 33	0.802 15	0.676 22	0.921 29	0.881 10	0.779 6

StratifiedFormer	0.747 21	0.901 13	0.803 26	0.845 14	0.757 17	0.846 26	0.512 32	0.825 36	0.696 8	0.645 22	0.956 26	0.576 17	0.262 58	0.744 29	0.861 25	0.742 23	0.770 42	0.705 8	0.899 44	0.860 27	0.734 17
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 31	0.850 20	0.501 37	0.874 16	0.587 54	0.658 19	0.956 26	0.564 22	0.299 31	0.765 16	0.900 12	0.716 36	0.812 11	0.631 39	0.939 14	0.858 28	0.709 31
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 37	0.865 9	0.397 85	0.899 9	0.699 6	0.664 18	0.948 55	0.588 11	0.330 19	0.746 28	0.851 35	0.764 17	0.796 24	0.704 9	0.935 18	0.866 23	0.728 20
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 24	0.725 75	0.814 18	0.837 19	0.751 22	0.831 40	0.514 31	0.896 11	0.674 17	0.684 9	0.960 17	0.564 22	0.303 30	0.773 9	0.820 44	0.713 39	0.798 22	0.690 16	0.923 27	0.875 17	0.757 11

Retro-FPN	0.744 25	0.842 27	0.800 27	0.767 55	0.740 27	0.836 35	0.541 18	0.914 3	0.672 19	0.626 32	0.958 21	0.552 28	0.272 49	0.777 6	0.886 19	0.696 46	0.801 19	0.674 25	0.941 12	0.858 28	0.717 27
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 26	0.620 95	0.799 30	0.849 9	0.730 30	0.822 50	0.493 44	0.897 10	0.664 20	0.681 10	0.955 29	0.562 24	0.378 3	0.760 18	0.903 10	0.738 24	0.801 19	0.673 26	0.907 36	0.877 13	0.745 13
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet	0.742 27	0.816 35	0.806 24	0.807 37	0.752 20	0.828 44	0.575 6	0.839 31	0.699 6	0.637 29	0.954 35	0.520 40	0.320 23	0.755 23	0.834 39	0.760 18	0.772 39	0.676 22	0.915 34	0.862 25	0.717 27

SAT	0.742 27	0.860 21	0.765 49	0.819 28	0.769 12	0.848 23	0.533 22	0.829 34	0.663 21	0.631 31	0.955 29	0.586 13	0.274 47	0.753 24	0.896 14	0.729 27	0.760 50	0.666 28	0.921 29	0.855 32	0.733 18

LargeKernel3D	0.739 29	0.909 10	0.820 10	0.806 39	0.740 27	0.852 18	0.545 16	0.826 35	0.594 52	0.643 24	0.955 29	0.541 30	0.263 57	0.723 33	0.858 28	0.775 14	0.767 43	0.678 19	0.933 20	0.848 37	0.694 36
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN	0.736 30	0.776 48	0.790 36	0.851 7	0.754 19	0.854 14	0.491 46	0.866 20	0.596 51	0.686 7	0.955 29	0.536 32	0.342 13	0.624 50	0.869 22	0.787 9	0.802 15	0.628 40	0.927 24	0.875 17	0.704 33

MinkowskiNet	0.736 30	0.859 22	0.818 14	0.832 24	0.709 35	0.840 30	0.521 28	0.853 24	0.660 23	0.643 24	0.951 45	0.544 29	0.286 39	0.731 31	0.893 15	0.675 55	0.772 39	0.683 18	0.874 66	0.852 35	0.727 22
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA	0.731 32	0.890 14	0.837 3	0.864 2	0.726 32	0.873 5	0.530 25	0.824 37	0.489 87	0.647 21	0.978 4	0.609 4	0.336 15	0.624 50	0.733 58	0.758 19	0.776 37	0.570 65	0.949 8	0.877 13	0.728 20

PointTransformer++	0.725 33	0.727 74	0.811 21	0.819 28	0.765 13	0.841 29	0.502 36	0.814 42	0.621 37	0.623 34	0.955 29	0.556 26	0.284 40	0.620 52	0.866 23	0.781 11	0.757 54	0.648 31	0.932 22	0.862 25	0.709 31

SparseConvNet	0.725 33	0.647 90	0.821 9	0.846 13	0.721 33	0.869 6	0.533 22	0.754 58	0.603 47	0.614 36	0.955 29	0.572 19	0.325 21	0.710 34	0.870 21	0.724 31	0.823 2	0.628 40	0.934 19	0.865 24	0.683 39

MatchingNet	0.724 35	0.812 37	0.812 20	0.810 34	0.735 29	0.834 37	0.495 43	0.860 23	0.572 61	0.602 44	0.954 35	0.512 42	0.280 43	0.757 21	0.845 37	0.725 30	0.780 35	0.606 50	0.937 16	0.851 36	0.700 35

INS-Conv-semantic	0.717 36	0.751 61	0.759 52	0.812 32	0.704 36	0.868 7	0.537 21	0.842 29	0.609 43	0.608 40	0.953 39	0.534 34	0.293 34	0.616 53	0.864 24	0.719 35	0.793 28	0.640 35	0.933 20	0.845 41	0.663 45

PointMetaBase	0.714 37	0.835 28	0.785 38	0.821 26	0.684 42	0.846 26	0.531 24	0.865 21	0.614 38	0.596 48	0.953 39	0.500 45	0.246 63	0.674 36	0.888 17	0.692 47	0.764 46	0.624 42	0.849 81	0.844 42	0.675 41

contrastBoundary	0.705 38	0.769 55	0.775 43	0.809 35	0.687 41	0.820 53	0.439 73	0.812 43	0.661 22	0.591 50	0.945 63	0.515 41	0.171 91	0.633 47	0.856 29	0.720 33	0.796 24	0.668 27	0.889 51	0.847 38	0.689 37
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic	0.703 39	0.774 50	0.800 27	0.793 46	0.760 14	0.847 25	0.471 51	0.802 46	0.463 94	0.634 30	0.968 12	0.491 48	0.271 51	0.726 32	0.910 7	0.706 41	0.815 6	0.551 77	0.878 60	0.833 43	0.570 77

RFCR	0.702 40	0.889 15	0.745 63	0.813 31	0.672 45	0.818 57	0.493 44	0.815 41	0.623 35	0.610 38	0.947 57	0.470 57	0.249 62	0.594 56	0.848 36	0.705 42	0.779 36	0.646 32	0.892 49	0.823 49	0.611 60
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 41	0.825 32	0.796 31	0.723 62	0.716 34	0.832 39	0.433 75	0.816 39	0.634 32	0.609 39	0.969 10	0.418 83	0.344 12	0.559 68	0.833 40	0.715 37	0.808 13	0.560 71	0.902 41	0.847 38	0.680 40

JSENet	0.699 42	0.881 17	0.762 50	0.821 26	0.667 46	0.800 69	0.522 27	0.792 49	0.613 39	0.607 41	0.935 83	0.492 47	0.205 78	0.576 61	0.853 33	0.691 49	0.758 52	0.652 30	0.872 69	0.828 46	0.649 49
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 43	0.743 65	0.794 33	0.655 85	0.684 42	0.822 50	0.497 42	0.719 68	0.622 36	0.617 35	0.977 8	0.447 70	0.339 14	0.750 27	0.664 74	0.703 44	0.790 31	0.596 55	0.946 10	0.855 32	0.647 50
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 44	0.732 70	0.772 44	0.786 47	0.677 44	0.866 8	0.517 29	0.848 26	0.509 80	0.626 32	0.952 43	0.536 32	0.225 69	0.545 74	0.704 65	0.689 52	0.810 12	0.564 70	0.903 40	0.854 34	0.729 19
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNet	0.690 45	0.884 16	0.754 56	0.795 44	0.647 53	0.818 57	0.422 77	0.802 46	0.612 40	0.604 42	0.945 63	0.462 60	0.189 86	0.563 67	0.853 33	0.726 29	0.765 45	0.632 38	0.904 38	0.821 52	0.606 64
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 46	0.704 80	0.741 67	0.754 59	0.656 48	0.829 42	0.501 37	0.741 63	0.609 43	0.548 58	0.950 49	0.522 39	0.371 4	0.633 47	0.756 53	0.715 37	0.771 41	0.623 43	0.861 77	0.814 55	0.658 46
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 47	0.866 19	0.748 60	0.819 28	0.645 55	0.794 72	0.450 63	0.802 46	0.587 54	0.604 42	0.945 63	0.464 59	0.201 81	0.554 70	0.840 38	0.723 32	0.732 64	0.602 53	0.907 36	0.822 51	0.603 67

KP-FCNN	0.684 48	0.847 25	0.758 54	0.784 49	0.647 53	0.814 60	0.473 50	0.772 52	0.605 45	0.594 49	0.935 83	0.450 68	0.181 89	0.587 57	0.805 48	0.690 50	0.785 34	0.614 46	0.882 56	0.819 53	0.632 56
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 48	0.728 73	0.757 55	0.776 52	0.690 38	0.804 67	0.464 56	0.816 39	0.577 60	0.587 51	0.945 63	0.508 44	0.276 46	0.671 37	0.710 63	0.663 60	0.750 58	0.589 60	0.881 57	0.832 45	0.653 48

DGNet	0.684 48	0.712 79	0.784 39	0.782 51	0.658 47	0.835 36	0.499 41	0.823 38	0.641 29	0.597 47	0.950 49	0.487 50	0.281 42	0.575 62	0.619 78	0.647 68	0.764 46	0.620 45	0.871 72	0.846 40	0.688 38

PointContrast_LA_SEM	0.683 51	0.757 59	0.784 39	0.786 47	0.639 57	0.824 48	0.408 80	0.775 51	0.604 46	0.541 60	0.934 87	0.532 35	0.269 53	0.552 71	0.777 51	0.645 71	0.793 28	0.640 35	0.913 35	0.824 48	0.671 42

Superpoint Network	0.683 51	0.851 24	0.728 71	0.800 43	0.653 50	0.806 65	0.468 53	0.804 44	0.572 61	0.602 44	0.946 60	0.453 67	0.239 66	0.519 79	0.822 42	0.689 52	0.762 49	0.595 57	0.895 47	0.827 47	0.630 57

VI-PointConv	0.676 53	0.770 54	0.754 56	0.783 50	0.621 61	0.814 60	0.552 13	0.758 56	0.571 63	0.557 56	0.954 35	0.529 36	0.268 55	0.530 77	0.682 69	0.675 55	0.719 67	0.603 52	0.888 52	0.833 43	0.665 44
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 54	0.789 41	0.748 60	0.763 57	0.635 59	0.814 60	0.407 82	0.747 60	0.581 58	0.573 53	0.950 49	0.484 51	0.271 51	0.607 54	0.754 54	0.649 65	0.774 38	0.596 55	0.883 55	0.823 49	0.606 64

SALANet	0.670 55	0.816 35	0.770 47	0.768 54	0.652 51	0.807 64	0.451 60	0.747 60	0.659 24	0.545 59	0.924 93	0.473 56	0.149 101	0.571 64	0.811 47	0.635 74	0.746 59	0.623 43	0.892 49	0.794 68	0.570 77

O3DSeg	0.668 56	0.822 33	0.771 46	0.496 105	0.651 52	0.833 38	0.541 18	0.761 55	0.555 69	0.611 37	0.966 13	0.489 49	0.370 5	0.388 99	0.580 81	0.776 13	0.751 56	0.570 65	0.956 6	0.817 54	0.646 51

PointConv	0.666 57	0.781 45	0.759 52	0.699 70	0.644 56	0.822 50	0.475 49	0.779 50	0.564 66	0.504 76	0.953 39	0.428 77	0.203 80	0.586 59	0.754 54	0.661 61	0.753 55	0.588 61	0.902 41	0.813 57	0.642 52
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNL	0.666 57	0.703 81	0.781 41	0.751 61	0.655 49	0.830 41	0.471 51	0.769 53	0.474 90	0.537 62	0.951 45	0.475 55	0.279 44	0.635 45	0.698 68	0.675 55	0.751 56	0.553 76	0.816 88	0.806 59	0.703 34
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 59	0.746 63	0.708 74	0.722 63	0.638 58	0.820 53	0.451 60	0.566 96	0.599 49	0.541 60	0.950 49	0.510 43	0.313 25	0.648 42	0.819 45	0.616 79	0.682 82	0.590 59	0.869 73	0.810 58	0.656 47
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 60	0.558 102	0.751 58	0.655 85	0.690 38	0.722 94	0.453 59	0.867 18	0.579 59	0.576 52	0.893 105	0.523 38	0.293 34	0.733 30	0.571 83	0.692 47	0.659 89	0.606 50	0.875 63	0.804 61	0.668 43

DCM-Net	0.658 60	0.778 46	0.702 77	0.806 39	0.619 62	0.813 63	0.468 53	0.693 76	0.494 83	0.524 68	0.941 75	0.449 69	0.298 32	0.510 81	0.821 43	0.675 55	0.727 66	0.568 68	0.826 86	0.803 62	0.637 54
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN	0.656 62	0.698 83	0.743 65	0.650 87	0.564 79	0.820 53	0.505 35	0.758 56	0.631 33	0.479 80	0.945 63	0.480 53	0.226 67	0.572 63	0.774 52	0.690 50	0.735 62	0.614 46	0.853 80	0.776 83	0.597 70
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 63	0.752 60	0.734 69	0.664 83	0.583 74	0.815 59	0.399 84	0.754 58	0.639 30	0.535 64	0.942 73	0.470 57	0.309 27	0.665 38	0.539 85	0.650 64	0.708 72	0.635 37	0.857 79	0.793 70	0.642 52
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 64	0.778 46	0.731 70	0.699 70	0.577 75	0.829 42	0.446 65	0.736 64	0.477 89	0.523 70	0.945 63	0.454 64	0.269 53	0.484 89	0.749 57	0.618 77	0.738 60	0.599 54	0.827 85	0.792 73	0.621 59

PointConv-SFPN	0.641 65	0.776 48	0.703 76	0.721 64	0.557 82	0.826 45	0.451 60	0.672 81	0.563 67	0.483 79	0.943 72	0.425 80	0.162 96	0.644 43	0.726 59	0.659 62	0.709 71	0.572 64	0.875 63	0.786 78	0.559 83

MVPNet	0.641 65	0.831 29	0.715 72	0.671 80	0.590 70	0.781 78	0.394 86	0.679 78	0.642 28	0.553 57	0.937 80	0.462 60	0.256 59	0.649 41	0.406 99	0.626 75	0.691 79	0.666 28	0.877 61	0.792 73	0.608 63
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet	0.640 67	0.717 78	0.701 78	0.692 73	0.576 76	0.801 68	0.467 55	0.716 69	0.563 67	0.459 86	0.953 39	0.429 76	0.169 93	0.581 60	0.854 32	0.605 80	0.710 69	0.550 78	0.894 48	0.793 70	0.575 75

FPConv	0.639 68	0.785 43	0.760 51	0.713 68	0.603 65	0.798 70	0.392 87	0.534 101	0.603 47	0.524 68	0.948 55	0.457 62	0.250 61	0.538 75	0.723 61	0.598 84	0.696 77	0.614 46	0.872 69	0.799 63	0.567 80
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 69	0.797 39	0.769 48	0.641 93	0.590 70	0.820 53	0.461 57	0.537 100	0.637 31	0.536 63	0.947 57	0.388 90	0.206 77	0.656 39	0.668 72	0.647 68	0.732 64	0.585 62	0.868 74	0.793 70	0.473 103

PointSPNet	0.637 70	0.734 69	0.692 85	0.714 67	0.576 76	0.797 71	0.446 65	0.743 62	0.598 50	0.437 91	0.942 73	0.403 86	0.150 100	0.626 49	0.800 50	0.649 65	0.697 76	0.557 74	0.846 82	0.777 82	0.563 81

SConv	0.636 71	0.830 30	0.697 81	0.752 60	0.572 78	0.780 80	0.445 67	0.716 69	0.529 73	0.530 65	0.951 45	0.446 71	0.170 92	0.507 84	0.666 73	0.636 73	0.682 82	0.541 84	0.886 53	0.799 63	0.594 71

Supervoxel-CNN	0.635 72	0.656 88	0.711 73	0.719 65	0.613 63	0.757 89	0.444 70	0.765 54	0.534 72	0.566 54	0.928 91	0.478 54	0.272 49	0.636 44	0.531 87	0.664 59	0.645 93	0.508 91	0.864 76	0.792 73	0.611 60

joint point-based	0.634 73	0.614 96	0.778 42	0.667 82	0.633 60	0.825 46	0.420 78	0.804 44	0.467 92	0.561 55	0.951 45	0.494 46	0.291 36	0.566 65	0.458 94	0.579 90	0.764 46	0.559 73	0.838 83	0.814 55	0.598 69
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 74	0.731 71	0.688 88	0.675 77	0.591 69	0.784 77	0.444 70	0.565 97	0.610 41	0.492 77	0.949 53	0.456 63	0.254 60	0.587 57	0.706 64	0.599 83	0.665 88	0.612 49	0.868 74	0.791 76	0.579 74

3DSM_DMMF	0.631 75	0.626 93	0.745 63	0.801 42	0.607 64	0.751 90	0.506 34	0.729 67	0.565 65	0.491 78	0.866 108	0.434 72	0.197 84	0.595 55	0.630 77	0.709 40	0.705 74	0.560 71	0.875 63	0.740 93	0.491 98

PointNet2-SFPN	0.631 75	0.771 52	0.692 85	0.672 78	0.524 87	0.837 33	0.440 72	0.706 74	0.538 71	0.446 88	0.944 69	0.421 82	0.219 72	0.552 71	0.751 56	0.591 86	0.737 61	0.543 83	0.901 43	0.768 85	0.557 84

APCF-Net	0.631 75	0.742 66	0.687 90	0.672 78	0.557 82	0.792 75	0.408 80	0.665 82	0.545 70	0.508 73	0.952 43	0.428 77	0.186 87	0.634 46	0.702 66	0.620 76	0.706 73	0.555 75	0.873 67	0.798 65	0.581 73
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv	0.630 78	0.604 98	0.741 67	0.766 56	0.590 70	0.747 91	0.501 37	0.734 65	0.503 82	0.527 66	0.919 97	0.454 64	0.323 22	0.550 73	0.420 98	0.678 54	0.688 80	0.544 81	0.896 46	0.795 67	0.627 58
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 79	0.800 38	0.625 101	0.719 65	0.545 84	0.806 65	0.445 67	0.597 90	0.448 97	0.519 71	0.938 79	0.481 52	0.328 20	0.489 88	0.499 92	0.657 63	0.759 51	0.592 58	0.881 57	0.797 66	0.634 55

SegGroup_sem	0.627 80	0.818 34	0.747 62	0.701 69	0.602 66	0.764 86	0.385 91	0.629 87	0.490 85	0.508 73	0.931 90	0.409 85	0.201 81	0.564 66	0.725 60	0.618 77	0.692 78	0.539 85	0.873 67	0.794 68	0.548 87
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 81	0.830 30	0.694 83	0.757 58	0.563 80	0.772 84	0.448 64	0.647 85	0.520 76	0.509 72	0.949 53	0.431 75	0.191 85	0.496 86	0.614 79	0.647 68	0.672 86	0.535 87	0.876 62	0.783 79	0.571 76

dtc_net	0.625 81	0.703 81	0.751 58	0.794 45	0.535 85	0.848 23	0.480 48	0.676 80	0.528 74	0.469 83	0.944 69	0.454 64	0.004 114	0.464 91	0.636 76	0.704 43	0.758 52	0.548 80	0.924 26	0.787 77	0.492 97

HPEIN	0.618 83	0.729 72	0.668 91	0.647 89	0.597 68	0.766 85	0.414 79	0.680 77	0.520 76	0.525 67	0.946 60	0.432 73	0.215 74	0.493 87	0.599 80	0.638 72	0.617 98	0.570 65	0.897 45	0.806 59	0.605 66
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 84	0.858 23	0.772 44	0.489 106	0.532 86	0.792 75	0.404 83	0.643 86	0.570 64	0.507 75	0.935 83	0.414 84	0.046 111	0.510 81	0.702 66	0.602 82	0.705 74	0.549 79	0.859 78	0.773 84	0.534 90
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 85	0.760 57	0.667 92	0.649 88	0.521 88	0.793 73	0.457 58	0.648 84	0.528 74	0.434 93	0.947 57	0.401 87	0.153 99	0.454 92	0.721 62	0.648 67	0.717 68	0.536 86	0.904 38	0.765 86	0.485 99
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 86	0.634 92	0.743 65	0.697 72	0.601 67	0.781 78	0.437 74	0.585 93	0.493 84	0.446 88	0.933 88	0.394 88	0.011 113	0.654 40	0.661 75	0.603 81	0.733 63	0.526 88	0.832 84	0.761 88	0.480 100

LAP-D	0.594 87	0.720 76	0.692 85	0.637 94	0.456 98	0.773 83	0.391 89	0.730 66	0.587 54	0.445 90	0.940 77	0.381 91	0.288 37	0.434 95	0.453 96	0.591 86	0.649 91	0.581 63	0.777 92	0.749 92	0.610 62

DPC	0.592 88	0.720 76	0.700 79	0.602 98	0.480 94	0.762 88	0.380 92	0.713 72	0.585 57	0.437 91	0.940 77	0.369 93	0.288 37	0.434 95	0.509 91	0.590 88	0.639 96	0.567 69	0.772 94	0.755 90	0.592 72
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 89	0.766 56	0.659 96	0.683 75	0.470 97	0.740 93	0.387 90	0.620 89	0.490 85	0.476 81	0.922 95	0.355 96	0.245 64	0.511 80	0.511 90	0.571 91	0.643 94	0.493 95	0.872 69	0.762 87	0.600 68

ROSMRF	0.580 90	0.772 51	0.707 75	0.681 76	0.563 80	0.764 86	0.362 94	0.515 102	0.465 93	0.465 85	0.936 82	0.427 79	0.207 76	0.438 93	0.577 82	0.536 94	0.675 85	0.486 96	0.723 100	0.779 80	0.524 93

SD-DETR	0.576 91	0.746 63	0.609 105	0.445 110	0.517 89	0.643 105	0.366 93	0.714 71	0.456 95	0.468 84	0.870 107	0.432 73	0.264 56	0.558 69	0.674 70	0.586 89	0.688 80	0.482 97	0.739 98	0.733 95	0.537 89

SQN_0.1%	0.569 92	0.676 85	0.696 82	0.657 84	0.497 90	0.779 81	0.424 76	0.548 98	0.515 78	0.376 98	0.902 104	0.422 81	0.357 8	0.379 100	0.456 95	0.596 85	0.659 89	0.544 81	0.685 103	0.665 106	0.556 85

TextureNet	0.566 93	0.672 87	0.664 93	0.671 80	0.494 92	0.719 95	0.445 67	0.678 79	0.411 103	0.396 96	0.935 83	0.356 95	0.225 69	0.412 97	0.535 86	0.565 92	0.636 97	0.464 99	0.794 91	0.680 103	0.568 79
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 94	0.648 89	0.700 79	0.770 53	0.586 73	0.687 99	0.333 98	0.650 83	0.514 79	0.475 82	0.906 101	0.359 94	0.223 71	0.340 102	0.442 97	0.422 105	0.668 87	0.501 92	0.708 101	0.779 80	0.534 90

Pointnet++ & Feature	0.557 95	0.735 68	0.661 95	0.686 74	0.491 93	0.744 92	0.392 87	0.539 99	0.451 96	0.375 99	0.946 60	0.376 92	0.205 78	0.403 98	0.356 102	0.553 93	0.643 94	0.497 93	0.824 87	0.756 89	0.515 94

GMLPs	0.538 96	0.495 107	0.693 84	0.647 89	0.471 96	0.793 73	0.300 101	0.477 103	0.505 81	0.358 101	0.903 103	0.327 99	0.081 108	0.472 90	0.529 88	0.448 103	0.710 69	0.509 89	0.746 96	0.737 94	0.554 86

PanopticFusion-label	0.529 97	0.491 108	0.688 88	0.604 97	0.386 103	0.632 106	0.225 111	0.705 75	0.434 100	0.293 107	0.815 109	0.348 97	0.241 65	0.499 85	0.669 71	0.507 96	0.649 91	0.442 105	0.796 90	0.602 110	0.561 82
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 98	0.676 85	0.591 108	0.609 95	0.442 99	0.774 82	0.335 97	0.597 90	0.422 102	0.357 102	0.932 89	0.341 98	0.094 107	0.298 104	0.528 89	0.473 101	0.676 84	0.495 94	0.602 109	0.721 98	0.349 110

Online SegFusion	0.515 99	0.607 97	0.644 99	0.579 100	0.434 100	0.630 107	0.353 95	0.628 88	0.440 98	0.410 94	0.762 113	0.307 101	0.167 94	0.520 78	0.403 100	0.516 95	0.565 101	0.447 103	0.678 104	0.701 100	0.514 95
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	0.501 100	0.558 102	0.608 106	0.424 112	0.478 95	0.690 98	0.246 107	0.586 92	0.468 91	0.450 87	0.911 99	0.394 88	0.160 97	0.438 93	0.212 109	0.432 104	0.541 107	0.475 98	0.742 97	0.727 96	0.477 101

PCNN	0.498 101	0.559 101	0.644 99	0.560 102	0.420 102	0.711 97	0.229 109	0.414 104	0.436 99	0.352 103	0.941 75	0.324 100	0.155 98	0.238 109	0.387 101	0.493 97	0.529 108	0.509 89	0.813 89	0.751 91	0.504 96

Weakly-Openseg v3	0.489 102	0.749 62	0.664 93	0.646 91	0.496 91	0.559 111	0.122 114	0.577 94	0.257 114	0.364 100	0.805 110	0.198 112	0.096 106	0.510 81	0.496 93	0.361 109	0.563 102	0.359 112	0.777 92	0.644 107	0.532 92

3DMV	0.484 103	0.484 109	0.538 110	0.643 92	0.424 101	0.606 110	0.310 99	0.574 95	0.433 101	0.378 97	0.796 111	0.301 102	0.214 75	0.537 76	0.208 110	0.472 102	0.507 111	0.413 108	0.693 102	0.602 110	0.539 88
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 104	0.577 100	0.611 104	0.356 114	0.321 111	0.715 96	0.299 103	0.376 108	0.328 110	0.319 105	0.944 69	0.285 104	0.164 95	0.216 112	0.229 107	0.484 99	0.545 106	0.456 101	0.755 95	0.709 99	0.475 102
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 105	0.679 84	0.604 107	0.578 101	0.380 104	0.682 100	0.291 104	0.106 114	0.483 88	0.258 112	0.920 96	0.258 108	0.025 112	0.231 111	0.325 103	0.480 100	0.560 104	0.463 100	0.725 99	0.666 105	0.231 114
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproduce	0.446 106	0.474 110	0.623 102	0.463 108	0.366 106	0.651 103	0.310 99	0.389 107	0.349 108	0.330 104	0.937 80	0.271 106	0.126 103	0.285 105	0.224 108	0.350 111	0.577 100	0.445 104	0.625 107	0.723 97	0.394 106
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	0.442 107	0.548 104	0.548 109	0.597 99	0.363 107	0.628 108	0.300 101	0.292 109	0.374 105	0.307 106	0.881 106	0.268 107	0.186 87	0.238 109	0.204 111	0.407 106	0.506 112	0.449 102	0.667 105	0.620 109	0.462 104

SurfaceConvPF	0.442 107	0.505 106	0.622 103	0.380 113	0.342 109	0.654 102	0.227 110	0.397 106	0.367 106	0.276 109	0.924 93	0.240 109	0.198 83	0.359 101	0.262 105	0.366 107	0.581 99	0.435 106	0.640 106	0.668 104	0.398 105
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutions	0.438 109	0.437 112	0.646 98	0.474 107	0.369 105	0.645 104	0.353 95	0.258 111	0.282 112	0.279 108	0.918 98	0.298 103	0.147 102	0.283 106	0.294 104	0.487 98	0.562 103	0.427 107	0.619 108	0.633 108	0.352 109
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 110	0.525 105	0.647 97	0.522 103	0.324 110	0.488 114	0.077 115	0.712 73	0.353 107	0.401 95	0.636 115	0.281 105	0.176 90	0.340 102	0.565 84	0.175 115	0.551 105	0.398 109	0.370 115	0.602 110	0.361 108

SPLAT Net	0.393 111	0.472 111	0.511 111	0.606 96	0.311 112	0.656 101	0.245 108	0.405 105	0.328 110	0.197 113	0.927 92	0.227 111	0.000 116	0.001 116	0.249 106	0.271 114	0.510 109	0.383 111	0.593 110	0.699 101	0.267 112
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	0.383 112	0.297 114	0.491 112	0.432 111	0.358 108	0.612 109	0.274 105	0.116 113	0.411 103	0.265 110	0.904 102	0.229 110	0.079 109	0.250 107	0.185 112	0.320 112	0.510 109	0.385 110	0.548 111	0.597 113	0.394 106

PointNet++	0.339 113	0.584 99	0.478 113	0.458 109	0.256 114	0.360 115	0.250 106	0.247 112	0.278 113	0.261 111	0.677 114	0.183 113	0.117 104	0.212 113	0.145 114	0.364 108	0.346 115	0.232 115	0.548 111	0.523 114	0.252 113
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNet	0.308 114	0.353 113	0.290 115	0.278 115	0.166 115	0.553 112	0.169 113	0.286 110	0.147 115	0.148 115	0.908 100	0.182 114	0.064 110	0.023 115	0.018 116	0.354 110	0.363 113	0.345 113	0.546 113	0.685 102	0.278 111

ScanNet	0.306 115	0.203 115	0.366 114	0.501 104	0.311 112	0.524 113	0.211 112	0.002 116	0.342 109	0.189 114	0.786 112	0.145 115	0.102 105	0.245 108	0.152 113	0.318 113	0.348 114	0.300 114	0.460 114	0.437 115	0.182 115
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 116	0.000 116	0.041 116	0.172 116	0.030 116	0.062 116	0.001 116	0.035 115	0.004 116	0.051 116	0.143 116	0.019 116	0.003 115	0.041 114	0.050 115	0.003 116	0.054 116	0.018 116	0.005 116	0.264 116	0.082 116

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

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

Spherical Mask(CtoF)	0.616 1	0.946 5	0.654 9	0.555 4	0.434 8	0.769 5	0.271 8	0.604 8	0.447 4	0.505 5	0.549 1	0.698 2	0.716 2	0.775 11	0.480 6	0.747 4	0.575 7	0.925 9	0.436 4

EV3D	0.615 2	0.946 5	0.652 10	0.555 4	0.433 9	0.773 2	0.271 9	0.604 8	0.447 4	0.506 4	0.544 4	0.698 2	0.716 2	0.775 11	0.480 6	0.747 4	0.572 9	0.925 9	0.435 5

SIM3D	0.614 3	0.952 4	0.654 8	0.539 7	0.422 12	0.768 7	0.302 5	0.688 2	0.419 7	0.476 11	0.513 11	0.703 1	0.717 1	0.743 20	0.460 14	0.770 1	0.565 11	0.914 13	0.446 2

ExtMask3D	0.598 4	0.852 14	0.692 4	0.433 26	0.461 5	0.791 1	0.264 10	0.488 31	0.493 1	0.508 3	0.528 10	0.594 9	0.706 5	0.791 6	0.483 4	0.734 8	0.595 2	0.911 15	0.437 3

MAFT	0.596 5	0.889 12	0.721 1	0.448 19	0.460 6	0.768 6	0.251 11	0.558 19	0.408 8	0.504 6	0.539 6	0.616 7	0.618 9	0.858 3	0.482 5	0.684 16	0.551 13	0.931 8	0.450 1

UniPerception	0.588 6	0.963 3	0.667 6	0.493 11	0.472 4	0.750 10	0.229 14	0.528 24	0.468 3	0.498 8	0.542 5	0.643 5	0.530 18	0.661 33	0.463 11	0.695 15	0.599 1	0.972 1	0.420 6

MG-Former	0.587 7	0.852 14	0.639 12	0.454 18	0.393 16	0.758 9	0.338 2	0.572 15	0.480 2	0.527 2	0.491 17	0.671 4	0.527 19	0.867 1	0.485 3	0.601 26	0.590 5	0.938 7	0.390 10

InsSSM	0.586 8	1.000 1	0.593 16	0.440 22	0.480 2	0.771 3	0.345 1	0.437 35	0.444 6	0.495 9	0.548 3	0.579 12	0.621 8	0.720 24	0.409 18	0.712 10	0.593 3	0.960 3	0.395 8

Queryformer	0.583 9	0.926 8	0.702 2	0.393 32	0.504 1	0.733 16	0.276 7	0.527 25	0.373 13	0.479 10	0.534 8	0.533 18	0.697 6	0.720 25	0.436 16	0.745 6	0.592 4	0.958 4	0.363 17

PBNet	0.573 10	0.926 8	0.575 21	0.619 1	0.472 3	0.736 14	0.239 13	0.487 32	0.383 12	0.459 14	0.506 14	0.533 17	0.585 11	0.767 13	0.404 19	0.717 9	0.559 12	0.969 2	0.381 13
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
TST3D	0.569 11	0.778 22	0.675 5	0.598 2	0.451 7	0.727 17	0.280 6	0.476 34	0.395 9	0.472 12	0.457 23	0.583 10	0.580 13	0.777 8	0.462 13	0.735 7	0.547 15	0.919 12	0.333 23

Mask3D	0.566 12	0.926 8	0.597 15	0.408 29	0.420 13	0.737 13	0.239 12	0.598 11	0.386 11	0.458 15	0.549 1	0.568 15	0.716 2	0.601 39	0.480 6	0.646 20	0.575 7	0.922 11	0.364 16
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
OneFormer3D	0.566 12	0.781 21	0.697 3	0.562 3	0.431 10	0.770 4	0.331 3	0.400 41	0.373 14	0.529 1	0.504 15	0.568 14	0.475 24	0.732 22	0.470 9	0.762 2	0.550 14	0.871 30	0.379 14
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
ISBNet	0.559 14	0.939 7	0.655 7	0.383 35	0.426 11	0.763 8	0.180 16	0.534 23	0.386 10	0.499 7	0.509 13	0.621 6	0.427 34	0.704 28	0.467 10	0.649 19	0.571 10	0.948 5	0.401 7
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
GraphCut	0.552 15	1.000 1	0.611 14	0.438 23	0.392 17	0.714 18	0.139 19	0.598 12	0.327 17	0.389 18	0.510 12	0.598 8	0.427 35	0.754 16	0.463 12	0.761 3	0.588 6	0.903 18	0.329 24

SPFormer	0.549 16	0.745 25	0.640 11	0.484 12	0.395 15	0.739 12	0.311 4	0.566 17	0.335 16	0.468 13	0.492 16	0.555 16	0.478 23	0.747 18	0.436 15	0.712 11	0.540 16	0.893 22	0.343 22
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
DKNet	0.532 17	0.815 18	0.624 13	0.517 8	0.377 19	0.749 11	0.107 21	0.509 28	0.304 19	0.437 16	0.475 18	0.581 11	0.539 16	0.775 10	0.339 24	0.640 22	0.506 19	0.901 19	0.385 12
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
IPCA-Inst	0.520 18	0.889 12	0.551 25	0.548 6	0.418 14	0.665 28	0.064 30	0.585 13	0.260 27	0.277 32	0.471 20	0.500 19	0.644 7	0.785 7	0.369 20	0.591 29	0.511 17	0.878 27	0.362 18

SoftGroup++	0.513 19	0.704 31	0.578 20	0.398 31	0.363 25	0.704 19	0.061 31	0.647 5	0.297 24	0.378 21	0.537 7	0.343 22	0.614 10	0.828 5	0.295 29	0.710 13	0.505 21	0.875 29	0.394 9

SSTNet	0.506 20	0.738 28	0.549 26	0.497 10	0.316 30	0.693 22	0.178 17	0.377 44	0.198 33	0.330 23	0.463 22	0.576 13	0.515 20	0.857 4	0.494 1	0.637 23	0.457 25	0.943 6	0.290 33
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
DANCENET	0.504 21	0.926 8	0.579 17	0.472 14	0.367 22	0.626 38	0.165 18	0.432 36	0.221 29	0.408 17	0.449 25	0.411 20	0.564 14	0.746 19	0.421 17	0.707 14	0.438 28	0.846 38	0.288 34

SoftGroup	0.504 21	0.667 38	0.579 18	0.372 37	0.381 18	0.694 21	0.072 27	0.677 3	0.303 20	0.387 19	0.531 9	0.319 26	0.582 12	0.754 15	0.318 25	0.643 21	0.492 22	0.907 17	0.388 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]
TD3D	0.489 23	0.852 14	0.511 35	0.434 24	0.322 29	0.735 15	0.101 24	0.512 27	0.355 15	0.349 22	0.468 21	0.283 30	0.514 21	0.676 32	0.268 34	0.671 17	0.510 18	0.908 16	0.329 25
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
OccuSeg+instance	0.486 24	0.802 20	0.536 28	0.428 27	0.369 21	0.702 20	0.205 15	0.331 49	0.301 21	0.379 20	0.474 19	0.327 23	0.437 29	0.862 2	0.485 2	0.601 27	0.394 36	0.846 40	0.273 37
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
TopoSeg	0.479 25	0.704 31	0.564 22	0.467 16	0.366 23	0.633 36	0.068 28	0.554 20	0.262 26	0.328 24	0.447 26	0.323 24	0.534 17	0.722 23	0.288 31	0.614 24	0.482 23	0.912 14	0.358 20

DualGroup	0.469 26	0.815 18	0.552 24	0.398 30	0.374 20	0.683 24	0.130 20	0.539 22	0.310 18	0.327 25	0.407 29	0.276 31	0.447 28	0.535 43	0.342 23	0.659 18	0.455 26	0.900 21	0.301 29

SSEC	0.465 27	0.667 38	0.578 19	0.502 9	0.362 26	0.641 35	0.035 40	0.605 7	0.291 25	0.323 26	0.451 24	0.296 28	0.417 38	0.677 31	0.245 38	0.501 47	0.506 20	0.900 20	0.366 15

HAIS	0.457 28	0.704 31	0.561 23	0.457 17	0.364 24	0.673 25	0.046 39	0.547 21	0.194 34	0.308 27	0.426 27	0.288 29	0.454 27	0.711 26	0.262 35	0.563 37	0.434 30	0.889 24	0.344 21
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
DD-UNet+Group	0.436 29	0.630 46	0.508 38	0.480 13	0.310 32	0.624 40	0.065 29	0.638 6	0.174 35	0.256 36	0.384 33	0.194 43	0.428 32	0.759 14	0.289 30	0.574 34	0.400 34	0.849 37	0.291 32
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	0.435 30	0.716 30	0.495 40	0.355 39	0.331 27	0.689 23	0.102 23	0.394 43	0.208 32	0.280 30	0.395 31	0.250 34	0.544 15	0.741 21	0.309 27	0.536 43	0.391 37	0.842 43	0.258 41

Mask-Group	0.434 31	0.778 22	0.516 33	0.471 15	0.330 28	0.658 29	0.029 42	0.526 26	0.249 28	0.256 35	0.400 30	0.309 27	0.384 42	0.296 59	0.368 21	0.575 33	0.425 31	0.877 28	0.362 19
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
Box2Mask	0.433 32	0.741 26	0.463 45	0.433 25	0.283 35	0.625 39	0.103 22	0.298 54	0.125 44	0.260 34	0.424 28	0.322 25	0.472 25	0.701 29	0.363 22	0.711 12	0.309 53	0.882 25	0.272 39
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
RPGN	0.428 33	0.630 46	0.508 37	0.367 38	0.249 42	0.658 30	0.016 50	0.673 4	0.131 42	0.234 39	0.383 34	0.270 32	0.434 30	0.748 17	0.274 33	0.609 25	0.406 33	0.842 42	0.267 40
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
DENet	0.413 34	0.741 26	0.520 30	0.237 50	0.284 34	0.523 49	0.097 25	0.691 1	0.138 39	0.209 49	0.229 51	0.238 37	0.390 40	0.707 27	0.310 26	0.448 54	0.470 24	0.892 23	0.310 27

PointGroup	0.407 35	0.639 45	0.496 39	0.415 28	0.243 44	0.645 34	0.021 47	0.570 16	0.114 45	0.211 47	0.359 36	0.217 41	0.428 33	0.660 34	0.256 36	0.562 38	0.341 45	0.860 33	0.291 31
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]
CSC-Pretrained	0.405 36	0.738 28	0.465 44	0.331 43	0.205 48	0.655 31	0.051 35	0.601 10	0.092 49	0.211 48	0.329 39	0.198 42	0.459 26	0.775 9	0.195 45	0.524 45	0.400 35	0.878 26	0.184 50

PE	0.396 37	0.667 38	0.467 43	0.446 21	0.243 43	0.624 41	0.022 46	0.577 14	0.106 46	0.219 42	0.340 37	0.239 36	0.487 22	0.475 50	0.225 40	0.541 42	0.350 43	0.818 45	0.273 38
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
Dyco3D	0.395 38	0.642 44	0.518 32	0.447 20	0.259 41	0.666 27	0.050 36	0.251 59	0.166 36	0.231 40	0.362 35	0.232 38	0.331 45	0.535 42	0.229 39	0.587 30	0.438 29	0.850 35	0.317 26
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OSIS	0.392 39	0.778 22	0.530 29	0.220 52	0.278 36	0.567 46	0.083 26	0.330 50	0.299 22	0.270 33	0.310 42	0.143 49	0.260 49	0.624 37	0.277 32	0.568 36	0.361 41	0.865 32	0.301 28

AOIA	0.387 40	0.704 31	0.515 34	0.385 34	0.225 47	0.669 26	0.005 57	0.482 33	0.126 43	0.181 52	0.269 48	0.221 40	0.426 36	0.478 49	0.218 41	0.592 28	0.371 39	0.851 34	0.242 43

SSEN	0.384 41	0.852 14	0.494 41	0.192 53	0.226 46	0.648 33	0.022 45	0.398 42	0.299 23	0.277 31	0.317 41	0.231 39	0.194 56	0.514 46	0.196 43	0.586 31	0.444 27	0.843 41	0.184 49
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
Mask3D_evaluation	0.382 42	0.593 48	0.520 31	0.390 33	0.314 31	0.600 42	0.018 49	0.287 57	0.151 38	0.281 29	0.387 32	0.169 47	0.429 31	0.654 35	0.172 49	0.578 32	0.384 38	0.670 56	0.278 36

PCJC	0.375 43	0.704 31	0.542 27	0.284 47	0.197 50	0.649 32	0.006 54	0.426 37	0.138 40	0.242 37	0.304 43	0.183 46	0.388 41	0.629 36	0.141 56	0.546 41	0.344 44	0.738 51	0.283 35

ClickSeg_Instance	0.366 44	0.654 42	0.375 49	0.184 54	0.302 33	0.592 44	0.050 37	0.300 53	0.093 48	0.283 28	0.277 45	0.249 35	0.426 37	0.615 38	0.299 28	0.504 46	0.367 40	0.832 44	0.191 48

SphereSeg	0.357 45	0.651 43	0.411 47	0.345 40	0.264 40	0.630 37	0.059 32	0.289 56	0.212 30	0.240 38	0.336 38	0.158 48	0.305 46	0.557 40	0.159 52	0.455 53	0.341 46	0.726 53	0.294 30

3D-MPA	0.355 46	0.457 58	0.484 42	0.299 45	0.277 37	0.591 45	0.047 38	0.332 47	0.212 31	0.217 43	0.278 44	0.193 44	0.413 39	0.410 53	0.195 44	0.574 35	0.352 42	0.849 36	0.213 46
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
NeuralBF	0.353 47	0.593 48	0.511 36	0.375 36	0.264 39	0.597 43	0.008 52	0.332 48	0.160 37	0.229 41	0.274 47	0.000 70	0.206 53	0.678 30	0.155 53	0.485 49	0.422 32	0.816 46	0.254 42
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
RWSeg	0.348 48	0.475 55	0.456 46	0.320 44	0.275 38	0.476 51	0.020 48	0.491 30	0.056 56	0.212 46	0.320 40	0.261 33	0.302 47	0.520 44	0.182 47	0.557 39	0.285 55	0.867 31	0.197 47

GICN	0.341 49	0.580 50	0.371 50	0.344 41	0.198 49	0.469 52	0.052 34	0.564 18	0.093 47	0.212 45	0.212 53	0.127 51	0.347 44	0.537 41	0.206 42	0.525 44	0.329 48	0.729 52	0.241 44

One_Thing_One_Click	0.326 50	0.472 56	0.361 51	0.232 51	0.183 51	0.555 47	0.000 63	0.498 29	0.038 58	0.195 50	0.226 52	0.362 21	0.168 57	0.469 51	0.251 37	0.553 40	0.335 47	0.846 39	0.117 58
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Occipital-SCS	0.320 51	0.679 37	0.352 52	0.334 42	0.229 45	0.436 53	0.025 43	0.412 40	0.058 54	0.161 57	0.240 50	0.085 53	0.262 48	0.496 48	0.187 46	0.467 51	0.328 49	0.775 47	0.231 45

Sparse R-CNN	0.292 52	0.704 31	0.213 62	0.153 56	0.154 53	0.551 48	0.053 33	0.212 60	0.132 41	0.174 54	0.274 46	0.070 55	0.363 43	0.441 52	0.176 48	0.424 56	0.234 57	0.758 49	0.161 54

MTML	0.282 53	0.577 51	0.380 48	0.182 55	0.107 59	0.430 54	0.001 60	0.422 38	0.057 55	0.179 53	0.162 56	0.070 56	0.229 51	0.511 47	0.161 50	0.491 48	0.313 50	0.650 59	0.162 52
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
SALoss-ResNet	0.262 54	0.667 38	0.335 53	0.067 63	0.123 57	0.427 55	0.022 44	0.280 58	0.058 53	0.216 44	0.211 54	0.039 59	0.142 59	0.519 45	0.106 60	0.338 60	0.310 52	0.721 54	0.138 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	0.254 55	0.463 57	0.249 61	0.113 57	0.167 52	0.412 57	0.000 62	0.374 45	0.073 50	0.173 55	0.243 49	0.130 50	0.228 52	0.368 55	0.160 51	0.356 58	0.208 58	0.711 55	0.136 56
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
3D-BoNet	0.253 56	0.519 53	0.324 56	0.251 49	0.137 56	0.345 62	0.031 41	0.419 39	0.069 51	0.162 56	0.131 58	0.052 57	0.202 55	0.338 57	0.147 55	0.301 63	0.303 54	0.651 58	0.178 51
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
SPG_WSIS	0.251 57	0.380 60	0.274 59	0.289 46	0.144 54	0.413 56	0.000 63	0.311 51	0.065 52	0.113 59	0.130 59	0.029 62	0.204 54	0.388 54	0.108 59	0.459 52	0.311 51	0.769 48	0.127 57

SegGroup_ins	0.246 58	0.556 52	0.335 54	0.062 65	0.115 58	0.490 50	0.000 63	0.297 55	0.018 62	0.186 51	0.142 57	0.083 54	0.233 50	0.216 61	0.153 54	0.469 50	0.251 56	0.744 50	0.083 61
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
PanopticFusion-inst	0.214 59	0.250 65	0.330 55	0.275 48	0.103 60	0.228 68	0.000 63

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