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

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

OA-CNN-L_ScanNet200	0.333 2	0.558 1	0.269 2	0.124 4	0.448 6	0.080 4	0.272 3	0.000 1	0.000 1	0.000 1	0.342 5	0.515 2	0.524 2	0.713 8	0.789 2	0.158 4	0.384 3	0.000 3	0.806 2	0.125 2	0.000 4	0.496 3	0.332 2	0.498 7	0.227 4	0.024 2	0.474 1	0.000 1	0.003 2	0.071 4	0.487 1	0.000 3	0.000 1	0.110 2	0.000 2	0.876 1	0.013 8	0.703 1	0.000 3	0.076 4	0.473 4	0.355 4	0.906 2	0.000 1	0.000 1	0.476 4	0.706 1	0.000 7	0.672 6	0.835 5	0.748 2	0.015 7	0.223 2	0.860 3	0.000 1	0.000 4	0.572 2	0.000 5	0.509 3	0.313 2	0.662 1	0.398 5	0.396 1	0.411 6	0.276 1	0.527 1	0.711 1	0.000 2	0.076 5	0.946 1	0.166 2	0.000 1	0.022 2	0.160 1	0.183 4	0.493 4	0.699 3	0.637 2	0.403 2	0.330 5	0.406 4	0.526 2	0.024 1	0.000 1	0.392 4	0.000 5	0.016 8	0.000 3	0.196 2	0.915 2	0.112 3	0.557 3	0.197 1	0.352 4	0.877 2	0.000 3	0.000 1	0.592 6	0.103 6	0.000 8	0.067 1	0.000 1	0.089 1	0.735 3	0.625 3	0.130 5	0.568 2	0.836 2	0.271 1	0.534 3	0.043 6	0.799 2	0.001 2	0.445 1	0.000 1	0.000 2	0.024 1	0.661 2	0.000 1	0.262 1	0.000 1	0.591 3	0.517 7	0.373 3	0.788 3	0.021 2	0.000 1	0.455 1	0.517 4	0.320 3	0.823 4	0.200 8	0.001 8	0.150 3	0.100 4	0.000 1	0.736 2	0.668 2	0.103 6	0.052 3	0.662 1	0.720 1	0.000 1	0.602 4	0.112 3	0.002 3	0.000 1	0.637 4	0.000 2	0.000 1	0.621 3	0.569 1	0.398 2	0.412 3	0.234 3	0.949 1	0.363 1	0.492 7	0.495 3	0.251 3	0.665 3	0.000 1	0.001 5	0.805 2	0.833 2	0.794 4	0.000 1	0.821 1	0.314 2	0.843 5	0.000 1	0.560 2	0.245 2	0.262 2	0.713 1	0.370 5

PPT-SpUNet-F.T.	0.332 3	0.556 2	0.270 1	0.123 5	0.519 1	0.091 2	0.349 2	0.000 1	0.000 1	0.000 1	0.339 6	0.383 5	0.498 5	0.833 2	0.807 1	0.241 1	0.584 2	0.000 3	0.755 3	0.124 3	0.000 4	0.608 2	0.330 3	0.530 4	0.314 1	0.000 4	0.374 3	0.000 1	0.000 3	0.197 1	0.459 3	0.000 3	0.000 1	0.117 1	0.000 2	0.876 1	0.095 1	0.682 2	0.000 3	0.086 3	0.518 2	0.433 1	0.930 1	0.000 1	0.000 1	0.563 3	0.542 5	0.077 4	0.715 2	0.858 3	0.756 1	0.008 8	0.171 4	0.874 2	0.000 1	0.039 1	0.550 3	0.000 5	0.545 2	0.256 3	0.657 3	0.453 1	0.351 3	0.449 5	0.213 2	0.392 3	0.611 4	0.000 2	0.037 6	0.946 1	0.138 5	0.000 1	0.000 4	0.063 3	0.308 1	0.537 2	0.796 1	0.673 1	0.323 5	0.392 3	0.400 5	0.509 3	0.000 2	0.000 1	0.649 1	0.000 5	0.023 5	0.000 3	0.000 3	0.914 3	0.002 7	0.506 7	0.163 5	0.359 3	0.872 3	0.000 3	0.000 1	0.623 2	0.112 3	0.001 7	0.000 4	0.000 1	0.021 2	0.753 1	0.565 7	0.150 1	0.579 1	0.806 4	0.267 2	0.616 1	0.042 7	0.783 4	0.000 3	0.374 5	0.000 1	0.000 2	0.000 2	0.620 4	0.000 1	0.000 4	0.000 1	0.572 6	0.634 1	0.350 4	0.792 2	0.000 3	0.000 1	0.376 4	0.535 2	0.378 2	0.855 1	0.672 1	0.074 5	0.000 4	0.185 3	0.000 1	0.727 3	0.660 3	0.076 8	0.000 6	0.432 4	0.646 3	0.000 1	0.594 5	0.006 7	0.000 4	0.000 1	0.658 2	0.000 2	0.000 1	0.661 1	0.549 3	0.300 5	0.291 5	0.045 5	0.942 4	0.304 2	0.600 3	0.572 2	0.135 7	0.695 1	0.000 1	0.008 3	0.793 3	0.942 1	0.899 2	0.000 1	0.816 2	0.181 4	0.897 1	0.000 1	0.679 1	0.223 3	0.264 1	0.691 2	0.345 6
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.
OctFormer ScanNet200	0.326 4	0.539 4	0.265 3	0.131 3	0.499 2	0.110 1	0.522 1	0.000 1	0.000 1	0.000 1	0.318 8	0.427 4	0.455 6	0.743 6	0.765 4	0.175 3	0.842 1	0.000 3	0.828 1	0.204 1	0.033 2	0.429 4	0.335 1	0.601 1	0.312 2	0.000 4	0.357 4	0.000 1	0.000 3	0.047 5	0.423 4	0.000 3	0.000 1	0.105 3	0.000 2	0.873 3	0.079 6	0.670 4	0.000 3	0.117 1	0.471 5	0.432 2	0.829 5	0.000 1	0.000 1	0.584 2	0.417 8	0.089 3	0.684 5	0.837 4	0.705 7	0.021 6	0.178 3	0.892 1	0.000 1	0.028 2	0.505 5	0.000 5	0.457 4	0.200 6	0.662 1	0.412 3	0.244 6	0.496 3	0.000 8	0.451 2	0.626 3	0.000 2	0.102 4	0.943 3	0.138 5	0.000 1	0.000 4	0.149 2	0.291 2	0.534 3	0.722 2	0.632 3	0.331 4	0.253 7	0.453 3	0.487 4	0.000 2	0.000 1	0.479 2	0.000 5	0.022 6	0.000 3	0.000 3	0.900 4	0.128 2	0.684 1	0.164 4	0.413 1	0.854 5	0.000 3	0.000 1	0.512 8	0.074 8	0.003 6	0.000 4	0.000 1	0.000 3	0.469 6	0.613 4	0.132 4	0.529 3	0.871 1	0.227 7	0.582 2	0.026 8	0.787 3	0.000 3	0.339 6	0.000 1	0.000 2	0.000 2	0.626 3	0.000 1	0.029 3	0.000 1	0.587 4	0.612 3	0.411 2	0.724 5	0.000 3	0.000 1	0.407 3	0.552 1	0.513 1	0.849 2	0.655 2	0.408 1	0.000 4	0.296 1	0.000 1	0.686 6	0.645 5	0.145 3	0.022 4	0.414 5	0.633 4	0.000 1	0.637 1	0.224 1	0.000 4	0.000 1	0.650 3	0.000 2	0.000 1	0.622 2	0.535 4	0.343 3	0.483 2	0.230 4	0.943 3	0.289 3	0.618 2	0.596 1	0.140 6	0.679 2	0.000 1	0.022 1	0.783 4	0.620 6	0.906 1	0.000 1	0.806 3	0.137 6	0.865 2	0.000 1	0.378 4	0.000 7	0.168 8	0.680 3	0.227 7
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
LGround	0.272 6	0.485 6	0.184 6	0.106 6	0.476 3	0.077 5	0.218 4	0.000 1	0.000 1	0.000 1	0.547 1	0.295 6	0.540 1	0.746 5	0.745 6	0.058 7	0.112 7	0.005 1	0.658 5	0.077 8	0.000 4	0.322 6	0.178 7	0.512 5	0.190 5	0.199 1	0.277 6	0.000 1	0.000 3	0.173 2	0.399 5	0.000 3	0.000 1	0.039 7	0.000 2	0.858 6	0.085 5	0.676 3	0.002 1	0.103 2	0.498 3	0.323 5	0.703 6	0.000 1	0.000 1	0.296 6	0.549 4	0.216 1	0.702 3	0.768 6	0.718 5	0.028 4	0.092 7	0.786 7	0.000 1	0.000 4	0.453 7	0.022 3	0.251 8	0.252 4	0.572 6	0.348 6	0.321 4	0.514 2	0.063 6	0.279 7	0.552 6	0.000 2	0.019 7	0.932 6	0.132 7	0.000 1	0.000 4	0.000 7	0.156 8	0.457 6	0.623 5	0.518 5	0.265 7	0.358 4	0.381 6	0.395 6	0.000 2	0.000 1	0.127 8	0.012 3	0.051 1	0.000 3	0.000 3	0.886 7	0.014 5	0.437 8	0.179 2	0.244 6	0.826 6	0.000 3	0.000 1	0.599 4	0.136 1	0.085 2	0.000 4	0.000 1	0.000 3	0.565 4	0.612 5	0.143 2	0.207 6	0.566 6	0.232 6	0.446 6	0.127 2	0.708 6	0.000 3	0.384 4	0.000 1	0.000 2	0.000 2	0.402 5	0.000 1	0.059 2	0.000 1	0.525 8	0.566 5	0.229 6	0.659 6	0.000 3	0.000 1	0.265 6	0.446 5	0.147 7	0.720 8	0.597 4	0.066 6	0.000 4	0.187 2	0.000 1	0.726 4	0.467 8	0.134 5	0.000 6	0.413 6	0.629 5	0.000 1	0.363 7	0.055 5	0.022 2	0.000 1	0.626 5	0.000 2	0.000 1	0.323 6	0.479 8	0.154 7	0.117 6	0.028 7	0.901 6	0.243 6	0.415 8	0.295 8	0.143 5	0.610 7	0.000 1	0.000 6	0.777 5	0.397 8	0.324 7	0.000 1	0.778 6	0.179 5	0.702 7	0.000 1	0.274 8	0.404 1	0.233 4	0.622 6	0.398 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CeCo	0.340 1	0.551 3	0.247 4	0.181 1	0.475 4	0.057 8	0.142 7	0.000 1	0.000 1	0.000 1	0.387 3	0.463 3	0.499 4	0.924 1	0.774 3	0.213 2	0.257 4	0.000 3	0.546 8	0.100 5	0.006 3	0.615 1	0.177 8	0.534 2	0.246 3	0.000 4	0.400 2	0.000 1	0.338 1	0.006 7	0.484 2	0.609 1	0.000 1	0.083 4	0.000 2	0.873 3	0.089 4	0.661 5	0.000 3	0.048 8	0.560 1	0.408 3	0.892 3	0.000 1	0.000 1	0.586 1	0.616 3	0.000 7	0.692 4	0.900 1	0.721 3	0.162 1	0.228 1	0.860 3	0.000 1	0.000 4	0.575 1	0.083 2	0.550 1	0.347 1	0.624 4	0.410 4	0.360 2	0.740 1	0.109 5	0.321 6	0.660 2	0.000 2	0.121 2	0.939 4	0.143 3	0.000 1	0.400 1	0.003 5	0.190 3	0.564 1	0.652 4	0.615 4	0.421 1	0.304 6	0.579 1	0.547 1	0.000 2	0.000 1	0.296 5	0.000 5	0.030 4	0.096 1	0.000 3	0.916 1	0.037 4	0.551 4	0.171 3	0.376 2	0.865 4	0.286 1	0.000 1	0.633 1	0.102 7	0.027 4	0.011 3	0.000 1	0.000 3	0.474 5	0.742 1	0.133 3	0.311 4	0.824 3	0.242 4	0.503 5	0.068 4	0.828 1	0.000 3	0.429 2	0.000 1	0.063 1	0.000 2	0.781 1	0.000 1	0.000 4	0.000 1	0.665 1	0.633 2	0.450 1	0.818 1	0.000 3	0.000 1	0.429 2	0.532 3	0.226 4	0.825 3	0.510 6	0.377 2	0.709 1	0.079 6	0.000 1	0.753 1	0.683 1	0.102 7	0.063 2	0.401 7	0.620 6	0.000 1	0.619 2	0.000 8	0.000 4	0.000 1	0.595 6	0.000 2	0.000 1	0.345 5	0.564 2	0.411 1	0.603 1	0.384 2	0.945 2	0.266 4	0.643 1	0.367 5	0.304 1	0.663 4	0.000 1	0.010 2	0.726 6	0.767 3	0.898 3	0.000 1	0.784 4	0.435 1	0.861 4	0.000 1	0.447 3	0.000 7	0.257 3	0.656 4	0.377 4
: Understanding Imbalanced Semantic Segmentation Through Neural Collapse.
Minkowski 34D	0.253 7	0.463 7	0.154 8	0.102 7	0.381 8	0.084 3	0.134 8	0.000 1	0.000 1	0.000 1	0.386 4	0.141 8	0.279 8	0.737 7	0.703 7	0.014 8	0.164 6	0.000 3	0.663 4	0.092 7	0.000 4	0.224 7	0.291 4	0.531 3	0.056 8	0.000 4	0.242 7	0.000 1	0.000 3	0.013 6	0.331 7	0.000 3	0.000 1	0.035 8	0.001 1	0.858 6	0.059 7	0.650 7	0.000 3	0.056 7	0.353 7	0.299 6	0.670 7	0.000 1	0.000 1	0.284 7	0.484 6	0.071 5	0.594 7	0.720 7	0.710 6	0.027 5	0.068 8	0.813 5	0.000 1	0.005 3	0.492 6	0.164 1	0.274 7	0.111 8	0.571 7	0.307 8	0.293 5	0.307 8	0.150 4	0.163 8	0.531 7	0.002 1	0.545 1	0.932 6	0.093 8	0.000 1	0.000 4	0.002 6	0.159 6	0.368 8	0.581 7	0.440 8	0.228 8	0.406 2	0.282 8	0.294 7	0.000 2	0.000 1	0.189 7	0.060 1	0.036 3	0.000 3	0.000 3	0.897 5	0.000 8	0.525 6	0.025 8	0.205 8	0.771 8	0.000 3	0.000 1	0.593 5	0.108 5	0.044 3	0.000 4	0.000 1	0.000 3	0.282 8	0.589 6	0.094 7	0.169 7	0.466 8	0.227 7	0.419 8	0.125 3	0.757 5	0.002 1	0.334 7	0.000 1	0.000 2	0.000 2	0.357 6	0.000 1	0.000 4	0.000 1	0.582 5	0.513 8	0.337 5	0.612 8	0.000 3	0.000 1	0.250 7	0.352 8	0.136 8	0.724 7	0.655 2	0.280 3	0.000 4	0.046 8	0.000 1	0.606 8	0.559 6	0.159 2	0.102 1	0.445 2	0.655 2	0.000 1	0.310 8	0.117 2	0.000 4	0.000 1	0.581 8	0.026 1	0.000 1	0.265 8	0.483 7	0.084 8	0.097 8	0.044 6	0.865 8	0.142 8	0.588 4	0.351 6	0.272 2	0.596 8	0.000 1	0.003 4	0.622 7	0.720 4	0.096 8	0.000 1	0.771 7	0.016 7	0.772 6	0.000 1	0.302 6	0.194 4	0.214 6	0.621 7	0.197 8
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain	0.249 8	0.455 8	0.171 7	0.079 8	0.418 7	0.059 7	0.186 6	0.000 1	0.000 1	0.000 1	0.335 7	0.250 7	0.316 7	0.766 4	0.697 8	0.142 5	0.170 5	0.003 2	0.553 7	0.112 4	0.097 1	0.201 8	0.186 5	0.476 8	0.081 7	0.000 4	0.216 8	0.000 1	0.000 3	0.001 8	0.314 8	0.000 3	0.000 1	0.055 6	0.000 2	0.832 8	0.094 2	0.659 6	0.002 1	0.076 4	0.310 8	0.293 8	0.664 8	0.000 1	0.000 1	0.175 8	0.634 2	0.130 2	0.552 8	0.686 8	0.700 8	0.076 3	0.110 6	0.770 8	0.000 1	0.000 4	0.430 8	0.000 5	0.319 6	0.166 7	0.542 8	0.327 7	0.205 7	0.332 7	0.052 7	0.375 4	0.444 8	0.000 2	0.012 8	0.930 8	0.203 1	0.000 1	0.000 4	0.046 4	0.175 5	0.413 7	0.592 6	0.471 7	0.299 6	0.152 8	0.340 7	0.247 8	0.000 2	0.000 1	0.225 6	0.058 2	0.037 2	0.000 3	0.207 1	0.862 8	0.014 5	0.548 5	0.033 7	0.233 7	0.816 7	0.000 3	0.000 1	0.542 7	0.123 2	0.121 1	0.019 2	0.000 1	0.000 3	0.463 7	0.454 8	0.045 8	0.128 8	0.557 7	0.235 5	0.441 7	0.063 5	0.484 8	0.000 3	0.308 8	0.000 1	0.000 2	0.000 2	0.318 8	0.000 1	0.000 4	0.000 1	0.545 7	0.543 6	0.164 8	0.734 4	0.000 3	0.000 1	0.215 8	0.371 7	0.198 5	0.743 5	0.205 7	0.062 7	0.000 4	0.079 6	0.000 1	0.683 7	0.547 7	0.142 4	0.000 6	0.441 3	0.579 8	0.000 1	0.464 6	0.098 4	0.041 1	0.000 1	0.590 7	0.000 2	0.000 1	0.373 4	0.494 5	0.174 6	0.105 7	0.001 8	0.895 7	0.222 7	0.537 5	0.307 7	0.180 4	0.625 5	0.000 1	0.000 6	0.591 8	0.609 7	0.398 6	0.000 1	0.766 8	0.014 8	0.638 8	0.000 1	0.377 5	0.004 6	0.206 7	0.609 8	0.465 2
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	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

Mask3D Scannet200	0.278 1	0.383 1	0.263 1	0.168 1	0.506 1	0.068 1	0.083 5	0.000 1	0.000 1	0.000 1	0.023 2	0.149 4	0.302 1	0.778 3	0.647 1	0.569 1	0.500 1	0.031 1	0.014 2	0.027 2	0.173 1	0.311 1	0.195 1	0.351 3	0.258 1	0.000 1	0.082 1	0.000 1	0.003 1	0.037 2	0.391 1	1.000 1	0.000 1	0.014 2	0.000 1	0.572 1	0.573 1	0.661 2	0.000 1	0.003 1	0.005 4	0.082 4	0.349 1	0.028 1	0.000 1	0.605 1	0.515 3	0.509 1	0.711 1	1.000 1	0.665 3	0.015 2	0.107 1	0.402 4	0.201 1	0.083 1	0.304 1	0.759 1	0.491 1	0.378 1	0.572 1	0.119 1	0.277 1	0.013 5	0.089 1	0.283 2	0.411 2	0.267 1	0.006 3	0.156 2	0.000 1	0.116 1	0.000 1	0.105 3	0.556 1	0.514 1	0.396 1	0.275 1	0.323 1	0.215 2	0.380 1	0.000 1	0.000 1	0.356 1	0.005 2	0.208 1	0.325 1	0.000 1	0.050 4	0.400 1	0.561 1	0.258 1	0.179 1	0.722 1	0.147 1	0.000 1	0.586 1	0.063 1	0.015 2	0.139 1	0.016 1	0.028 1	0.708 1	0.418 2	0.016 1	0.048 3	0.500 1	0.489 1	0.349 1	0.001 2	0.475 2	0.086 1	0.365 1	0.000 1	0.500 1	0.000 2	0.323 3	0.000 1	0.222 1	0.000 1	0.497 1	0.626 1	0.044 3	0.795 1	0.556 1	0.008 2	0.121 4	0.265 1	0.667 1	0.789 1	0.568 2	0.579 1	0.444 1	0.176 1	0.004 2	0.474 1	0.752 1	0.233 2	0.014 2	0.002 4	0.570 2	0.007 1	0.377 5	0.000 1	0.000 2	0.000 2	0.337 1	0.000 1	0.000 1	0.384 1	0.465 1	0.287 1	0.085 1	0.048 2	0.816 5	0.467 1	0.810 1	0.377 1	0.415 1	0.744 1	0.000 1	0.004 1	0.724 1	0.778 2	0.590 1	0.000 1	0.032 2	0.441 1	0.000 1	0.377 2	0.391 1	0.427 1	0.321 1	0.192 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
LGround Inst.	0.154 3	0.275 3	0.108 3	0.060 3	0.295 5	0.002 4	0.278 1	0.000 1	0.000 1	0.000 1	0.006 4	0.272 2	0.064 5	0.815 2	0.503 3	0.333 5	0.000 2	0.000 3	0.556 1	0.001 4	0.000 2	0.148 3	0.078 2	0.448 1	0.007 3	0.000 1	0.024 3	0.000 1	0.000 2	0.000 3	0.190 4	0.000 2	0.000 1	0.000 3	0.000 1	0.209 5	0.031 5	0.573 3	0.000 1	0.000 2	0.041 2	0.099 3	0.037 4	0.000 2	0.000 1	0.327 2	0.364 5	0.181 2	0.642 2	1.000 1	0.654 4	0.000 3	0.023 3	0.429 3	0.000 3	0.000 3	0.097 3	0.000 3	0.278 2	0.267 2	0.434 3	0.048 2	0.092 3	0.257 2	0.030 3	0.097 4	0.189 3	0.000 2	0.089 2	0.000 5	0.000 1	0.000 3	0.000 1	0.115 2	0.166 3	0.222 5	0.222 3	0.003 3	0.127 3	0.213 4	0.169 2	0.000 1	0.000 1	0.000 3	0.000 3	0.044 3	0.000 3	0.000 1	0.000 5	0.000 4	0.268 5	0.222 2	0.130 2	0.494 3	0.000 3	0.000 1	0.363 3	0.015 3	0.000 3	0.000 3	0.000 2	0.000 3	0.611 2	0.400 3	0.000 2	0.056 2	0.278 3	0.242 4	0.180 3	0.000 3	0.383 4	0.000 2	0.209 2	0.000 1	0.000 3	0.000 2	0.364 2	0.000 1	0.000 2	0.000 1	0.323 4	0.302 3	0.019 4	0.654 2	0.000 3	0.000 3	0.141 2	0.045 3	0.000 5	0.427 5	0.514 3	0.143 3	0.000 2	0.028 4	0.000 3	0.252 3	0.402 4	0.156 4	0.000 3	0.028 2	0.470 3	0.000 3	0.444 3	0.000 1	0.000 2	0.000 2	0.205 3	0.000 1	0.000 1	0.203 3	0.381 3	0.026 3	0.037 3	0.000 3	0.881 3	0.099 4	0.135 4	0.239 3	0.000 4	0.585 4	0.000 1	0.000 2	0.616 2	0.778 2	0.322 2	0.000 1	0.000 3	0.407 3	0.000 1	0.333 4	0.148 3	0.177 3	0.242 3	0.028 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
CSC-Pretrain Inst.	0.123 5	0.223 5	0.082 5	0.046 4	0.308 3	0.004 3	0.278 1	0.000 1	0.000 1	0.000 1	0.000 5	0.032 5	0.105 3	0.537 4	0.348 5	0.378 4	0.000 2	0.000 3	0.000 3	0.000 5	0.000 2	0.000 5	0.037 5	0.323 4	0.000 4	0.000 1	0.013 5	0.000 1	0.000 2	0.000 3	0.235 2	0.000 2	0.000 1	0.000 3	0.000 1	0.231 3	0.045 3	0.564 4	0.000 1	0.000 2	0.006 3	0.078 5	0.065 3	0.000 2	0.000 1	0.259 3	0.516 2	0.000 4	0.600 4	1.000 1	0.578 5	0.000 3	0.000 5	0.184 5	0.000 3	0.000 3	0.034 5	0.000 3	0.211 4	0.089 3	0.394 5	0.018 5	0.064 4	0.171 4	0.001 5	0.144 3	0.172 4	0.000 2	0.000 4	0.044 4	0.000 1	0.000 3	0.000 1	0.064 5	0.126 4	0.278 2	0.093 5	0.000 4	0.094 4	0.214 3	0.011 5	0.000 1	0.000 1	0.000 3	0.000 3	0.022 5	0.000 3	0.000 1	0.275 3	0.000 4	0.275 4	0.000 5	0.098 4	0.407 4	0.000 3	0.000 1	0.250 5	0.007 5	0.000 3	0.000 3	0.000 2	0.000 3	0.333 4	0.376 4	0.000 2	0.000 5	0.042 5	0.285 3	0.119 4	0.000 3	0.224 5	0.000 2	0.184 3	0.000 1	0.000 3	0.000 2	0.244 4	0.000 1	0.000 2	0.000 1	0.377 3	0.378 2	0.051 2	0.424 5	0.000 3	0.000 3	0.116 5	0.030 4	0.125 2	0.441 4	0.444 5	0.063 5	0.000 2	0.042 3	0.000 3	0.297 2	0.483 3	0.096 5	0.000 3	0.028 2	0.338 4	0.000 3	0.444 3	0.000 1	0.000 2	0.000 2	0.189 4	0.000 1	0.000 1	0.141 4	0.152 5	0.017 4	0.000 5	0.000 3	0.838 4	0.193 3	0.111 5	0.105 5	0.198 3	0.588 3	0.000 1	0.000 2	0.542 3	0.343 5	0.267 3	0.000 1	0.000 3	0.108 5	0.000 1	0.333 4	0.000 5	0.228 2	0.202 5	0.022 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34D Inst.	0.130 4	0.246 4	0.083 4	0.043 5	0.299 4	0.000 5	0.278 1	0.000 1	0.000 1	0.000 1	0.022 3	0.175 3	0.122 2	0.537 4	0.521 2	0.400 3	0.000 2	0.000 3	0.000 3	0.008 3	0.000 2	0.048 4	0.076 3	0.182 5	0.000 4	0.000 1	0.022 4	0.000 1	0.000 2	0.000 3	0.141 5	0.000 2	0.000 1	0.000 3	0.000 1	0.210 4	0.063 2	0.547 5	0.000 1	0.000 2	0.000 5	0.100 2	0.026 5	0.000 2	0.000 1	0.241 4	0.488 4	0.000 4	0.564 5	1.000 1	0.672 2	0.000 3	0.021 4	0.486 1	0.000 3	0.000 3	0.067 4	0.000 3	0.194 5	0.033 4	0.415 4	0.026 4	0.025 5	0.271 1	0.004 4	0.094 5	0.142 5	0.000 2	0.000 4	0.111 3	0.000 1	0.000 3	0.000 1	0.088 4	0.083 5	0.278 2	0.110 4	0.000 4	0.082 5	0.199 5	0.137 3	0.000 1	0.000 1	0.000 3	0.000 3	0.041 4	0.000 3	0.000 1	0.308 2	0.067 3	0.280 3	0.016 4	0.101 3	0.373 5	0.000 3	0.000 1	0.319 4	0.007 4	0.000 3	0.000 3	0.000 2	0.000 3	0.028 5	0.355 5	0.000 2	0.101 1	0.444 2	0.289 2	0.114 5	0.000 3	0.394 3	0.000 2	0.032 5	0.000 1	0.000 3	0.000 2	0.201 5	0.000 1	0.000 2	0.000 1	0.384 2	0.248 4	0.000 5	0.529 4	0.000 3	0.000 3	0.133 3	0.020 5	0.089 3	0.720 3	0.500 4	0.099 4	0.000 2	0.000 5	0.000 3	0.238 4	0.334 5	0.190 3	0.000 3	0.000 5	0.317 5	0.000 3	0.472 1	0.000 1	0.000 2	0.000 2	0.094 5	0.000 1	0.000 1	0.082 5	0.236 4	0.004 5	0.019 4	0.000 3	0.883 2	0.061 5	0.262 2	0.217 4	0.000 4	0.557 5	0.000 1	0.000 2	0.460 4	0.761 4	0.156 5	0.000 1	0.000 3	0.259 4	0.000 1	0.394 1	0.019 4	0.084 4	0.232 4	0.000 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
TD3D Scannet200	0.211 2	0.332 2	0.177 2	0.103 2	0.337 2	0.036 2	0.222 4	0.000 1	0.000 1	0.000 1	0.031 1	0.342 1	0.093 4	0.852 1	0.452 4	0.559 2	0.000 2	0.004 2	0.000 3	0.039 1	0.000 2	0.309 2	0.047 4	0.380 2	0.028 2	0.000 1	0.080 2	0.000 1	0.000 2	0.147 1	0.192 3	0.000 2	0.000 1	0.083 1	0.000 1	0.395 2	0.039 4	0.662 1	0.000 1	0.000 2	0.074 1	0.135 1	0.296 2	0.000 2	0.000 1	0.231 5	0.646 1	0.139 3	0.633 3	1.000 1	0.705 1	0.048 1	0.088 2	0.439 2	0.184 2	0.039 2	0.266 2	0.551 2	0.260 3	0.026 5	0.463 2	0.046 3	0.252 2	0.249 3	0.083 2	0.372 1	0.411 1	0.000 2	0.414 1	0.323 1	0.000 1	0.052 2	0.000 1	0.157 1	0.278 2	0.278 2	0.237 2	0.015 2	0.321 2	0.253 1	0.060 4	0.000 1	0.000 1	0.272 2	0.008 1	0.169 2	0.032 2	0.000 1	0.404 1	0.356 2	0.283 2	0.073 3	0.028 5	0.617 2	0.038 2	0.000 1	0.494 2	0.037 2	0.215 1	0.083 2	0.000 2	0.003 2	0.486 3	0.694 1	0.000 2	0.040 4	0.083 4	0.219 5	0.209 2	0.007 1	0.483 1	0.000 2	0.125 4	0.000 1	0.150 2	0.014 1	0.544 1	0.000 1	0.000 2	0.000 1	0.260 5	0.143 5	0.200 1	0.610 3	0.028 2	0.032 1	0.145 1	0.059 2	0.046 4	0.740 2	0.806 1	0.543 2	0.000 2	0.108 2	0.008 1	0.222 5	0.669 2	0.456 1	0.074 1	0.224 1	0.586 1	0.006 2	0.451 2	0.000 1	0.002 1	0.889 1	0.282 2	0.000 1	0.000 1	0.252 2	0.413 2	0.111 2	0.074 2	0.240 1	0.893 1	0.266 2	0.144 3	0.293 2	0.281 2	0.604 2	0.000 1	0.000 2	0.379 5	0.963 1	0.250 4	0.000 1	0.160 1	0.420 2	0.000 1	0.343 3	0.207 2	0.079 5	0.315 2	0.052 2

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

OccuSeg+Semantic	0.764 5	0.758 52	0.796 23	0.839 15	0.746 17	0.907 1	0.562 7	0.850 18	0.680 11	0.672 9	0.978 2	0.610 2	0.335 11	0.777 5	0.819 37	0.847 1	0.830 1	0.691 10	0.972 1	0.885 4	0.727 15

PPT-SpUNet-Joint	0.766 3	0.932 2	0.794 25	0.829 19	0.751 15	0.854 11	0.540 14	0.903 4	0.630 26	0.672 9	0.963 9	0.565 15	0.357 4	0.788 2	0.900 8	0.737 19	0.802 13	0.685 12	0.950 2	0.887 2	0.780 2
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.
IPCA	0.731 24	0.890 10	0.837 3	0.864 2	0.726 24	0.873 3	0.530 19	0.824 29	0.489 78	0.647 13	0.978 2	0.609 3	0.336 10	0.624 42	0.733 51	0.758 13	0.776 31	0.570 57	0.949 3	0.877 8	0.728 13

PointConvFormer	0.749 11	0.793 35	0.790 28	0.807 30	0.750 16	0.856 10	0.524 20	0.881 9	0.588 46	0.642 19	0.977 4	0.591 6	0.274 37	0.781 3	0.929 2	0.804 3	0.796 19	0.642 26	0.947 4	0.885 4	0.715 22
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
One-Thing-One-Click	0.693 36	0.743 58	0.794 25	0.655 78	0.684 34	0.822 41	0.497 34	0.719 59	0.622 28	0.617 28	0.977 4	0.447 60	0.339 9	0.750 21	0.664 67	0.703 34	0.790 26	0.596 47	0.946 5	0.855 24	0.647 42
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PointTransformerV2	0.752 9	0.742 59	0.809 15	0.872 1	0.758 9	0.860 8	0.552 9	0.891 8	0.610 34	0.687 3	0.960 11	0.559 18	0.304 23	0.766 10	0.926 3	0.767 10	0.797 18	0.644 25	0.942 6	0.876 11	0.722 19
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
Retro-FPN	0.744 17	0.842 22	0.800 20	0.767 47	0.740 19	0.836 27	0.541 13	0.914 1	0.672 13	0.626 25	0.958 14	0.552 21	0.272 39	0.777 5	0.886 15	0.696 36	0.801 16	0.674 17	0.941 7	0.858 20	0.717 20
Peng Xiang, Xin Wen, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
Mix3D	0.781 1	0.964 1	0.855 1	0.843 13	0.781 3	0.858 9	0.575 4	0.831 25	0.685 9	0.714 2	0.979 1	0.594 4	0.310 20	0.801 1	0.892 12	0.841 2	0.819 3	0.723 3	0.940 8	0.887 2	0.725 17
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
VMNet	0.746 15	0.870 14	0.838 2	0.858 4	0.729 23	0.850 16	0.501 29	0.874 11	0.587 47	0.658 12	0.956 19	0.564 16	0.299 24	0.765 11	0.900 8	0.716 28	0.812 9	0.631 31	0.939 9	0.858 20	0.709 23
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)
MatchingNet	0.724 27	0.812 32	0.812 13	0.810 28	0.735 21	0.834 29	0.495 35	0.860 16	0.572 53	0.602 36	0.954 28	0.512 33	0.280 34	0.757 15	0.845 31	0.725 22	0.780 29	0.606 43	0.937 10	0.851 29	0.700 28

OA-CNN-L_ScanNet20	0.756 8	0.783 38	0.826 4	0.858 4	0.776 4	0.837 25	0.548 11	0.896 7	0.649 19	0.675 7	0.962 10	0.586 9	0.335 11	0.771 8	0.802 41	0.770 9	0.787 27	0.691 10	0.936 11	0.880 7	0.761 6

Virtual MVFusion	0.746 15	0.771 46	0.819 8	0.848 9	0.702 29	0.865 7	0.397 76	0.899 5	0.699 4	0.664 11	0.948 47	0.588 7	0.330 13	0.746 22	0.851 29	0.764 11	0.796 19	0.704 8	0.935 12	0.866 15	0.728 13
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
SparseConvNet	0.725 25	0.647 82	0.821 6	0.846 10	0.721 25	0.869 4	0.533 16	0.754 49	0.603 40	0.614 29	0.955 22	0.572 13	0.325 15	0.710 27	0.870 17	0.724 23	0.823 2	0.628 32	0.934 13	0.865 16	0.683 32

INS-Conv-semantic	0.717 29	0.751 55	0.759 44	0.812 26	0.704 28	0.868 5	0.537 15	0.842 22	0.609 36	0.608 32	0.953 31	0.534 26	0.293 27	0.616 45	0.864 20	0.719 27	0.793 23	0.640 27	0.933 14	0.845 34	0.663 37

LargeKernel3D	0.739 21	0.909 6	0.820 7	0.806 32	0.740 19	0.852 14	0.545 12	0.826 27	0.594 45	0.643 16	0.955 22	0.541 23	0.263 48	0.723 26	0.858 24	0.775 8	0.767 37	0.678 14	0.933 14	0.848 30	0.694 29
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
O-CNN	0.762 7	0.924 4	0.823 5	0.844 12	0.770 5	0.852 14	0.577 2	0.847 21	0.711 1	0.640 20	0.958 14	0.592 5	0.217 64	0.762 13	0.888 13	0.758 13	0.813 8	0.726 1	0.932 16	0.868 13	0.744 8
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
PointTransformer++	0.725 25	0.727 67	0.811 14	0.819 22	0.765 7	0.841 22	0.502 28	0.814 34	0.621 29	0.623 27	0.955 22	0.556 19	0.284 32	0.620 44	0.866 19	0.781 6	0.757 46	0.648 23	0.932 16	0.862 17	0.709 23

CU-Hybrid Net	0.764 5	0.924 4	0.819 8	0.840 14	0.757 10	0.853 13	0.580 1	0.848 19	0.709 2	0.643 16	0.958 14	0.587 8	0.295 26	0.753 18	0.884 16	0.758 13	0.815 5	0.725 2	0.927 18	0.867 14	0.743 9

RPN	0.736 22	0.776 42	0.790 28	0.851 6	0.754 12	0.854 11	0.491 38	0.866 13	0.596 44	0.686 4	0.955 22	0.536 24	0.342 8	0.624 42	0.869 18	0.787 5	0.802 13	0.628 32	0.927 18	0.875 12	0.704 26

OctFormer	0.766 3	0.925 3	0.808 16	0.849 7	0.786 2	0.846 19	0.566 6	0.876 10	0.690 7	0.674 8	0.960 11	0.576 11	0.226 58	0.753 18	0.904 6	0.777 7	0.815 5	0.722 4	0.923 20	0.877 8	0.776 4
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
SAT	0.742 19	0.860 17	0.765 41	0.819 22	0.769 6	0.848 17	0.533 16	0.829 26	0.663 15	0.631 23	0.955 22	0.586 9	0.274 37	0.753 18	0.896 10	0.729 20	0.760 43	0.666 20	0.921 21	0.855 24	0.733 11

MSP	0.748 13	0.623 85	0.804 18	0.859 3	0.745 18	0.824 38	0.501 29	0.912 2	0.690 7	0.685 5	0.956 19	0.567 14	0.320 17	0.768 9	0.918 4	0.720 25	0.802 13	0.676 15	0.921 21	0.881 6	0.779 3

DMF-Net	0.752 9	0.906 8	0.793 27	0.802 34	0.689 32	0.825 36	0.556 8	0.867 12	0.681 10	0.602 36	0.960 11	0.555 20	0.365 3	0.779 4	0.859 22	0.747 16	0.795 22	0.717 5	0.917 23	0.856 22	0.764 5
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
Swin3D	0.779 2	0.861 16	0.818 10	0.836 16	0.790 1	0.875 2	0.576 3	0.905 3	0.704 3	0.739 1	0.969 6	0.611 1	0.349 6	0.756 16	0.958 1	0.702 35	0.805 12	0.708 6	0.916 24	0.898 1	0.801 1

BPNet	0.749 11	0.909 6	0.818 10	0.811 27	0.752 13	0.839 24	0.485 39	0.842 22	0.673 12	0.644 15	0.957 17	0.528 29	0.305 22	0.773 7	0.859 22	0.788 4	0.818 4	0.693 9	0.916 24	0.856 22	0.723 18
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
LRPNet	0.742 19	0.816 30	0.806 17	0.807 30	0.752 13	0.828 34	0.575 4	0.839 24	0.699 4	0.637 21	0.954 28	0.520 31	0.320 17	0.755 17	0.834 33	0.760 12	0.772 33	0.676 15	0.915 26	0.862 17	0.717 20

PointContrast_LA_SEM	0.683 44	0.757 53	0.784 32	0.786 39	0.639 48	0.824 38	0.408 71	0.775 43	0.604 39	0.541 51	0.934 79	0.532 27	0.269 43	0.552 63	0.777 44	0.645 61	0.793 23	0.640 27	0.913 27	0.824 41	0.671 35

dtc_net	0.596 77	0.683 75	0.725 62	0.715 59	0.549 75	0.803 59	0.444 60	0.647 75	0.493 74	0.495 68	0.941 66	0.409 75	0.000 105	0.424 87	0.544 75	0.598 74	0.703 67	0.522 79	0.912 28	0.792 64	0.520 84

Feature-Geometry Net	0.685 40	0.866 15	0.748 50	0.819 22	0.645 46	0.794 64	0.450 53	0.802 38	0.587 47	0.604 34	0.945 55	0.464 50	0.201 72	0.554 62	0.840 32	0.723 24	0.732 55	0.602 45	0.907 29	0.822 44	0.603 58

EQ-Net	0.743 18	0.620 86	0.799 22	0.849 7	0.730 22	0.822 41	0.493 36	0.897 6	0.664 14	0.681 6	0.955 22	0.562 17	0.378 1	0.760 14	0.903 7	0.738 18	0.801 16	0.673 18	0.907 29	0.877 8	0.745 7
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
Feature_GeometricNet	0.690 38	0.884 12	0.754 48	0.795 37	0.647 44	0.818 48	0.422 68	0.802 38	0.612 33	0.604 34	0.945 55	0.462 51	0.189 77	0.563 59	0.853 27	0.726 21	0.765 38	0.632 30	0.904 31	0.821 45	0.606 55
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
AttAN	0.609 75	0.760 51	0.667 83	0.649 80	0.521 79	0.793 65	0.457 49	0.648 74	0.528 65	0.434 84	0.947 49	0.401 78	0.153 90	0.454 82	0.721 55	0.648 57	0.717 59	0.536 76	0.904 31	0.765 77	0.485 89
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
PicassoNet-II	0.692 37	0.732 63	0.772 37	0.786 39	0.677 36	0.866 6	0.517 23	0.848 19	0.509 70	0.626 25	0.952 35	0.536 24	0.225 60	0.545 66	0.704 58	0.689 41	0.810 10	0.564 61	0.903 33	0.854 27	0.729 12
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One Thing One Click	0.701 34	0.825 28	0.796 23	0.723 54	0.716 26	0.832 30	0.433 66	0.816 31	0.634 24	0.609 31	0.969 6	0.418 73	0.344 7	0.559 60	0.833 34	0.715 29	0.808 11	0.560 62	0.902 34	0.847 31	0.680 33

PointConv	0.666 49	0.781 39	0.759 44	0.699 63	0.644 47	0.822 41	0.475 40	0.779 42	0.564 58	0.504 67	0.953 31	0.428 67	0.203 71	0.586 51	0.754 47	0.661 51	0.753 47	0.588 53	0.902 34	0.813 49	0.642 43
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointNet2-SFPN	0.631 66	0.771 46	0.692 76	0.672 71	0.524 78	0.837 25	0.440 63	0.706 65	0.538 62	0.446 79	0.944 61	0.421 72	0.219 63	0.552 63	0.751 49	0.591 77	0.737 52	0.543 73	0.901 36	0.768 76	0.557 75

StratifiedFormer	0.747 14	0.901 9	0.803 19	0.845 11	0.757 10	0.846 19	0.512 24	0.825 28	0.696 6	0.645 14	0.956 19	0.576 11	0.262 49	0.744 23	0.861 21	0.742 17	0.770 36	0.705 7	0.899 37	0.860 19	0.734 10
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
HPEIN	0.618 73	0.729 65	0.668 82	0.647 81	0.597 59	0.766 77	0.414 70	0.680 68	0.520 66	0.525 58	0.946 52	0.432 63	0.215 65	0.493 78	0.599 72	0.638 62	0.617 89	0.570 57	0.897 38	0.806 51	0.605 57
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
FusionAwareConv	0.630 69	0.604 89	0.741 57	0.766 48	0.590 61	0.747 83	0.501 29	0.734 56	0.503 72	0.527 57	0.919 89	0.454 55	0.323 16	0.550 65	0.420 88	0.678 43	0.688 72	0.544 71	0.896 39	0.795 58	0.627 49
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
Superpoint Network	0.683 44	0.851 20	0.728 61	0.800 36	0.653 42	0.806 56	0.468 44	0.804 36	0.572 53	0.602 36	0.946 52	0.453 57	0.239 57	0.519 71	0.822 35	0.689 41	0.762 42	0.595 49	0.895 40	0.827 40	0.630 48

PointMRNet	0.640 58	0.717 70	0.701 69	0.692 66	0.576 67	0.801 60	0.467 46	0.716 60	0.563 59	0.459 77	0.953 31	0.429 66	0.169 84	0.581 52	0.854 26	0.605 70	0.710 60	0.550 69	0.894 41	0.793 61	0.575 66

SALANet	0.670 48	0.816 30	0.770 39	0.768 46	0.652 43	0.807 55	0.451 50	0.747 51	0.659 18	0.545 50	0.924 85	0.473 47	0.149 92	0.571 56	0.811 39	0.635 64	0.746 50	0.623 35	0.892 42	0.794 59	0.570 68

PNE	0.721 28	0.840 23	0.789 30	0.833 17	0.690 30	0.823 40	0.509 25	0.864 15	0.618 30	0.629 24	0.957 17	0.500 36	0.266 46	0.763 12	0.797 43	0.674 48	0.791 25	0.621 37	0.892 42	0.855 24	0.708 25

RFCR	0.702 33	0.889 11	0.745 53	0.813 25	0.672 37	0.818 48	0.493 36	0.815 33	0.623 27	0.610 30	0.947 49	0.470 48	0.249 53	0.594 48	0.848 30	0.705 33	0.779 30	0.646 24	0.892 42	0.823 42	0.611 51
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
contrastBoundary	0.705 31	0.769 49	0.775 36	0.809 29	0.687 33	0.820 44	0.439 64	0.812 35	0.661 16	0.591 42	0.945 55	0.515 32	0.171 82	0.633 39	0.856 25	0.720 25	0.796 19	0.668 19	0.889 45	0.847 31	0.689 30
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
VI-PointConv	0.676 46	0.770 48	0.754 48	0.783 42	0.621 52	0.814 51	0.552 9	0.758 47	0.571 55	0.557 47	0.954 28	0.529 28	0.268 45	0.530 69	0.682 62	0.675 44	0.719 58	0.603 44	0.888 46	0.833 36	0.665 36
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
SConv	0.636 62	0.830 26	0.697 72	0.752 52	0.572 69	0.780 72	0.445 57	0.716 60	0.529 64	0.530 56	0.951 37	0.446 61	0.170 83	0.507 75	0.666 66	0.636 63	0.682 74	0.541 74	0.886 47	0.799 54	0.594 62

ROSMRF3D	0.673 47	0.789 36	0.748 50	0.763 49	0.635 50	0.814 51	0.407 73	0.747 51	0.581 51	0.573 44	0.950 41	0.484 42	0.271 41	0.607 46	0.754 47	0.649 55	0.774 32	0.596 47	0.883 48	0.823 42	0.606 55

KP-FCNN	0.684 41	0.847 21	0.758 46	0.784 41	0.647 44	0.814 51	0.473 41	0.772 44	0.605 38	0.594 41	0.935 75	0.450 58	0.181 80	0.587 49	0.805 40	0.690 39	0.785 28	0.614 39	0.882 49	0.819 46	0.632 47
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 41	0.728 66	0.757 47	0.776 44	0.690 30	0.804 58	0.464 47	0.816 31	0.577 52	0.587 43	0.945 55	0.508 35	0.276 36	0.671 29	0.710 56	0.663 50	0.750 49	0.589 52	0.881 50	0.832 38	0.653 40

DenSeR	0.628 70	0.800 33	0.625 91	0.719 57	0.545 76	0.806 56	0.445 57	0.597 81	0.448 88	0.519 62	0.938 71	0.481 43	0.328 14	0.489 79	0.499 83	0.657 53	0.759 44	0.592 50	0.881 50	0.797 57	0.634 46

ClickSeg_Semantic	0.703 32	0.774 44	0.800 20	0.793 38	0.760 8	0.847 18	0.471 42	0.802 38	0.463 85	0.634 22	0.968 8	0.491 40	0.271 41	0.726 25	0.910 5	0.706 32	0.815 5	0.551 68	0.878 52	0.833 36	0.570 68

MVPNet	0.641 56	0.831 25	0.715 63	0.671 73	0.590 61	0.781 70	0.394 77	0.679 69	0.642 20	0.553 48	0.937 72	0.462 51	0.256 50	0.649 33	0.406 89	0.626 65	0.691 71	0.666 20	0.877 53	0.792 64	0.608 54
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
SIConv	0.625 72	0.830 26	0.694 74	0.757 50	0.563 71	0.772 76	0.448 54	0.647 75	0.520 66	0.509 63	0.949 45	0.431 65	0.191 76	0.496 77	0.614 71	0.647 58	0.672 78	0.535 77	0.876 54	0.783 70	0.571 67

PointConv-SFPN	0.641 56	0.776 42	0.703 67	0.721 56	0.557 73	0.826 35	0.451 50	0.672 71	0.563 59	0.483 71	0.943 63	0.425 70	0.162 87	0.644 35	0.726 52	0.659 52	0.709 62	0.572 56	0.875 55	0.786 69	0.559 74

3DSM_DMMF	0.631 66	0.626 84	0.745 53	0.801 35	0.607 55	0.751 82	0.506 26	0.729 58	0.565 57	0.491 70	0.866 99	0.434 62	0.197 75	0.595 47	0.630 69	0.709 31	0.705 65	0.560 62	0.875 55	0.740 84	0.491 88

MinkowskiNet	0.736 22	0.859 18	0.818 10	0.832 18	0.709 27	0.840 23	0.521 22	0.853 17	0.660 17	0.643 16	0.951 37	0.544 22	0.286 31	0.731 24	0.893 11	0.675 44	0.772 33	0.683 13	0.874 57	0.852 28	0.727 15
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
APCF-Net	0.631 66	0.742 59	0.687 81	0.672 71	0.557 73	0.792 67	0.408 71	0.665 72	0.545 61	0.508 64	0.952 35	0.428 67	0.186 78	0.634 38	0.702 59	0.620 66	0.706 64	0.555 66	0.873 58	0.798 56	0.581 64
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
SegGroup_sem	0.627 71	0.818 29	0.747 52	0.701 62	0.602 57	0.764 78	0.385 82	0.629 78	0.490 76	0.508 64	0.931 82	0.409 75	0.201 72	0.564 58	0.725 53	0.618 67	0.692 70	0.539 75	0.873 58	0.794 59	0.548 78
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
CCRFNet	0.589 80	0.766 50	0.659 86	0.683 68	0.470 87	0.740 85	0.387 81	0.620 80	0.490 76	0.476 73	0.922 87	0.355 87	0.245 55	0.511 72	0.511 81	0.571 82	0.643 85	0.493 86	0.872 60	0.762 78	0.600 59

FPConv	0.639 59	0.785 37	0.760 43	0.713 61	0.603 56	0.798 62	0.392 78	0.534 91	0.603 40	0.524 59	0.948 47	0.457 53	0.250 52	0.538 67	0.723 54	0.598 74	0.696 69	0.614 39	0.872 60	0.799 54	0.567 71
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
JSENet	0.699 35	0.881 13	0.762 42	0.821 20	0.667 38	0.800 61	0.522 21	0.792 41	0.613 32	0.607 33	0.935 75	0.492 39	0.205 69	0.576 53	0.853 27	0.691 38	0.758 45	0.652 22	0.872 60	0.828 39	0.649 41
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
DGNet	0.684 41	0.712 71	0.784 32	0.782 43	0.658 39	0.835 28	0.499 33	0.823 30	0.641 21	0.597 39	0.950 41	0.487 41	0.281 33	0.575 54	0.619 70	0.647 58	0.764 39	0.620 38	0.871 63	0.846 33	0.688 31

PPCNN++	0.663 51	0.746 56	0.708 65	0.722 55	0.638 49	0.820 44	0.451 50	0.566 86	0.599 42	0.541 51	0.950 41	0.510 34	0.313 19	0.648 34	0.819 37	0.616 69	0.682 74	0.590 51	0.869 64	0.810 50	0.656 39
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
PointMTL	0.632 65	0.731 64	0.688 79	0.675 70	0.591 60	0.784 69	0.444 60	0.565 87	0.610 34	0.492 69	0.949 45	0.456 54	0.254 51	0.587 49	0.706 57	0.599 73	0.665 80	0.612 42	0.868 65	0.791 68	0.579 65

PD-Net	0.638 60	0.797 34	0.769 40	0.641 84	0.590 61	0.820 44	0.461 48	0.537 90	0.637 23	0.536 54	0.947 49	0.388 81	0.206 68	0.656 31	0.668 65	0.647 58	0.732 55	0.585 54	0.868 65	0.793 61	0.473 93

Supervoxel-CNN	0.635 63	0.656 80	0.711 64	0.719 57	0.613 54	0.757 81	0.444 60	0.765 46	0.534 63	0.566 45	0.928 83	0.478 45	0.272 39	0.636 36	0.531 78	0.664 49	0.645 84	0.508 82	0.864 67	0.792 64	0.611 51

FusionNet	0.688 39	0.704 72	0.741 57	0.754 51	0.656 40	0.829 32	0.501 29	0.741 54	0.609 36	0.548 49	0.950 41	0.522 30	0.371 2	0.633 39	0.756 46	0.715 29	0.771 35	0.623 35	0.861 68	0.814 47	0.658 38
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
SPH3D-GCN	0.610 74	0.858 19	0.772 37	0.489 96	0.532 77	0.792 67	0.404 74	0.643 77	0.570 56	0.507 66	0.935 75	0.414 74	0.046 101	0.510 73	0.702 59	0.602 72	0.705 65	0.549 70	0.859 69	0.773 75	0.534 81
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
SAFNet-seg	0.654 54	0.752 54	0.734 59	0.664 76	0.583 65	0.815 50	0.399 75	0.754 49	0.639 22	0.535 55	0.942 64	0.470 48	0.309 21	0.665 30	0.539 76	0.650 54	0.708 63	0.635 29	0.857 70	0.793 61	0.642 43
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
HPGCNN	0.656 53	0.698 74	0.743 55	0.650 79	0.564 70	0.820 44	0.505 27	0.758 47	0.631 25	0.479 72	0.945 55	0.480 44	0.226 58	0.572 55	0.774 45	0.690 39	0.735 53	0.614 39	0.853 71	0.776 74	0.597 61
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
PointMetaBase	0.714 30	0.835 24	0.785 31	0.821 20	0.684 34	0.846 19	0.531 18	0.865 14	0.614 31	0.596 40	0.953 31	0.500 36	0.246 54	0.674 28	0.888 13	0.692 37	0.764 39	0.624 34	0.849 72	0.844 35	0.675 34

PointSPNet	0.637 61	0.734 62	0.692 76	0.714 60	0.576 67	0.797 63	0.446 55	0.743 53	0.598 43	0.437 82	0.942 64	0.403 77	0.150 91	0.626 41	0.800 42	0.649 55	0.697 68	0.557 65	0.846 73	0.777 73	0.563 72

joint point-based	0.634 64	0.614 87	0.778 35	0.667 75	0.633 51	0.825 36	0.420 69	0.804 36	0.467 83	0.561 46	0.951 37	0.494 38	0.291 28	0.566 57	0.458 84	0.579 81	0.764 39	0.559 64	0.838 74	0.814 47	0.598 60
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
wsss-transformer	0.600 76	0.634 83	0.743 55	0.697 65	0.601 58	0.781 70	0.437 65	0.585 84	0.493 74	0.446 79	0.933 80	0.394 79	0.011 103	0.654 32	0.661 68	0.603 71	0.733 54	0.526 78	0.832 75	0.761 79	0.480 90

RandLA-Net	0.645 55	0.778 40	0.731 60	0.699 63	0.577 66	0.829 32	0.446 55	0.736 55	0.477 80	0.523 61	0.945 55	0.454 55	0.269 43	0.484 80	0.749 50	0.618 67	0.738 51	0.599 46	0.827 76	0.792 64	0.621 50

DCM-Net	0.658 52	0.778 40	0.702 68	0.806 32	0.619 53	0.813 54	0.468 44	0.693 67	0.494 73	0.524 59	0.941 66	0.449 59	0.298 25	0.510 73	0.821 36	0.675 44	0.727 57	0.568 59	0.826 77	0.803 53	0.637 45
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
Pointnet++ & Feature	0.557 86	0.735 61	0.661 85	0.686 67	0.491 83	0.744 84	0.392 78	0.539 89	0.451 87	0.375 90	0.946 52	0.376 83	0.205 69	0.403 89	0.356 92	0.553 84	0.643 85	0.497 84	0.824 78	0.756 80	0.515 85

PointASNL	0.666 49	0.703 73	0.781 34	0.751 53	0.655 41	0.830 31	0.471 42	0.769 45	0.474 81	0.537 53	0.951 37	0.475 46	0.279 35	0.635 37	0.698 61	0.675 44	0.751 48	0.553 67	0.816 79	0.806 51	0.703 27
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PCNN	0.498 92	0.559 92	0.644 89	0.560 93	0.420 92	0.711 88	0.229 100	0.414 94	0.436 90	0.352 93	0.941 66	0.324 91	0.155 89	0.238 99	0.387 91	0.493 88	0.529 98	0.509 80	0.813 80	0.751 82	0.504 87

PanopticFusion-label	0.529 88	0.491 98	0.688 79	0.604 88	0.386 93	0.632 97	0.225 102	0.705 66	0.434 91	0.293 97	0.815 100	0.348 88	0.241 56	0.499 76	0.669 64	0.507 87	0.649 82	0.442 96	0.796 81	0.602 100	0.561 73
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
TextureNet	0.566 84	0.672 79	0.664 84	0.671 73	0.494 82	0.719 86	0.445 57	0.678 70	0.411 94	0.396 87	0.935 75	0.356 86	0.225 60	0.412 88	0.535 77	0.565 83	0.636 88	0.464 90	0.794 82	0.680 94	0.568 70
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
LAP-D	0.594 78	0.720 68	0.692 76	0.637 85	0.456 88	0.773 75	0.391 80	0.730 57	0.587 47	0.445 81	0.940 69	0.381 82	0.288 29	0.434 85	0.453 86	0.591 77	0.649 82	0.581 55	0.777 83	0.749 83	0.610 53

DPC	0.592 79	0.720 68	0.700 70	0.602 89	0.480 84	0.762 80	0.380 83	0.713 63	0.585 50	0.437 82	0.940 69	0.369 84	0.288 29	0.434 85	0.509 82	0.590 79	0.639 87	0.567 60	0.772 84	0.755 81	0.592 63
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
PointCNN with RGB	0.458 94	0.577 91	0.611 94	0.356 104	0.321 101	0.715 87	0.299 94	0.376 98	0.328 101	0.319 95	0.944 61	0.285 95	0.164 86	0.216 102	0.229 97	0.484 90	0.545 96	0.456 92	0.755 85	0.709 90	0.475 92
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
GMLPs	0.538 87	0.495 97	0.693 75	0.647 81	0.471 86	0.793 65	0.300 92	0.477 93	0.505 71	0.358 91	0.903 95	0.327 90	0.081 98	0.472 81	0.529 79	0.448 94	0.710 60	0.509 80	0.746 86	0.737 85	0.554 77

3DMV, FTSDF	0.501 91	0.558 93	0.608 96	0.424 102	0.478 85	0.690 89	0.246 98	0.586 83	0.468 82	0.450 78	0.911 91	0.394 79	0.160 88	0.438 83	0.212 99	0.432 95	0.541 97	0.475 89	0.742 87	0.727 87	0.477 91

SD-DETR	0.576 82	0.746 56	0.609 95	0.445 100	0.517 80	0.643 96	0.366 84	0.714 62	0.456 86	0.468 75	0.870 98	0.432 63	0.264 47	0.558 61	0.674 63	0.586 80	0.688 72	0.482 88	0.739 88	0.733 86	0.537 80

FCPN	0.447 95	0.679 76	0.604 97	0.578 92	0.380 94	0.682 91	0.291 95	0.106 104	0.483 79	0.258 102	0.920 88	0.258 99	0.025 102	0.231 101	0.325 93	0.480 91	0.560 94	0.463 91	0.725 89	0.666 96	0.231 104
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
ROSMRF	0.580 81	0.772 45	0.707 66	0.681 69	0.563 71	0.764 78	0.362 85	0.515 92	0.465 84	0.465 76	0.936 74	0.427 69	0.207 67	0.438 83	0.577 73	0.536 85	0.675 77	0.486 87	0.723 90	0.779 71	0.524 83

DVVNet	0.562 85	0.648 81	0.700 70	0.770 45	0.586 64	0.687 90	0.333 89	0.650 73	0.514 69	0.475 74	0.906 93	0.359 85	0.223 62	0.340 92	0.442 87	0.422 96	0.668 79	0.501 83	0.708 91	0.779 71	0.534 81

3DMV	0.484 93	0.484 99	0.538 100	0.643 83	0.424 91	0.606 101	0.310 90	0.574 85	0.433 92	0.378 88	0.796 101	0.301 93	0.214 66	0.537 68	0.208 100	0.472 93	0.507 101	0.413 99	0.693 92	0.602 100	0.539 79
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
SQN_0.1%	0.569 83	0.676 77	0.696 73	0.657 77	0.497 81	0.779 73	0.424 67	0.548 88	0.515 68	0.376 89	0.902 96	0.422 71	0.357 4	0.379 90	0.456 85	0.596 76	0.659 81	0.544 71	0.685 93	0.665 97	0.556 76

Online SegFusion	0.515 90	0.607 88	0.644 89	0.579 91	0.434 90	0.630 98	0.353 86	0.628 79	0.440 89	0.410 85	0.762 103	0.307 92	0.167 85	0.520 70	0.403 90	0.516 86	0.565 92	0.447 94	0.678 94	0.701 91	0.514 86
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
PNET2	0.442 97	0.548 94	0.548 99	0.597 90	0.363 97	0.628 99	0.300 92	0.292 99	0.374 96	0.307 96	0.881 97	0.268 98	0.186 78	0.238 99	0.204 101	0.407 97	0.506 102	0.449 93	0.667 95	0.620 99	0.462 94

SurfaceConvPF	0.442 97	0.505 96	0.622 93	0.380 103	0.342 99	0.654 93	0.227 101	0.397 96	0.367 97	0.276 99	0.924 85	0.240 100	0.198 74	0.359 91	0.262 95	0.366 98	0.581 90	0.435 97	0.640 96	0.668 95	0.398 95
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
DGCNN_reproduce	0.446 96	0.474 100	0.623 92	0.463 98	0.366 96	0.651 94	0.310 90	0.389 97	0.349 99	0.330 94	0.937 72	0.271 97	0.126 94	0.285 95	0.224 98	0.350 101	0.577 91	0.445 95	0.625 97	0.723 88	0.394 96
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
Tangent Convolutions	0.438 99	0.437 102	0.646 88	0.474 97	0.369 95	0.645 95	0.353 86	0.258 101	0.282 103	0.279 98	0.918 90	0.298 94	0.147 93	0.283 96	0.294 94	0.487 89	0.562 93	0.427 98	0.619 98	0.633 98	0.352 99
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
subcloud_weak	0.516 89	0.676 77	0.591 98	0.609 86	0.442 89	0.774 74	0.335 88	0.597 81	0.422 93	0.357 92	0.932 81	0.341 89	0.094 97	0.298 94	0.528 80	0.473 92	0.676 76	0.495 85	0.602 99	0.721 89	0.349 100

SPLAT Net	0.393 101	0.472 101	0.511 101	0.606 87	0.311 102	0.656 92	0.245 99	0.405 95	0.328 101	0.197 103	0.927 84	0.227 102	0.000 105	0.001 106	0.249 96	0.271 104	0.510 99	0.383 102	0.593 100	0.699 92	0.267 102
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	0.383 102	0.297 104	0.491 102	0.432 101	0.358 98	0.612 100	0.274 96	0.116 103	0.411 94	0.265 100	0.904 94	0.229 101	0.079 99	0.250 97	0.185 102	0.320 102	0.510 99	0.385 101	0.548 101	0.597 103	0.394 96

PointNet++	0.339 103	0.584 90	0.478 103	0.458 99	0.256 104	0.360 105	0.250 97	0.247 102	0.278 104	0.261 101	0.677 104	0.183 103	0.117 95	0.212 103	0.145 104	0.364 99	0.346 105	0.232 105	0.548 101	0.523 104	0.252 103
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNet	0.308 104	0.353 103	0.290 105	0.278 105	0.166 105	0.553 102	0.169 104	0.286 100	0.147 105	0.148 105	0.908 92	0.182 104	0.064 100	0.023 105	0.018 106	0.354 100	0.363 103	0.345 103	0.546 103	0.685 93	0.278 101

ScanNet	0.306 105	0.203 105	0.366 104	0.501 95	0.311 102	0.524 103	0.211 103	0.002 106	0.342 100	0.189 104	0.786 102	0.145 105	0.102 96	0.245 98	0.152 103	0.318 103	0.348 104	0.300 104	0.460 104	0.437 105	0.182 105
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
3DWSSS	0.425 100	0.525 95	0.647 87	0.522 94	0.324 100	0.488 104	0.077 105	0.712 64	0.353 98	0.401 86	0.636 105	0.281 96	0.176 81	0.340 92	0.565 74	0.175 105	0.551 95	0.398 100	0.370 105	0.602 100	0.361 98

ERROR	0.054 106	0.000 106	0.041 106	0.172 106	0.030 106	0.062 106	0.001 106	0.035 105	0.004 106	0.051 106	0.143 106	0.019 106	0.003 104	0.041 104	0.050 105	0.003 106	0.054 106	0.018 106	0.005 106	0.264 106	0.082 106

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

ISBNet	0.559 5	0.926 2	0.597 7	0.390 23	0.436 4	0.722 8	0.276 3	0.556 16	0.380 4	0.450 6	0.505 8	0.583 3	0.730 1	0.575 28	0.455 6	0.603 16	0.573 4	0.979 1	0.332 14
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
PBNet	0.573 3	0.926 2	0.575 11	0.619 1	0.472 2	0.736 5	0.239 6	0.487 26	0.383 3	0.459 4	0.506 7	0.533 8	0.585 7	0.767 8	0.404 9	0.717 3	0.559 5	0.969 2	0.381 5
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
Queryformer	0.583 2	0.926 2	0.702 2	0.393 22	0.504 1	0.733 7	0.276 2	0.527 20	0.373 5	0.479 2	0.534 4	0.533 9	0.697 3	0.720 16	0.436 8	0.745 2	0.592 1	0.958 3	0.363 8

SSTNet	0.506 11	0.738 18	0.549 16	0.497 5	0.316 20	0.693 13	0.178 8	0.377 34	0.198 23	0.330 13	0.463 14	0.576 5	0.515 12	0.857 3	0.494 1	0.637 13	0.457 16	0.943 4	0.290 24
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
MAFT	0.596 1	0.889 6	0.721 1	0.448 11	0.460 3	0.768 1	0.251 4	0.558 15	0.408 1	0.504 1	0.539 2	0.616 1	0.618 5	0.858 2	0.482 3	0.684 7	0.551 6	0.931 5	0.450 1

Mask3D	0.566 4	0.926 2	0.597 6	0.408 19	0.420 5	0.737 4	0.239 5	0.598 8	0.386 2	0.458 5	0.549 1	0.568 6	0.716 2	0.601 27	0.480 4	0.646 10	0.575 3	0.922 6	0.364 7
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TopoSeg	0.479 15	0.704 21	0.564 12	0.467 9	0.366 13	0.633 27	0.068 18	0.554 17	0.262 17	0.328 14	0.447 16	0.323 14	0.534 11	0.722 15	0.288 21	0.614 14	0.482 14	0.912 7	0.358 11

TD3D	0.489 13	0.852 8	0.511 24	0.434 15	0.322 19	0.735 6	0.101 14	0.512 22	0.355 6	0.349 12	0.468 13	0.283 20	0.514 13	0.676 22	0.268 24	0.671 8	0.510 9	0.908 8	0.329 16

SoftGroup	0.504 12	0.667 28	0.579 8	0.372 26	0.381 9	0.694 12	0.072 17	0.677 2	0.303 11	0.387 9	0.531 5	0.319 16	0.582 8	0.754 10	0.318 15	0.643 11	0.492 13	0.907 9	0.388 3
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
GraphCut	0.552 6	1.000 1	0.611 5	0.438 14	0.392 8	0.714 9	0.139 9	0.598 9	0.327 8	0.389 8	0.510 6	0.598 2	0.427 24	0.754 11	0.463 5	0.761 1	0.588 2	0.903 10	0.329 15

DKNet	0.532 8	0.815 10	0.624 4	0.517 3	0.377 10	0.749 2	0.107 11	0.509 23	0.304 10	0.437 7	0.475 10	0.581 4	0.539 10	0.775 7	0.339 14	0.640 12	0.506 10	0.901 11	0.385 4
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
SSEC	0.465 17	0.667 28	0.578 9	0.502 4	0.362 16	0.641 26	0.035 30	0.605 6	0.291 16	0.323 16	0.451 15	0.296 18	0.417 27	0.677 21	0.245 28	0.501 36	0.506 11	0.900 12	0.366 6

DualGroup	0.469 16	0.815 10	0.552 14	0.398 20	0.374 11	0.683 15	0.130 10	0.539 19	0.310 9	0.327 15	0.407 19	0.276 21	0.447 19	0.535 32	0.342 13	0.659 9	0.455 17	0.900 13	0.301 20

SPFormer	0.549 7	0.745 15	0.640 3	0.484 6	0.395 7	0.739 3	0.311 1	0.566 13	0.335 7	0.468 3	0.492 9	0.555 7	0.478 15	0.747 13	0.436 7	0.712 4	0.540 7	0.893 14	0.343 13
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
DENet	0.413 24	0.741 16	0.520 20	0.237 39	0.284 23	0.523 38	0.097 15	0.691 1	0.138 28	0.209 38	0.229 40	0.238 27	0.390 29	0.707 18	0.310 16	0.448 43	0.470 15	0.892 15	0.310 18

HAIS	0.457 18	0.704 21	0.561 13	0.457 10	0.364 14	0.673 16	0.046 29	0.547 18	0.194 24	0.308 17	0.426 17	0.288 19	0.454 18	0.711 17	0.262 25	0.563 26	0.434 20	0.889 16	0.344 12
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask	0.433 22	0.741 16	0.463 34	0.433 16	0.283 24	0.625 29	0.103 12	0.298 44	0.125 33	0.260 23	0.424 18	0.322 15	0.472 16	0.701 19	0.363 12	0.711 5	0.309 42	0.882 17	0.272 28
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
CSC-Pretrained	0.405 26	0.738 18	0.465 33	0.331 32	0.205 37	0.655 22	0.051 25	0.601 7	0.092 38	0.211 37	0.329 28	0.198 32	0.459 17	0.775 6	0.195 35	0.524 34	0.400 25	0.878 18	0.184 39

IPCA-Inst	0.520 9	0.889 6	0.551 15	0.548 2	0.418 6	0.665 19	0.064 20	0.585 10	0.260 18	0.277 21	0.471 12	0.500 10	0.644 4	0.785 5	0.369 10	0.591 19	0.511 8	0.878 19	0.362 9

Mask-Group	0.434 21	0.778 13	0.516 22	0.471 8	0.330 18	0.658 20	0.029 32	0.526 21	0.249 19	0.256 24	0.400 20	0.309 17	0.384 31	0.296 48	0.368 11	0.575 22	0.425 21	0.877 20	0.362 10
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
SoftGroup++	0.513 10	0.704 21	0.578 10	0.398 21	0.363 15	0.704 10	0.061 21	0.647 4	0.297 15	0.378 11	0.537 3	0.343 12	0.614 6	0.828 4	0.295 19	0.710 6	0.505 12	0.875 21	0.394 2

RWSeg	0.348 37	0.475 44	0.456 35	0.320 33	0.275 27	0.476 40	0.020 38	0.491 25	0.056 45	0.212 35	0.320 29	0.261 23	0.302 36	0.520 33	0.182 37	0.557 28	0.285 44	0.867 22	0.197 36

OSIS	0.392 29	0.778 13	0.530 19	0.220 41	0.278 25	0.567 35	0.083 16	0.330 40	0.299 13	0.270 22	0.310 31	0.143 38	0.260 38	0.624 25	0.277 22	0.568 25	0.361 30	0.865 23	0.301 19

PointGroup	0.407 25	0.639 35	0.496 28	0.415 18	0.243 33	0.645 25	0.021 37	0.570 12	0.114 34	0.211 36	0.359 25	0.217 31	0.428 23	0.660 23	0.256 26	0.562 27	0.341 34	0.860 24	0.291 22
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]
AOIA	0.387 30	0.704 21	0.515 23	0.385 24	0.225 36	0.669 17	0.005 45	0.482 27	0.126 32	0.181 41	0.269 37	0.221 30	0.426 25	0.478 38	0.218 31	0.592 18	0.371 28	0.851 25	0.242 32

Dyco3D	0.395 28	0.642 34	0.518 21	0.447 12	0.259 30	0.666 18	0.050 26	0.251 48	0.166 26	0.231 29	0.362 24	0.232 28	0.331 34	0.535 31	0.229 29	0.587 20	0.438 19	0.850 26	0.317 17
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
3D-MPA	0.355 35	0.457 47	0.484 31	0.299 34	0.277 26	0.591 34	0.047 28	0.332 37	0.212 21	0.217 32	0.278 33	0.193 34	0.413 28	0.410 42	0.195 34	0.574 24	0.352 31	0.849 27	0.213 35
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
DD-UNet+Group	0.436 19	0.630 36	0.508 27	0.480 7	0.310 21	0.624 30	0.065 19	0.638 5	0.174 25	0.256 25	0.384 22	0.194 33	0.428 22	0.759 9	0.289 20	0.574 23	0.400 24	0.849 28	0.291 23
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
One_Thing_One_Click	0.326 39	0.472 45	0.361 40	0.232 40	0.183 40	0.555 36	0.000 51	0.498 24	0.038 47	0.195 39	0.226 41	0.362 11	0.168 46	0.469 40	0.251 27	0.553 29	0.335 36	0.846 29	0.117 47
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
OccuSeg+instance	0.486 14	0.802 12	0.536 18	0.428 17	0.369 12	0.702 11	0.205 7	0.331 39	0.301 12	0.379 10	0.474 11	0.327 13	0.437 20	0.862 1	0.485 2	0.601 17	0.394 26	0.846 30	0.273 26
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
SSEN	0.384 31	0.852 8	0.494 30	0.192 42	0.226 35	0.648 24	0.022 35	0.398 32	0.299 14	0.277 20	0.317 30	0.231 29	0.194 45	0.514 35	0.196 33	0.586 21	0.444 18	0.843 31	0.184 38
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RPGN	0.428 23	0.630 36	0.508 26	0.367 27	0.249 31	0.658 21	0.016 39	0.673 3	0.131 31	0.234 28	0.383 23	0.270 22	0.434 21	0.748 12	0.274 23	0.609 15	0.406 23	0.842 32	0.267 29
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
INS-Conv-instance	0.435 20	0.716 20	0.495 29	0.355 28	0.331 17	0.689 14	0.102 13	0.394 33	0.208 22	0.280 19	0.395 21	0.250 24	0.544 9	0.741 14	0.309 17	0.536 32	0.391 27	0.842 33	0.258 30

ClickSeg_Instance	0.366 33	0.654 32	0.375 38	0.184 43	0.302 22	0.592 33	0.050 27	0.300 43	0.093 37	0.283 18	0.277 34	0.249 25	0.426 26	0.615 26	0.299 18	0.504 35	0.367 29	0.832 34	0.191 37

PE	0.396 27	0.667 28	0.467 32	0.446 13	0.243 32	0.624 31	0.022 36	0.577 11	0.106 35	0.219 31	0.340 26	0.239 26	0.487 14	0.475 39	0.225 30	0.541 31	0.350 32	0.818 35	0.273 27
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
NeuralBF	0.353 36	0.593 38	0.511 25	0.375 25	0.264 28	0.597 32	0.008 41	0.332 38	0.160 27	0.229 30	0.274 36	0.000 58	0.206 42	0.678 20	0.155 42	0.485 38	0.422 22	0.816 36	0.254 31
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
Occipital-SCS	0.320 40	0.679 27	0.352 41	0.334 31	0.229 34	0.436 42	0.025 33	0.412 31	0.058 43	0.161 46	0.240 39	0.085 42	0.262 37	0.496 37	0.187 36	0.467 40	0.328 38	0.775 37	0.231 34

SPG_WSIS	0.251 46	0.380 49	0.274 48	0.289 35	0.144 43	0.413 45	0.000 51	0.311 41	0.065 41	0.113 48	0.130 48	0.029 50	0.204 43	0.388 43	0.108 48	0.459 41	0.311 40	0.769 38	0.127 46

Sparse R-CNN	0.292 41	0.704 21	0.213 51	0.153 45	0.154 42	0.551 37	0.053 23	0.212 49	0.132 30	0.174 43	0.274 35	0.070 44	0.363 32	0.441 41	0.176 38	0.424 45	0.234 46	0.758 39	0.161 43

SegGroup_ins	0.246 47	0.556 41	0.335 43	0.062 54	0.115 47	0.490 39	0.000 51	0.297 45	0.018 51	0.186 40	0.142 46	0.083 43	0.233 39	0.216 50	0.153 43	0.469 39	0.251 45	0.744 40	0.083 50
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
PCJC	0.375 32	0.704 21	0.542 17	0.284 36	0.197 39	0.649 23	0.006 43	0.426 28	0.138 29	0.242 26	0.304 32	0.183 36	0.388 30	0.629 24	0.141 45	0.546 30	0.344 33	0.738 41	0.283 25

GICN	0.341 38	0.580 39	0.371 39	0.344 30	0.198 38	0.469 41	0.052 24	0.564 14	0.093 36	0.212 34	0.212 42	0.127 40	0.347 33	0.537 30	0.206 32	0.525 33	0.329 37	0.729 42	0.241 33

SphereSeg	0.357 34	0.651 33	0.411 36	0.345 29	0.264 29	0.630 28	0.059 22	0.289 46	0.212 20	0.240 27	0.336 27	0.158 37	0.305 35	0.557 29	0.159 41	0.455 42	0.341 35	0.726 43	0.294 21

SALoss-ResNet	0.262 43	0.667 28	0.335 42	0.067 52	0.123 46	0.427 44	0.022 34	0.280 47	0.058 42	0.216 33	0.211 43	0.039 48	0.142 48	0.519 34	0.106 49	0.338 49	0.310 41	0.721 44	0.138 44
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 44	0.463 46	0.249 50	0.113 46	0.167 41	0.412 46	0.000 50	0.374 35	0.073 39	0.173 44	0.243 38	0.130 39	0.228 41	0.368 44	0.160 40	0.356 47	0.208 47	0.711 45	0.136 45
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
PanopticFusion-inst	0.214 48	0.250 53	0.330 44	0.275 37	0.103 49	0.228 57	0.000 51	0.345 36	0.024 49	0.088 50	0.203 44	0.186 35	0.167 47	0.367 45	0.125 46	0.221 55	0.112 57	0.666 46	0.162 42
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3D-BoNet	0.253 45	0.519 42	0.324 45	0.251 38	0.137 45	0.345 51	0.031 31	0.419 30	0.069 40	0.162 45	0.131 47	0.052 46	0.202 44	0.338 46	0.147 44	0.301 52	0.303 43	0.651 47	0.178 40
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
MTML	0.282 42	0.577 40	0.380 37	0.182 44	0.107 48	0.430 43	0.001 48	0.422 29	0.057 44	0.179 42	0.162 45	0.070 45	0.229 40	0.511 36	0.161 39	0.491 37	0.313 39	0.650 48	0.162 41
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
UNet-backbone	0.161 49	0.519 42	0.259 49	0.084 48	0.059 51	0.325 53	0.002 46	0.093 54	0.009 53	0.077 52	0.064 51	0.045 47	0.044 55	0.161 52	0.045 51	0.331 50	0.180 49	0.566 49	0.033 58

R-PointNet	0.158 51	0.356 50	0.173 53	0.113 47	0.140 44	0.359 47	0.012 40	0.023 56	0.039 46	0.134 47	0.123 49	0.008 54	0.089 51	0.149 53	0.117 47	0.221 54	0.128 54	0.563 50	0.094 48

Region-18class	0.146 52	0.175 57	0.321 46	0.080 49	0.062 50	0.357 48	0.000 51	0.307 42	0.002 55	0.066 53	0.044 53	0.000 58	0.018 57	0.036 57	0.054 50	0.447 44	0.133 52	0.472 51	0.060 53

3D-SIS	0.161 49	0.407 48	0.155 55	0.068 51	0.043 55	0.346 50	0.001 47	0.134 51	0.005 54	0.088 49	0.106 50	0.037 49	0.135 50	0.321 47	0.028 54	0.339 48	0.116 56	0.466 52	0.093 49
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
SemRegionNet-20cls	0.121 53	0.296 52	0.203 52	0.071 50	0.058 52	0.349 49	0.000 51	0.150 50	0.019 50	0.054 54	0.034 55	0.017 53	0.052 53	0.042 56	0.013 57	0.209 56	0.183 48	0.371 53	0.057 54

3D-BEVIS	0.117 54	0.250 53	0.308 47	0.020 58	0.009 59	0.269 56	0.006 44	0.008 57	0.029 48	0.037 57	0.014 58	0.003 56	0.036 56	0.147 54	0.042 52	0.381 46	0.118 55	0.362 54	0.069 52
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
tmp	0.113 56	0.333 51	0.151 56	0.056 55	0.053 53	0.344 52	0.000 51	0.105 53	0.016 52	0.049 55	0.035 54	0.020 52	0.053 52	0.048 55	0.013 56	0.183 57	0.173 50	0.344 55	0.054 55

Sgpn_scannet	0.049 58	0.023 59	0.134 57	0.031 57	0.013 58	0.144 58	0.006 42	0.008 58	0.000 58	0.028 58	0.017 57	0.003 55	0.009 59	0.000 58	0.021 55	0.122 58	0.095 58	0.175 56	0.054 56

ASIS	0.085 57	0.037 58	0.080 58	0.066 53	0.047 54	0.282 55	0.000 51	0.052 55	0.002 56	0.047 56	0.026 56	0.001 57	0.046 54	0.194 51	0.031 53	0.264 53	0.140 51	0.167 57	0.047 57

Hier3D	0.117 54	0.222 55	0.161 54	0.054 56	0.027 56	0.289 54	0.000 51	0.124 52	0.001 57	0.079 51	0.061 52	0.027 51	0.141 49	0.240 49	0.005 58	0.310 51	0.129 53	0.153 58	0.081 51
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
MaskRCNN 2d->3d Proj	0.022 59	0.185 56	0.000 59	0.000 59	0.015 57	0.000 59	0.000 49	0.006 59	0.000 58	0.010 59	0.006 59	0.107 41	0.012 58	0.000 58	0.002 59	0.027 59	0.004 59	0.022 59	0.001 59

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 1	0.512 1	0.422 15	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
SSMA	0.577 11	0.695 4	0.716 12	0.439 14	0.563 11	0.314 11	0.444 13	0.719 8	0.551 10	0.503 9	0.887 12	0.346 13	0.348 9	0.603 9	0.353 17	0.709 5	0.600 12	0.457 12	0.901 2	0.786 8	0.599 11
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
FAN_NV_RVC	0.586 8	0.510 18	0.764 4	0.079 23	0.620 7	0.330 8	0.494 7	0.753 4	0.573 8	0.556 4	0.884 13	0.405 3	0.303 14	0.718 2	0.452 11	0.672 12	0.658 5	0.509 4	0.898 3	0.813 6	0.727 2

CMX	0.613 4	0.681 7	0.725 9	0.502 12	0.634 5	0.297 15	0.478 9	0.830 2	0.651 4	0.537 6	0.924 4	0.375 5	0.315 12	0.686 5	0.451 12	0.714 4	0.543 18	0.504 5	0.894 4	0.823 4	0.688 3

MIX6D_RVC	0.582 10	0.695 4	0.687 14	0.225 18	0.632 6	0.328 10	0.550 1	0.748 5	0.623 5	0.494 13	0.890 11	0.350 12	0.254 20	0.688 4	0.454 10	0.716 3	0.597 14	0.489 8	0.881 5	0.768 13	0.575 12

BPNet_2D	0.670 2	0.822 3	0.795 3	0.836 2	0.659 2	0.481 2	0.451 11	0.769 3	0.656 3	0.567 3	0.931 3	0.395 4	0.390 4	0.700 3	0.534 3	0.689 9	0.770 2	0.574 3	0.865 6	0.831 3	0.675 4
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
DCRedNet	0.583 9	0.682 6	0.723 10	0.542 11	0.510 17	0.310 12	0.451 11	0.668 13	0.549 11	0.520 8	0.920 6	0.375 5	0.446 2	0.528 17	0.417 13	0.670 14	0.577 15	0.478 10	0.862 7	0.806 7	0.628 8

UNIV_CNP_RVC_UE	0.566 12	0.569 16	0.686 16	0.435 15	0.524 14	0.294 16	0.421 16	0.712 9	0.543 12	0.463 15	0.872 14	0.320 14	0.363 7	0.611 8	0.477 9	0.686 10	0.627 9	0.443 15	0.862 7	0.775 11	0.639 5

segfomer with 6d	0.542 16	0.594 12	0.687 14	0.146 21	0.579 10	0.308 13	0.515 5	0.703 10	0.472 18	0.498 11	0.868 15	0.369 7	0.282 15	0.589 12	0.390 14	0.701 8	0.556 17	0.416 18	0.860 9	0.759 15	0.539 16

SN_RN152pyrx8_RVC	0.546 14	0.572 14	0.663 18	0.638 7	0.518 15	0.298 14	0.366 21	0.633 18	0.510 15	0.446 17	0.864 16	0.296 17	0.267 17	0.542 16	0.346 18	0.704 7	0.575 16	0.431 16	0.853 10	0.766 14	0.630 7

EMSAFormer	0.564 13	0.581 13	0.736 8	0.564 10	0.546 13	0.219 20	0.517 4	0.675 11	0.486 17	0.427 19	0.904 9	0.352 11	0.320 11	0.589 12	0.528 4	0.708 6	0.464 21	0.413 19	0.847 11	0.786 8	0.611 10

MCA-Net	0.595 6	0.533 17	0.756 6	0.746 4	0.590 8	0.334 7	0.506 6	0.670 12	0.587 7	0.500 10	0.905 8	0.366 8	0.352 8	0.601 10	0.506 6	0.669 15	0.648 7	0.501 6	0.839 12	0.769 12	0.516 18

CU-Hybrid-2D Net	0.636 3	0.825 2	0.820 2	0.179 20	0.648 3	0.463 3	0.549 2	0.742 6	0.676 2	0.628 2	0.961 1	0.420 2	0.379 5	0.684 6	0.381 15	0.732 2	0.723 3	0.599 2	0.827 13	0.851 2	0.634 6

UDSSEG_RVC	0.545 15	0.610 11	0.661 19	0.588 8	0.556 12	0.268 18	0.482 8	0.642 17	0.572 9	0.475 14	0.836 20	0.312 15	0.367 6	0.630 7	0.189 20	0.639 17	0.495 20	0.452 13	0.826 14	0.756 17	0.541 14

ILC-PSPNet	0.475 21	0.490 20	0.581 21	0.289 17	0.507 18	0.067 23	0.379 19	0.610 20	0.417 21	0.435 18	0.822 22	0.278 18	0.267 17	0.503 19	0.228 19	0.616 20	0.533 19	0.375 20	0.820 15	0.729 18	0.560 13

RFBNet	0.592 7	0.616 9	0.758 5	0.659 5	0.581 9	0.330 8	0.469 10	0.655 15	0.543 12	0.524 7	0.924 4	0.355 10	0.336 10	0.572 14	0.479 8	0.671 13	0.648 7	0.480 9	0.814 16	0.814 5	0.614 9

AdapNet++	0.503 18	0.613 10	0.722 11	0.418 16	0.358 23	0.337 6	0.370 20	0.479 21	0.443 19	0.368 21	0.907 7	0.207 20	0.213 22	0.464 21	0.525 5	0.618 19	0.657 6	0.450 14	0.788 17	0.721 20	0.408 22
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DMMF_3d	0.605 5	0.651 8	0.744 7	0.782 3	0.637 4	0.387 4	0.536 3	0.732 7	0.590 6	0.540 5	0.856 18	0.359 9	0.306 13	0.596 11	0.539 2	0.627 18	0.706 4	0.497 7	0.785 18	0.757 16	0.476 19

FuseNet	0.535 17	0.570 15	0.681 17	0.182 19	0.512 16	0.290 17	0.431 14	0.659 14	0.504 16	0.495 12	0.903 10	0.308 16	0.428 3	0.523 18	0.365 16	0.676 11	0.621 11	0.470 11	0.762 19	0.779 10	0.541 14
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
3DMV (2d proj)	0.498 19	0.481 21	0.612 20	0.579 9	0.456 19	0.343 5	0.384 18	0.623 19	0.525 14	0.381 20	0.845 19	0.254 19	0.264 19	0.557 15	0.182 21	0.581 21	0.598 13	0.429 17	0.760 20	0.661 22	0.446 21
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVC	0.485 20	0.505 19	0.709 13	0.092 22	0.427 20	0.241 19	0.411 17	0.654 16	0.385 23	0.457 16	0.861 17	0.053 23	0.279 16	0.503 19	0.481 7	0.645 16	0.626 10	0.365 21	0.748 21	0.725 19	0.529 17
John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
Enet (reimpl)	0.376 22	0.264 23	0.452 23	0.452 13	0.365 21	0.181 21	0.143 23	0.456 22	0.409 22	0.346 22	0.769 23	0.164 21	0.218 21	0.359 22	0.123 23	0.403 23	0.381 23	0.313 23	0.571 22	0.685 21	0.472 20
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 23	0.293 22	0.521 22	0.657 6	0.361 22	0.161 22	0.250 22	0.004 23	0.440 20	0.183 23	0.836 20	0.125 22	0.060 23	0.319 23	0.132 22	0.417 22	0.412 22	0.344 22	0.541 23	0.427 23	0.109 23
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
DMMF	0.003 24	0.000 24	0.005 24	0.000 24	0.000 24	0.037 24	0.001 24	0.000 24	0.001 24	0.005 24	0.003 24	0.000 24	0.000 24	0.000 24	0.000 24	0.000 24	0.002 24	0.001 24	0.000 24	0.006 24	0.000 24

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

UniDet_RVC	0.205 1	0.381 1	0.323 1	0.037 1	0.226 1	0.177 1	0.063 1	0.277 1	0.120 1	0.067 1	0.131 1	0.074 2	0.317 1	0.080 1	0.235 1	0.289 1	0.141 1	0.678 1	0.080 1

MaskRCNN_ScanNet	0.119 2	0.129 2	0.212 2	0.002 2	0.112 2	0.148 2	0.014 2	0.205 2	0.044 2	0.066 2	0.078 2	0.095 1	0.142 2	0.030 2	0.128 2	0.139 2	0.080 2	0.459 2	0.057 2
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17

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

multi-task	0.700 1	0.500 1	1.000 1	0.882 2	0.500 2	1.000 1	1.000 1	0.500 2	1.000 1	1.000 1	0.778 1	0.000 2	0.938 1	0.000 2
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
3DASPP-SCE	0.691 2	0.500 1	0.938 2	0.824 3	1.000 1	1.000 1	0.500 2	1.000 1	0.857 2	0.500 2	0.556 3	0.000 2	0.812 2	0.500 1

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