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

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.
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

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
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.
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
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
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

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

Method	avg ap 25%	head ap 25%	common ap 25%	tail ap 25%	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	0.445 1	0.653 1	0.392 1	0.254 1	0.648 1	0.097 1	0.125 5	0.000 1	0.000 1	0.000 1	0.657 1	0.971 1	0.451 2	1.000 1	1.000 1	0.640 1	0.500 1	0.045 1	1.000 1	0.241 2	0.409 1	0.363 1	0.440 1	0.686 3	0.300 1	0.000 1	0.201 1	0.000 1	0.009 1	0.290 1	0.556 1	1.000 1	0.000 1	0.063 3	0.000 1	0.830 1	0.573 1	0.844 2	0.333 1	0.204 1	0.058 5	0.158 5	0.552 2	0.056 1	0.000 1	1.000 1	0.725 4	0.750 1	0.927 1	1.000 1	0.888 4	0.042 3	0.120 2	0.615 4	0.226 1	0.250 1	0.890 1	0.792 1	0.677 2	0.510 2	0.818 1	0.699 1	0.512 2	0.167 5	0.125 1	0.315 2	0.943 1	0.309 1	0.017 3	0.200 3	0.000 1	0.188 1	0.000 1	0.183 3	0.815 1	1.000 1	0.827 1	0.741 1	0.442 3	0.414 4	0.600 1	0.000 1	0.000 1	0.458 1	0.049 3	0.321 1	0.381 1	0.000 1	0.908 2	0.400 1	0.841 1	0.260 1	0.710 1	0.966 1	0.265 1	0.000 1	0.924 1	0.152 1	0.025 2	0.500 1	0.027 1	0.028 1	1.000 1	0.556 5	0.016 1	0.080 5	0.500 1	0.694 3	0.608 1	0.084 1	0.604 3	0.194 1	0.538 3	0.000 1	0.500 1	0.000 2	0.354 4	0.000 1	1.000 1	0.000 1	0.761 2	0.930 1	0.053 4	0.890 3	1.000 1	0.008 2	0.262 1	0.358 2	1.000 1	1.000 1	0.792 4	0.966 1	1.000 1	0.765 2	0.004 2	0.930 1	0.780 2	0.330 2	0.027 2	0.625 1	0.974 4	0.050 1	0.412 5	0.021 2	0.000 3	0.000 2	0.778 1	0.000 1	0.000 1	0.493 2	0.746 2	0.454 1	0.335 2	0.396 1	0.930 5	0.551 2	1.000 1	0.552 1	0.606 1	0.853 1	0.000 1	0.004 1	0.806 1	1.000 1	0.727 2	0.000 1	0.042 3	0.745 2	0.000 1	0.399 4	0.391 1	0.630 1	0.721 1	0.619 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TD3D Scannet200	0.379 2	0.603 2	0.306 2	0.190 2	0.635 2	0.073 2	0.500 1	0.000 1	0.000 1	0.000 1	0.495 3	0.735 2	0.275 5	1.000 1	0.979 2	0.590 2	0.000 4	0.021 2	0.000 3	0.146 3	0.000 2	0.356 2	0.173 5	0.795 1	0.226 2	0.000 1	0.173 2	0.000 1	0.000 2	0.226 2	0.390 2	0.000 2	0.000 1	0.250 1	0.000 1	0.706 2	0.061 3	0.885 1	0.093 2	0.186 2	0.259 4	0.200 1	0.667 1	0.000 2	0.000 1	0.667 2	0.825 1	0.250 4	0.834 4	1.000 1	0.958 1	0.553 1	0.111 3	0.748 1	0.220 2	0.051 2	0.866 2	0.792 1	0.390 5	0.045 5	0.800 2	0.302 5	0.517 1	0.533 3	0.113 2	0.427 1	0.843 2	0.000 2	0.458 1	0.600 1	0.000 1	0.101 2	0.000 1	0.259 1	0.717 2	0.500 2	0.615 2	0.520 2	0.526 2	0.457 1	0.270 4	0.000 1	0.000 1	0.400 2	0.088 2	0.294 2	0.181 2	0.000 1	1.000 1	0.400 1	0.710 5	0.103 3	0.477 5	0.905 2	0.061 2	0.000 1	0.906 2	0.102 2	0.232 1	0.125 2	0.000 2	0.003 2	0.792 3	1.000 1	0.000 2	0.102 3	0.125 4	0.559 5	0.523 3	0.075 2	0.715 1	0.000 2	0.424 5	0.000 1	0.396 2	0.250 1	0.638 1	0.000 1	0.000 2	0.000 1	0.622 5	0.833 2	0.221 1	0.970 1	0.250 2	0.038 1	0.260 2	0.415 1	0.125 2	1.000 1	1.000 1	0.857 2	0.000 2	0.908 1	0.012 1	0.869 3	0.836 1	0.635 1	0.111 1	0.625 1	1.000 1	0.020 2	0.510 1	0.003 3	0.009 2	1.000 1	0.778 1	0.000 1	0.000 1	0.370 3	0.755 1	0.288 2	0.333 3	0.274 2	1.000 1	0.557 1	0.731 2	0.456 2	0.433 3	0.769 5	0.000 1	0.000 2	0.621 4	1.000 1	0.458 4	0.000 1	0.196 2	0.817 1	0.000 1	0.472 1	0.222 3	0.205 5	0.689 2	0.274 3

LGround Inst.	0.314 3	0.529 3	0.225 3	0.155 3	0.578 5	0.010 3	0.500 1	0.000 1	0.000 1	0.000 1	0.515 2	0.556 3	0.696 1	1.000 1	0.927 3	0.400 3	0.083 3	0.000 3	1.000 1	0.252 1	0.000 2	0.167 3	0.350 2	0.731 2	0.067 3	0.000 1	0.123 4	0.000 1	0.000 2	0.036 3	0.372 3	0.000 2	0.000 1	0.250 1	0.000 1	0.569 4	0.031 5	0.810 3	0.000 3	0.000 4	0.630 1	0.183 2	0.278 3	0.000 2	0.000 1	0.582 4	0.589 5	0.500 2	0.863 3	1.000 1	0.940 2	0.000 4	0.144 1	0.716 3	0.000 3	0.000 3	0.484 3	0.000 3	0.500 3	0.400 3	0.798 3	0.500 2	0.278 4	0.750 1	0.093 3	0.166 4	0.783 3	0.000 2	0.200 2	0.400 2	0.000 1	0.000 3	0.000 1	0.219 2	0.539 3	0.500 2	0.578 3	0.413 3	0.181 5	0.457 2	0.375 2	0.000 1	0.000 1	0.050 5	0.000 4	0.077 4	0.000 3	0.000 1	0.500 5	0.000 5	0.743 3	0.250 2	0.488 4	0.846 3	0.000 3	0.000 1	0.800 3	0.069 3	0.000 3	0.000 3	0.000 2	0.000 3	1.000 1	0.607 4	0.000 2	0.200 1	0.500 1	0.694 2	0.528 2	0.063 3	0.659 2	0.000 2	0.594 2	0.000 1	0.000 3	0.000 2	0.571 2	0.000 1	0.000 2	0.000 1	0.716 4	0.647 5	0.221 2	0.857 4	0.000 3	0.000 3	0.217 3	0.346 3	0.071 5	0.530 5	1.000 1	0.429 3	0.000 2	0.286 3	0.000 3	0.826 5	0.706 3	0.208 4	0.000 3	0.250 4	0.744 5	0.000 3	0.500 2	0.042 1	0.000 3	0.000 2	0.746 3	0.000 1	0.000 1	0.517 1	0.625 3	0.085 5	0.333 3	0.000 4	1.000 1	0.378 4	0.533 5	0.376 4	0.042 5	0.814 3	0.000 1	0.000 2	0.765 3	1.000 1	0.600 3	0.000 1	0.000 4	0.667 3	0.000 1	0.472 1	0.333 2	0.337 3	0.605 3	0.305 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.	0.280 4	0.488 4	0.192 5	0.124 4	0.593 4	0.010 4	0.500 1	0.000 1	0.000 1	0.000 1	0.447 4	0.535 4	0.445 3	1.000 1	0.861 4	0.400 3	0.225 2	0.000 3	0.000 3	0.142 4	0.000 2	0.074 4	0.342 3	0.467 5	0.067 3	0.000 1	0.119 5	0.000 1	0.000 2	0.000 4	0.337 5	0.000 2	0.000 1	0.000 4	0.000 1	0.506 5	0.070 2	0.804 4	0.000 3	0.000 4	0.333 3	0.172 3	0.150 5	0.000 2	0.000 1	0.479 5	0.745 3	0.000 5	0.830 5	1.000 1	0.904 3	0.167 2	0.090 4	0.732 2	0.000 3	0.000 3	0.443 4	0.000 3	0.500 3	0.542 1	0.772 5	0.396 4	0.077 5	0.385 4	0.044 4	0.118 5	0.777 4	0.000 2	0.000 4	0.200 3	0.000 1	0.000 3	0.000 1	0.148 4	0.502 4	0.500 2	0.419 4	0.159 5	0.281 4	0.404 5	0.317 3	0.000 1	0.000 1	0.200 3	0.000 4	0.077 3	0.000 3	0.000 1	0.750 3	0.200 3	0.715 4	0.021 4	0.551 2	0.828 5	0.000 3	0.000 1	0.743 4	0.059 5	0.000 3	0.000 3	0.000 2	0.000 3	0.125 5	0.648 3	0.000 2	0.191 2	0.500 1	0.669 4	0.502 4	0.000 5	0.568 4	0.000 2	0.516 4	0.000 1	0.000 3	0.000 2	0.305 5	0.000 1	0.000 2	0.000 1	0.825 1	0.833 2	0.021 5	0.918 2	0.000 3	0.000 3	0.191 4	0.346 4	0.100 4	0.981 3	1.000 1	0.286 4	0.000 2	0.000 5	0.000 3	0.868 4	0.648 5	0.292 3	0.000 3	0.375 3	1.000 1	0.000 3	0.500 2	0.000 4	0.333 1	0.000 2	0.538 5	0.000 1	0.000 1	0.213 5	0.518 4	0.098 4	0.528 1	0.250 3	0.997 3	0.284 5	0.677 3	0.398 3	0.167 4	0.790 4	0.000 1	0.000 2	0.618 5	0.903 5	0.200 5	0.000 1	0.333 1	0.333 4	0.000 1	0.442 3	0.083 4	0.213 4	0.587 4	0.131 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.	0.275 5	0.466 5	0.218 4	0.110 5	0.625 3	0.007 5	0.500 1	0.000 1	0.000 1	0.000 1	0.000 5	0.222 5	0.377 4	1.000 1	0.661 5	0.400 3	0.000 4	0.000 3	0.000 3	0.119 5	0.000 2	0.000 5	0.277 4	0.685 4	0.067 3	0.000 1	0.132 3	0.000 1	0.000 2	0.000 4	0.367 4	0.000 2	0.000 1	0.000 4	0.000 1	0.591 3	0.055 4	0.783 5	0.000 3	0.014 3	0.500 2	0.161 4	0.278 3	0.000 2	0.000 1	0.667 2	0.768 2	0.500 2	0.866 2	1.000 1	0.829 5	0.000 4	0.019 5	0.555 5	0.000 3	0.000 3	0.305 5	0.000 3	0.750 1	0.200 4	0.783 4	0.429 3	0.395 3	0.677 2	0.020 5	0.286 3	0.584 5	0.000 2	0.000 4	0.115 5	0.000 1	0.000 3	0.000 1	0.145 5	0.423 5	0.500 2	0.364 5	0.369 4	0.571 1	0.448 3	0.206 5	0.000 1	0.000 1	0.200 3	0.106 1	0.065 5	0.000 3	0.000 1	0.750 3	0.200 3	0.774 2	0.000 5	0.501 3	0.841 4	0.000 3	0.000 1	0.692 5	0.063 4	0.000 3	0.000 3	0.000 2	0.000 3	0.500 4	0.649 2	0.000 2	0.084 4	0.125 4	0.719 1	0.413 5	0.004 4	0.450 5	0.000 2	0.638 1	0.000 1	0.000 3	0.000 2	0.505 3	0.000 1	0.000 2	0.000 1	0.727 3	0.833 2	0.221 2	0.779 5	0.000 3	0.000 3	0.168 5	0.311 5	0.125 2	0.571 4	0.500 5	0.143 5	0.000 2	0.250 4	0.000 3	0.869 2	0.667 4	0.162 5	0.000 3	0.250 4	1.000 1	0.000 3	0.500 2	0.000 4	0.000 3	0.000 2	0.689 4	0.000 1	0.000 1	0.312 4	0.383 5	0.114 3	0.333 3	0.000 4	0.997 3	0.420 3	0.613 4	0.212 5	0.500 2	0.819 2	0.000 1	0.000 2	0.768 2	1.000 1	0.918 1	0.000 1	0.000 4	0.278 5	0.000 1	0.333 5	0.000 5	0.353 2	0.546 5	0.258 4
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

Mix3D	0.781 1	0.964 1	0.855 1	0.843 13	0.781 4	0.858 9	0.575 4	0.831 26	0.685 9	0.714 2	0.979 1	0.594 4	0.310 21	0.801 1	0.892 12	0.841 2	0.819 3	0.723 3	0.940 9	0.887 3	0.725 18
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 2	0.861 17	0.818 12	0.836 16	0.790 2	0.875 2	0.576 3	0.905 3	0.704 3	0.739 1	0.969 7	0.611 1	0.349 7	0.756 16	0.958 1	0.702 37	0.805 12	0.708 6	0.916 25	0.898 1	0.801 1

PPT-SpUNet-Joint	0.766 3	0.932 2	0.794 27	0.829 20	0.751 17	0.854 11	0.540 15	0.903 4	0.630 28	0.672 10	0.963 10	0.565 17	0.357 5	0.788 2	0.900 8	0.737 20	0.802 13	0.685 12	0.950 3	0.887 3	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.
OctFormer	0.766 3	0.925 4	0.808 18	0.849 7	0.786 3	0.846 21	0.566 7	0.876 10	0.690 7	0.674 9	0.960 12	0.576 13	0.226 59	0.753 18	0.904 6	0.777 8	0.815 5	0.722 4	0.923 21	0.877 9	0.776 4
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net	0.764 5	0.924 5	0.819 10	0.840 14	0.757 12	0.853 13	0.580 1	0.848 19	0.709 2	0.643 18	0.958 15	0.587 8	0.295 27	0.753 18	0.884 16	0.758 14	0.815 5	0.725 2	0.927 19	0.867 16	0.743 10

OccuSeg+Semantic	0.764 5	0.758 53	0.796 25	0.839 15	0.746 19	0.907 1	0.562 8	0.850 18	0.680 11	0.672 10	0.978 2	0.610 2	0.335 12	0.777 5	0.819 39	0.847 1	0.830 1	0.691 10	0.972 1	0.885 5	0.727 16

O-CNN	0.762 7	0.924 5	0.823 6	0.844 12	0.770 6	0.852 14	0.577 2	0.847 21	0.711 1	0.640 22	0.958 15	0.592 5	0.217 65	0.762 12	0.888 13	0.758 14	0.813 8	0.726 1	0.932 17	0.868 15	0.744 9
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
OA-CNN-L_ScanNet20	0.756 8	0.783 39	0.826 5	0.858 4	0.776 5	0.837 27	0.548 12	0.896 7	0.649 20	0.675 8	0.962 11	0.586 9	0.335 12	0.771 8	0.802 43	0.770 10	0.787 28	0.691 10	0.936 12	0.880 8	0.761 6

PNE	0.755 9	0.786 37	0.835 4	0.834 18	0.758 10	0.849 17	0.570 6	0.836 25	0.648 21	0.668 12	0.978 2	0.581 12	0.367 3	0.683 28	0.856 25	0.804 3	0.801 17	0.678 14	0.961 2	0.889 2	0.716 23

ConDaFormer	0.755 9	0.927 3	0.822 7	0.836 16	0.801 1	0.849 17	0.516 25	0.864 15	0.651 19	0.680 7	0.958 15	0.584 11	0.282 34	0.759 14	0.855 27	0.728 22	0.802 13	0.678 14	0.880 52	0.873 14	0.756 7
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
PointTransformerV2	0.752 11	0.742 60	0.809 17	0.872 1	0.758 10	0.860 8	0.552 10	0.891 8	0.610 35	0.687 3	0.960 12	0.559 20	0.304 24	0.766 10	0.926 3	0.767 11	0.797 20	0.644 27	0.942 7	0.876 12	0.722 20
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net	0.752 11	0.906 9	0.793 29	0.802 35	0.689 33	0.825 38	0.556 9	0.867 12	0.681 10	0.602 37	0.960 12	0.555 22	0.365 4	0.779 4	0.859 22	0.747 17	0.795 24	0.717 5	0.917 24	0.856 24	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
PointConvFormer	0.749 13	0.793 35	0.790 30	0.807 31	0.750 18	0.856 10	0.524 21	0.881 9	0.588 47	0.642 21	0.977 5	0.591 6	0.274 39	0.781 3	0.929 2	0.804 3	0.796 21	0.642 28	0.947 5	0.885 5	0.715 24
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNet	0.749 13	0.909 7	0.818 12	0.811 28	0.752 15	0.839 26	0.485 40	0.842 22	0.673 12	0.644 17	0.957 19	0.528 31	0.305 23	0.773 7	0.859 22	0.788 5	0.818 4	0.693 9	0.916 25	0.856 24	0.723 19
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 15	0.623 86	0.804 20	0.859 3	0.745 20	0.824 40	0.501 30	0.912 2	0.690 7	0.685 5	0.956 20	0.567 16	0.320 18	0.768 9	0.918 4	0.720 27	0.802 13	0.676 17	0.921 22	0.881 7	0.779 3

StratifiedFormer	0.747 16	0.901 10	0.803 21	0.845 11	0.757 12	0.846 21	0.512 26	0.825 29	0.696 6	0.645 16	0.956 20	0.576 13	0.262 50	0.744 23	0.861 21	0.742 18	0.770 37	0.705 7	0.899 38	0.860 21	0.734 11
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 17	0.870 15	0.838 2	0.858 4	0.729 25	0.850 16	0.501 30	0.874 11	0.587 48	0.658 14	0.956 20	0.564 18	0.299 25	0.765 11	0.900 8	0.716 30	0.812 9	0.631 33	0.939 10	0.858 22	0.709 25
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 17	0.771 47	0.819 10	0.848 9	0.702 31	0.865 7	0.397 77	0.899 5	0.699 4	0.664 13	0.948 48	0.588 7	0.330 14	0.746 22	0.851 31	0.764 12	0.796 21	0.704 8	0.935 13	0.866 17	0.728 14
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
Retro-FPN	0.744 19	0.842 23	0.800 22	0.767 48	0.740 21	0.836 29	0.541 14	0.914 1	0.672 13	0.626 26	0.958 15	0.552 23	0.272 41	0.777 5	0.886 15	0.696 38	0.801 17	0.674 19	0.941 8	0.858 22	0.717 21
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 20	0.620 87	0.799 24	0.849 7	0.730 24	0.822 42	0.493 37	0.897 6	0.664 14	0.681 6	0.955 23	0.562 19	0.378 1	0.760 13	0.903 7	0.738 19	0.801 17	0.673 20	0.907 30	0.877 9	0.745 8
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet	0.742 21	0.816 30	0.806 19	0.807 31	0.752 15	0.828 36	0.575 4	0.839 24	0.699 4	0.637 23	0.954 29	0.520 33	0.320 18	0.755 17	0.834 35	0.760 13	0.772 34	0.676 17	0.915 27	0.862 19	0.717 21

SAT	0.742 21	0.860 18	0.765 42	0.819 23	0.769 7	0.848 19	0.533 17	0.829 27	0.663 15	0.631 25	0.955 23	0.586 9	0.274 39	0.753 18	0.896 10	0.729 21	0.760 44	0.666 22	0.921 22	0.855 26	0.733 12

LargeKernel3D	0.739 23	0.909 7	0.820 9	0.806 33	0.740 21	0.852 14	0.545 13	0.826 28	0.594 46	0.643 18	0.955 23	0.541 25	0.263 49	0.723 26	0.858 24	0.775 9	0.767 38	0.678 14	0.933 15	0.848 31	0.694 30
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN	0.736 24	0.776 43	0.790 30	0.851 6	0.754 14	0.854 11	0.491 39	0.866 13	0.596 45	0.686 4	0.955 23	0.536 26	0.342 9	0.624 43	0.869 18	0.787 6	0.802 13	0.628 34	0.927 19	0.875 13	0.704 27

MinkowskiNet	0.736 24	0.859 19	0.818 12	0.832 19	0.709 29	0.840 25	0.521 23	0.853 17	0.660 17	0.643 18	0.951 38	0.544 24	0.286 32	0.731 24	0.893 11	0.675 46	0.772 34	0.683 13	0.874 58	0.852 29	0.727 16
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA	0.731 26	0.890 11	0.837 3	0.864 2	0.726 26	0.873 3	0.530 20	0.824 30	0.489 79	0.647 15	0.978 2	0.609 3	0.336 11	0.624 43	0.733 52	0.758 14	0.776 32	0.570 58	0.949 4	0.877 9	0.728 14

PointTransformer++	0.725 27	0.727 68	0.811 16	0.819 23	0.765 8	0.841 24	0.502 29	0.814 35	0.621 31	0.623 28	0.955 23	0.556 21	0.284 33	0.620 45	0.866 19	0.781 7	0.757 47	0.648 25	0.932 17	0.862 19	0.709 25

SparseConvNet	0.725 27	0.647 83	0.821 8	0.846 10	0.721 27	0.869 4	0.533 17	0.754 50	0.603 41	0.614 30	0.955 23	0.572 15	0.325 16	0.710 27	0.870 17	0.724 25	0.823 2	0.628 34	0.934 14	0.865 18	0.683 33

MatchingNet	0.724 29	0.812 32	0.812 15	0.810 29	0.735 23	0.834 31	0.495 36	0.860 16	0.572 54	0.602 37	0.954 29	0.512 35	0.280 36	0.757 15	0.845 33	0.725 24	0.780 30	0.606 44	0.937 11	0.851 30	0.700 29

INS-Conv-semantic	0.717 30	0.751 56	0.759 45	0.812 27	0.704 30	0.868 5	0.537 16	0.842 22	0.609 37	0.608 33	0.953 32	0.534 28	0.293 28	0.616 46	0.864 20	0.719 29	0.793 25	0.640 29	0.933 15	0.845 35	0.663 38

PointMetaBase	0.714 31	0.835 24	0.785 32	0.821 21	0.684 35	0.846 21	0.531 19	0.865 14	0.614 32	0.596 41	0.953 32	0.500 38	0.246 55	0.674 29	0.888 13	0.692 39	0.764 40	0.624 36	0.849 73	0.844 36	0.675 35

contrastBoundary	0.705 32	0.769 50	0.775 37	0.809 30	0.687 34	0.820 45	0.439 65	0.812 36	0.661 16	0.591 43	0.945 56	0.515 34	0.171 83	0.633 40	0.856 25	0.720 27	0.796 21	0.668 21	0.889 45	0.847 32	0.689 31
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic	0.703 33	0.774 45	0.800 22	0.793 39	0.760 9	0.847 20	0.471 43	0.802 39	0.463 86	0.634 24	0.968 9	0.491 41	0.271 43	0.726 25	0.910 5	0.706 34	0.815 5	0.551 69	0.878 53	0.833 37	0.570 69

RFCR	0.702 34	0.889 12	0.745 54	0.813 26	0.672 38	0.818 49	0.493 37	0.815 34	0.623 29	0.610 31	0.947 50	0.470 49	0.249 54	0.594 49	0.848 32	0.705 35	0.779 31	0.646 26	0.892 43	0.823 43	0.611 52
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 35	0.825 28	0.796 25	0.723 55	0.716 28	0.832 32	0.433 67	0.816 32	0.634 26	0.609 32	0.969 7	0.418 74	0.344 8	0.559 61	0.833 36	0.715 31	0.808 11	0.560 63	0.902 35	0.847 32	0.680 34

JSENet	0.699 36	0.881 14	0.762 43	0.821 21	0.667 39	0.800 62	0.522 22	0.792 42	0.613 33	0.607 34	0.935 76	0.492 40	0.205 70	0.576 54	0.853 29	0.691 40	0.758 46	0.652 24	0.872 61	0.828 40	0.649 42
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 37	0.743 59	0.794 27	0.655 79	0.684 35	0.822 42	0.497 35	0.719 60	0.622 30	0.617 29	0.977 5	0.447 61	0.339 10	0.750 21	0.664 68	0.703 36	0.790 27	0.596 48	0.946 6	0.855 26	0.647 43
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 38	0.732 64	0.772 38	0.786 40	0.677 37	0.866 6	0.517 24	0.848 19	0.509 71	0.626 26	0.952 36	0.536 26	0.225 61	0.545 67	0.704 59	0.689 43	0.810 10	0.564 62	0.903 34	0.854 28	0.729 13
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNet	0.690 39	0.884 13	0.754 49	0.795 38	0.647 45	0.818 49	0.422 69	0.802 39	0.612 34	0.604 35	0.945 56	0.462 52	0.189 78	0.563 60	0.853 29	0.726 23	0.765 39	0.632 32	0.904 32	0.821 46	0.606 56
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 40	0.704 73	0.741 58	0.754 52	0.656 41	0.829 34	0.501 30	0.741 55	0.609 37	0.548 50	0.950 42	0.522 32	0.371 2	0.633 40	0.756 47	0.715 31	0.771 36	0.623 37	0.861 69	0.814 48	0.658 39
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 41	0.866 16	0.748 51	0.819 23	0.645 47	0.794 65	0.450 54	0.802 39	0.587 48	0.604 35	0.945 56	0.464 51	0.201 73	0.554 63	0.840 34	0.723 26	0.732 56	0.602 46	0.907 30	0.822 45	0.603 59

KP-FCNN	0.684 42	0.847 22	0.758 47	0.784 42	0.647 45	0.814 52	0.473 42	0.772 45	0.605 39	0.594 42	0.935 76	0.450 59	0.181 81	0.587 50	0.805 42	0.690 41	0.785 29	0.614 40	0.882 49	0.819 47	0.632 48
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DGNet	0.684 42	0.712 72	0.784 33	0.782 44	0.658 40	0.835 30	0.499 34	0.823 31	0.641 23	0.597 40	0.950 42	0.487 42	0.281 35	0.575 55	0.619 71	0.647 59	0.764 40	0.620 39	0.871 64	0.846 34	0.688 32

VACNN++	0.684 42	0.728 67	0.757 48	0.776 45	0.690 32	0.804 59	0.464 48	0.816 32	0.577 53	0.587 44	0.945 56	0.508 37	0.276 38	0.671 30	0.710 57	0.663 51	0.750 50	0.589 53	0.881 50	0.832 39	0.653 41

Superpoint Network	0.683 45	0.851 21	0.728 62	0.800 37	0.653 43	0.806 57	0.468 45	0.804 37	0.572 54	0.602 37	0.946 53	0.453 58	0.239 58	0.519 72	0.822 37	0.689 43	0.762 43	0.595 50	0.895 41	0.827 41	0.630 49

PointContrast_LA_SEM	0.683 45	0.757 54	0.784 33	0.786 40	0.639 49	0.824 40	0.408 72	0.775 44	0.604 40	0.541 52	0.934 80	0.532 29	0.269 45	0.552 64	0.777 45	0.645 62	0.793 25	0.640 29	0.913 28	0.824 42	0.671 36

VI-PointConv	0.676 47	0.770 49	0.754 49	0.783 43	0.621 53	0.814 52	0.552 10	0.758 48	0.571 56	0.557 48	0.954 29	0.529 30	0.268 47	0.530 70	0.682 63	0.675 46	0.719 59	0.603 45	0.888 46	0.833 37	0.665 37
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 48	0.789 36	0.748 51	0.763 50	0.635 51	0.814 52	0.407 74	0.747 52	0.581 52	0.573 45	0.950 42	0.484 43	0.271 43	0.607 47	0.754 48	0.649 56	0.774 33	0.596 48	0.883 48	0.823 43	0.606 56

SALANet	0.670 49	0.816 30	0.770 40	0.768 47	0.652 44	0.807 56	0.451 51	0.747 52	0.659 18	0.545 51	0.924 86	0.473 48	0.149 93	0.571 57	0.811 41	0.635 65	0.746 51	0.623 37	0.892 43	0.794 60	0.570 69

PointConv	0.666 50	0.781 40	0.759 45	0.699 64	0.644 48	0.822 42	0.475 41	0.779 43	0.564 59	0.504 68	0.953 32	0.428 68	0.203 72	0.586 52	0.754 48	0.661 52	0.753 48	0.588 54	0.902 35	0.813 50	0.642 44
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNL	0.666 50	0.703 74	0.781 35	0.751 54	0.655 42	0.830 33	0.471 43	0.769 46	0.474 82	0.537 54	0.951 38	0.475 47	0.279 37	0.635 38	0.698 62	0.675 46	0.751 49	0.553 68	0.816 80	0.806 52	0.703 28
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 52	0.746 57	0.708 66	0.722 56	0.638 50	0.820 45	0.451 51	0.566 87	0.599 43	0.541 52	0.950 42	0.510 36	0.313 20	0.648 35	0.819 39	0.616 70	0.682 75	0.590 52	0.869 65	0.810 51	0.656 40
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net	0.658 53	0.778 41	0.702 69	0.806 33	0.619 54	0.813 55	0.468 45	0.693 68	0.494 74	0.524 60	0.941 67	0.449 60	0.298 26	0.510 74	0.821 38	0.675 46	0.727 58	0.568 60	0.826 78	0.803 54	0.637 46
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN	0.656 54	0.698 75	0.743 56	0.650 80	0.564 71	0.820 45	0.505 28	0.758 48	0.631 27	0.479 73	0.945 56	0.480 45	0.226 59	0.572 56	0.774 46	0.690 41	0.735 54	0.614 40	0.853 72	0.776 75	0.597 62
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 55	0.752 55	0.734 60	0.664 77	0.583 66	0.815 51	0.399 76	0.754 50	0.639 24	0.535 56	0.942 65	0.470 49	0.309 22	0.665 31	0.539 77	0.650 55	0.708 64	0.635 31	0.857 71	0.793 62	0.642 44
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 56	0.778 41	0.731 61	0.699 64	0.577 67	0.829 34	0.446 56	0.736 56	0.477 81	0.523 62	0.945 56	0.454 56	0.269 45	0.484 81	0.749 51	0.618 68	0.738 52	0.599 47	0.827 77	0.792 65	0.621 51

MVPNet	0.641 57	0.831 25	0.715 64	0.671 74	0.590 62	0.781 71	0.394 78	0.679 70	0.642 22	0.553 49	0.937 73	0.462 52	0.256 51	0.649 34	0.406 90	0.626 66	0.691 72	0.666 22	0.877 54	0.792 65	0.608 55
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN	0.641 57	0.776 43	0.703 68	0.721 57	0.557 74	0.826 37	0.451 51	0.672 72	0.563 60	0.483 72	0.943 64	0.425 71	0.162 88	0.644 36	0.726 53	0.659 53	0.709 63	0.572 57	0.875 56	0.786 70	0.559 75

PointMRNet	0.640 59	0.717 71	0.701 70	0.692 67	0.576 68	0.801 61	0.467 47	0.716 61	0.563 60	0.459 78	0.953 32	0.429 67	0.169 85	0.581 53	0.854 28	0.605 71	0.710 61	0.550 70	0.894 42	0.793 62	0.575 67

FPConv	0.639 60	0.785 38	0.760 44	0.713 62	0.603 57	0.798 63	0.392 79	0.534 92	0.603 41	0.524 60	0.948 48	0.457 54	0.250 53	0.538 68	0.723 55	0.598 75	0.696 70	0.614 40	0.872 61	0.799 55	0.567 72
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 61	0.797 34	0.769 41	0.641 85	0.590 62	0.820 45	0.461 49	0.537 91	0.637 25	0.536 55	0.947 50	0.388 82	0.206 69	0.656 32	0.668 66	0.647 59	0.732 56	0.585 55	0.868 66	0.793 62	0.473 94

PointSPNet	0.637 62	0.734 63	0.692 77	0.714 61	0.576 68	0.797 64	0.446 56	0.743 54	0.598 44	0.437 83	0.942 65	0.403 78	0.150 92	0.626 42	0.800 44	0.649 56	0.697 69	0.557 66	0.846 74	0.777 74	0.563 73

SConv	0.636 63	0.830 26	0.697 73	0.752 53	0.572 70	0.780 73	0.445 58	0.716 61	0.529 65	0.530 57	0.951 38	0.446 62	0.170 84	0.507 76	0.666 67	0.636 64	0.682 75	0.541 75	0.886 47	0.799 55	0.594 63

Supervoxel-CNN	0.635 64	0.656 81	0.711 65	0.719 58	0.613 55	0.757 82	0.444 61	0.765 47	0.534 64	0.566 46	0.928 84	0.478 46	0.272 41	0.636 37	0.531 79	0.664 50	0.645 85	0.508 83	0.864 68	0.792 65	0.611 52

joint point-based	0.634 65	0.614 88	0.778 36	0.667 76	0.633 52	0.825 38	0.420 70	0.804 37	0.467 84	0.561 47	0.951 38	0.494 39	0.291 29	0.566 58	0.458 85	0.579 82	0.764 40	0.559 65	0.838 75	0.814 48	0.598 61
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 66	0.731 65	0.688 80	0.675 71	0.591 61	0.784 70	0.444 61	0.565 88	0.610 35	0.492 70	0.949 46	0.456 55	0.254 52	0.587 50	0.706 58	0.599 74	0.665 81	0.612 43	0.868 66	0.791 69	0.579 66

3DSM_DMMF	0.631 67	0.626 85	0.745 54	0.801 36	0.607 56	0.751 83	0.506 27	0.729 59	0.565 58	0.491 71	0.866 100	0.434 63	0.197 76	0.595 48	0.630 70	0.709 33	0.705 66	0.560 63	0.875 56	0.740 85	0.491 89

APCF-Net	0.631 67	0.742 60	0.687 82	0.672 72	0.557 74	0.792 68	0.408 72	0.665 73	0.545 62	0.508 65	0.952 36	0.428 68	0.186 79	0.634 39	0.702 60	0.620 67	0.706 65	0.555 67	0.873 59	0.798 57	0.581 65
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN	0.631 67	0.771 47	0.692 77	0.672 72	0.524 79	0.837 27	0.440 64	0.706 66	0.538 63	0.446 80	0.944 62	0.421 73	0.219 64	0.552 64	0.751 50	0.591 78	0.737 53	0.543 74	0.901 37	0.768 77	0.557 76

FusionAwareConv	0.630 70	0.604 90	0.741 58	0.766 49	0.590 62	0.747 84	0.501 30	0.734 57	0.503 73	0.527 58	0.919 90	0.454 56	0.323 17	0.550 66	0.420 89	0.678 45	0.688 73	0.544 72	0.896 40	0.795 59	0.627 50
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 71	0.800 33	0.625 92	0.719 58	0.545 77	0.806 57	0.445 58	0.597 82	0.448 89	0.519 63	0.938 72	0.481 44	0.328 15	0.489 80	0.499 84	0.657 54	0.759 45	0.592 51	0.881 50	0.797 58	0.634 47

SegGroup_sem	0.627 72	0.818 29	0.747 53	0.701 63	0.602 58	0.764 79	0.385 83	0.629 79	0.490 77	0.508 65	0.931 83	0.409 76	0.201 73	0.564 59	0.725 54	0.618 68	0.692 71	0.539 76	0.873 59	0.794 60	0.548 79
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 73	0.830 26	0.694 75	0.757 51	0.563 72	0.772 77	0.448 55	0.647 76	0.520 67	0.509 64	0.949 46	0.431 66	0.191 77	0.496 78	0.614 72	0.647 59	0.672 79	0.535 78	0.876 55	0.783 71	0.571 68

HPEIN	0.618 74	0.729 66	0.668 83	0.647 82	0.597 60	0.766 78	0.414 71	0.680 69	0.520 67	0.525 59	0.946 53	0.432 64	0.215 66	0.493 79	0.599 73	0.638 63	0.617 90	0.570 58	0.897 39	0.806 52	0.605 58
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 75	0.858 20	0.772 38	0.489 97	0.532 78	0.792 68	0.404 75	0.643 78	0.570 57	0.507 67	0.935 76	0.414 75	0.046 102	0.510 74	0.702 60	0.602 73	0.705 66	0.549 71	0.859 70	0.773 76	0.534 82
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 76	0.760 52	0.667 84	0.649 81	0.521 80	0.793 66	0.457 50	0.648 75	0.528 66	0.434 85	0.947 50	0.401 79	0.153 91	0.454 83	0.721 56	0.648 58	0.717 60	0.536 77	0.904 32	0.765 78	0.485 90
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 77	0.634 84	0.743 56	0.697 66	0.601 59	0.781 71	0.437 66	0.585 85	0.493 75	0.446 80	0.933 81	0.394 80	0.011 104	0.654 33	0.661 69	0.603 72	0.733 55	0.526 79	0.832 76	0.761 80	0.480 91

dtc_net	0.596 78	0.683 76	0.725 63	0.715 60	0.549 76	0.803 60	0.444 61	0.647 76	0.493 75	0.495 69	0.941 67	0.409 76	0.000 106	0.424 88	0.544 76	0.598 75	0.703 68	0.522 80	0.912 29	0.792 65	0.520 85

LAP-D	0.594 79	0.720 69	0.692 77	0.637 86	0.456 89	0.773 76	0.391 81	0.730 58	0.587 48	0.445 82	0.940 70	0.381 83	0.288 30	0.434 86	0.453 87	0.591 78	0.649 83	0.581 56	0.777 84	0.749 84	0.610 54

DPC	0.592 80	0.720 69	0.700 71	0.602 90	0.480 85	0.762 81	0.380 84	0.713 64	0.585 51	0.437 83	0.940 70	0.369 85	0.288 30	0.434 86	0.509 83	0.590 80	0.639 88	0.567 61	0.772 85	0.755 82	0.592 64
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 81	0.766 51	0.659 87	0.683 69	0.470 88	0.740 86	0.387 82	0.620 81	0.490 77	0.476 74	0.922 88	0.355 88	0.245 56	0.511 73	0.511 82	0.571 83	0.643 86	0.493 87	0.872 61	0.762 79	0.600 60

ROSMRF	0.580 82	0.772 46	0.707 67	0.681 70	0.563 72	0.764 79	0.362 86	0.515 93	0.465 85	0.465 77	0.936 75	0.427 70	0.207 68	0.438 84	0.577 74	0.536 86	0.675 78	0.486 88	0.723 91	0.779 72	0.524 84

SD-DETR	0.576 83	0.746 57	0.609 96	0.445 101	0.517 81	0.643 97	0.366 85	0.714 63	0.456 87	0.468 76	0.870 99	0.432 64	0.264 48	0.558 62	0.674 64	0.586 81	0.688 73	0.482 89	0.739 89	0.733 87	0.537 81

SQN_0.1%	0.569 84	0.676 78	0.696 74	0.657 78	0.497 82	0.779 74	0.424 68	0.548 89	0.515 69	0.376 90	0.902 97	0.422 72	0.357 5	0.379 91	0.456 86	0.596 77	0.659 82	0.544 72	0.685 94	0.665 98	0.556 77

TextureNet	0.566 85	0.672 80	0.664 85	0.671 74	0.494 83	0.719 87	0.445 58	0.678 71	0.411 95	0.396 88	0.935 76	0.356 87	0.225 61	0.412 89	0.535 78	0.565 84	0.636 89	0.464 91	0.794 83	0.680 95	0.568 71
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 86	0.648 82	0.700 71	0.770 46	0.586 65	0.687 91	0.333 90	0.650 74	0.514 70	0.475 75	0.906 94	0.359 86	0.223 63	0.340 93	0.442 88	0.422 97	0.668 80	0.501 84	0.708 92	0.779 72	0.534 82

Pointnet++ & Feature	0.557 87	0.735 62	0.661 86	0.686 68	0.491 84	0.744 85	0.392 79	0.539 90	0.451 88	0.375 91	0.946 53	0.376 84	0.205 70	0.403 90	0.356 93	0.553 85	0.643 86	0.497 85	0.824 79	0.756 81	0.515 86

GMLPs	0.538 88	0.495 98	0.693 76	0.647 82	0.471 87	0.793 66	0.300 93	0.477 94	0.505 72	0.358 92	0.903 96	0.327 91	0.081 99	0.472 82	0.529 80	0.448 95	0.710 61	0.509 81	0.746 87	0.737 86	0.554 78

PanopticFusion-label	0.529 89	0.491 99	0.688 80	0.604 89	0.386 94	0.632 98	0.225 103	0.705 67	0.434 92	0.293 98	0.815 101	0.348 89	0.241 57	0.499 77	0.669 65	0.507 88	0.649 83	0.442 97	0.796 82	0.602 101	0.561 74
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 90	0.676 78	0.591 99	0.609 87	0.442 90	0.774 75	0.335 89	0.597 82	0.422 94	0.357 93	0.932 82	0.341 90	0.094 98	0.298 95	0.528 81	0.473 93	0.676 77	0.495 86	0.602 100	0.721 90	0.349 101

Online SegFusion	0.515 91	0.607 89	0.644 90	0.579 92	0.434 91	0.630 99	0.353 87	0.628 80	0.440 90	0.410 86	0.762 104	0.307 93	0.167 86	0.520 71	0.403 91	0.516 87	0.565 93	0.447 95	0.678 95	0.701 92	0.514 87
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 92	0.558 94	0.608 97	0.424 103	0.478 86	0.690 90	0.246 99	0.586 84	0.468 83	0.450 79	0.911 92	0.394 80	0.160 89	0.438 84	0.212 100	0.432 96	0.541 98	0.475 90	0.742 88	0.727 88	0.477 92

PCNN	0.498 93	0.559 93	0.644 90	0.560 94	0.420 93	0.711 89	0.229 101	0.414 95	0.436 91	0.352 94	0.941 67	0.324 92	0.155 90	0.238 100	0.387 92	0.493 89	0.529 99	0.509 81	0.813 81	0.751 83	0.504 88

3DMV	0.484 94	0.484 100	0.538 101	0.643 84	0.424 92	0.606 102	0.310 91	0.574 86	0.433 93	0.378 89	0.796 102	0.301 94	0.214 67	0.537 69	0.208 101	0.472 94	0.507 102	0.413 100	0.693 93	0.602 101	0.539 80
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 95	0.577 92	0.611 95	0.356 105	0.321 102	0.715 88	0.299 95	0.376 99	0.328 102	0.319 96	0.944 62	0.285 96	0.164 87	0.216 103	0.229 98	0.484 91	0.545 97	0.456 93	0.755 86	0.709 91	0.475 93
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 96	0.679 77	0.604 98	0.578 93	0.380 95	0.682 92	0.291 96	0.106 105	0.483 80	0.258 103	0.920 89	0.258 100	0.025 103	0.231 102	0.325 94	0.480 92	0.560 95	0.463 92	0.725 90	0.666 97	0.231 105
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 97	0.474 101	0.623 93	0.463 99	0.366 97	0.651 95	0.310 91	0.389 98	0.349 100	0.330 95	0.937 73	0.271 98	0.126 95	0.285 96	0.224 99	0.350 102	0.577 92	0.445 96	0.625 98	0.723 89	0.394 97
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 98	0.548 95	0.548 100	0.597 91	0.363 98	0.628 100	0.300 93	0.292 100	0.374 97	0.307 97	0.881 98	0.268 99	0.186 79	0.238 100	0.204 102	0.407 98	0.506 103	0.449 94	0.667 96	0.620 100	0.462 95

SurfaceConvPF	0.442 98	0.505 97	0.622 94	0.380 104	0.342 100	0.654 94	0.227 102	0.397 97	0.367 98	0.276 100	0.924 86	0.240 101	0.198 75	0.359 92	0.262 96	0.366 99	0.581 91	0.435 98	0.640 97	0.668 96	0.398 96
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutions	0.438 100	0.437 103	0.646 89	0.474 98	0.369 96	0.645 96	0.353 87	0.258 102	0.282 104	0.279 99	0.918 91	0.298 95	0.147 94	0.283 97	0.294 95	0.487 90	0.562 94	0.427 99	0.619 99	0.633 99	0.352 100
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 101	0.525 96	0.647 88	0.522 95	0.324 101	0.488 105	0.077 106	0.712 65	0.353 99	0.401 87	0.636 106	0.281 97	0.176 82	0.340 93	0.565 75	0.175 106	0.551 96	0.398 101	0.370 106	0.602 101	0.361 99

SPLAT Net	0.393 102	0.472 102	0.511 102	0.606 88	0.311 103	0.656 93	0.245 100	0.405 96	0.328 102	0.197 104	0.927 85	0.227 103	0.000 106	0.001 107	0.249 97	0.271 105	0.510 100	0.383 103	0.593 101	0.699 93	0.267 103
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	0.383 103	0.297 105	0.491 103	0.432 102	0.358 99	0.612 101	0.274 97	0.116 104	0.411 95	0.265 101	0.904 95	0.229 102	0.079 100	0.250 98	0.185 103	0.320 103	0.510 100	0.385 102	0.548 102	0.597 104	0.394 97

PointNet++	0.339 104	0.584 91	0.478 104	0.458 100	0.256 105	0.360 106	0.250 98	0.247 103	0.278 105	0.261 102	0.677 105	0.183 104	0.117 96	0.212 104	0.145 105	0.364 100	0.346 106	0.232 106	0.548 102	0.523 105	0.252 104
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNet	0.308 105	0.353 104	0.290 106	0.278 106	0.166 106	0.553 103	0.169 105	0.286 101	0.147 106	0.148 106	0.908 93	0.182 105	0.064 101	0.023 106	0.018 107	0.354 101	0.363 104	0.345 104	0.546 104	0.685 94	0.278 102

ScanNet	0.306 106	0.203 106	0.366 105	0.501 96	0.311 103	0.524 104	0.211 104	0.002 107	0.342 101	0.189 105	0.786 103	0.145 106	0.102 97	0.245 99	0.152 104	0.318 104	0.348 105	0.300 105	0.460 105	0.437 106	0.182 106
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 107	0.000 107	0.041 107	0.172 107	0.030 107	0.062 107	0.001 107	0.035 106	0.004 107	0.051 107	0.143 107	0.019 107	0.003 105	0.041 105	0.050 106	0.003 107	0.054 107	0.018 107	0.005 107	0.264 107	0.082 107

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

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

TD3D	0.875 1	1.000 1	0.976 12	0.877 9	0.783 15	0.970 1	0.889 1	0.828 12	0.945 3	0.803 7	0.713 10	0.720 11	0.709 8	1.000 1	0.936 7	0.934 3	0.873 7	1.000 1	0.791 6

Queryformer	0.874 2	1.000 1	0.978 11	0.809 25	0.876 1	0.936 6	0.702 9	0.716 27	0.920 5	0.875 4	0.766 4	0.772 3	0.818 3	1.000 1	0.995 1	0.916 4	0.892 1	1.000 1	0.767 9

SoftGroup++	0.874 2	1.000 1	0.972 13	0.947 1	0.839 5	0.898 13	0.556 25	0.913 2	0.881 10	0.756 9	0.828 2	0.748 6	0.821 1	1.000 1	0.937 6	0.937 1	0.887 2	1.000 1	0.821 3

Mask3D	0.870 4	1.000 1	0.985 7	0.782 32	0.818 10	0.938 5	0.760 6	0.749 23	0.923 4	0.877 3	0.760 5	0.785 2	0.820 2	1.000 1	0.912 10	0.864 23	0.878 5	0.983 40	0.825 2
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SoftGroup	0.865 5	1.000 1	0.969 14	0.860 12	0.860 2	0.913 9	0.558 22	0.899 3	0.911 6	0.760 8	0.828 1	0.736 8	0.802 5	0.981 30	0.919 9	0.875 14	0.877 6	1.000 1	0.820 4
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
MAFT	0.860 6	1.000 1	0.990 6	0.810 24	0.829 6	0.949 3	0.809 4	0.688 33	0.836 16	0.904 1	0.751 7	0.796 1	0.741 6	1.000 1	0.864 24	0.848 30	0.837 12	1.000 1	0.828 1

IPCA-Inst	0.851 7	1.000 1	0.968 15	0.884 8	0.842 4	0.862 25	0.693 11	0.812 17	0.888 9	0.677 21	0.783 3	0.698 12	0.807 4	1.000 1	0.911 14	0.865 22	0.865 9	1.000 1	0.757 12

SPFormer	0.851 7	1.000 1	0.994 2	0.806 26	0.774 17	0.942 4	0.637 14	0.849 10	0.859 13	0.889 2	0.720 9	0.730 9	0.665 13	1.000 1	0.911 14	0.868 21	0.873 8	1.000 1	0.796 5
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SphereSeg	0.835 9	1.000 1	0.963 18	0.891 6	0.794 12	0.954 2	0.822 3	0.710 28	0.961 2	0.721 13	0.693 16	0.530 32	0.653 15	1.000 1	0.867 23	0.857 26	0.859 10	0.991 37	0.771 8

ISBNet	0.835 9	1.000 1	0.950 20	0.731 40	0.819 8	0.918 7	0.790 5	0.740 24	0.851 15	0.831 5	0.661 18	0.742 7	0.650 16	1.000 1	0.937 5	0.814 42	0.836 13	1.000 1	0.765 10
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
TopoSeg	0.832 11	1.000 1	0.981 9	0.933 2	0.819 9	0.826 33	0.524 31	0.841 11	0.811 20	0.681 20	0.759 6	0.687 13	0.727 7	0.981 30	0.911 14	0.883 10	0.853 11	1.000 1	0.756 13

GraphCut	0.832 11	1.000 1	0.922 33	0.724 42	0.798 11	0.902 12	0.701 10	0.856 8	0.859 12	0.715 14	0.706 11	0.748 5	0.640 27	1.000 1	0.934 8	0.862 24	0.880 3	1.000 1	0.729 15

PBNet	0.825 13	1.000 1	0.963 17	0.837 16	0.843 3	0.865 20	0.822 2	0.647 36	0.878 11	0.733 11	0.639 25	0.683 14	0.650 16	1.000 1	0.853 25	0.870 18	0.820 14	1.000 1	0.744 14
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
SSEC	0.820 14	1.000 1	0.983 8	0.924 3	0.826 7	0.817 36	0.415 40	0.899 4	0.793 24	0.673 22	0.731 8	0.636 19	0.653 14	1.000 1	0.939 4	0.804 44	0.878 4	1.000 1	0.780 7

DKNet	0.815 15	1.000 1	0.930 25	0.844 14	0.765 21	0.915 8	0.534 29	0.805 19	0.805 22	0.807 6	0.654 19	0.763 4	0.650 16	1.000 1	0.794 37	0.881 11	0.766 18	1.000 1	0.758 11
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN	0.806 16	1.000 1	0.992 4	0.789 28	0.723 33	0.891 14	0.650 13	0.810 18	0.832 17	0.665 24	0.699 14	0.658 15	0.700 9	1.000 1	0.881 18	0.832 34	0.774 16	0.997 30	0.613 35
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAIS	0.803 17	1.000 1	0.994 2	0.820 20	0.759 22	0.855 26	0.554 26	0.882 5	0.827 19	0.615 30	0.676 17	0.638 18	0.646 25	1.000 1	0.912 10	0.797 47	0.767 17	0.994 35	0.726 16
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask	0.803 17	1.000 1	0.962 19	0.874 10	0.707 37	0.887 17	0.686 12	0.598 40	0.961 1	0.715 15	0.694 15	0.469 37	0.700 9	1.000 1	0.912 10	0.902 5	0.753 23	0.997 30	0.637 29
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group	0.792 19	1.000 1	0.968 16	0.812 21	0.766 20	0.864 21	0.460 34	0.815 16	0.888 8	0.598 34	0.651 22	0.639 17	0.600 32	0.918 35	0.941 2	0.896 6	0.721 30	1.000 1	0.723 17
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained	0.791 20	1.000 1	0.996 1	0.829 19	0.767 19	0.889 16	0.600 17	0.819 15	0.770 29	0.594 35	0.620 28	0.541 29	0.700 9	1.000 1	0.941 2	0.889 8	0.763 19	1.000 1	0.526 44

SSTNet	0.789 21	1.000 1	0.840 47	0.888 7	0.717 34	0.835 29	0.717 8	0.684 34	0.627 43	0.724 12	0.652 21	0.727 10	0.600 32	1.000 1	0.912 10	0.822 37	0.757 22	1.000 1	0.691 23
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN	0.788 22	1.000 1	0.978 10	0.867 11	0.781 16	0.833 30	0.527 30	0.824 13	0.806 21	0.549 43	0.596 31	0.551 25	0.700 9	1.000 1	0.853 25	0.935 2	0.733 27	1.000 1	0.651 26

DENet	0.786 23	1.000 1	0.929 26	0.736 39	0.750 28	0.720 49	0.755 7	0.934 1	0.794 23	0.590 36	0.561 37	0.537 30	0.650 16	1.000 1	0.882 17	0.804 45	0.789 15	1.000 1	0.719 18

DualGroup	0.782 24	1.000 1	0.927 27	0.811 22	0.772 18	0.853 27	0.631 16	0.805 19	0.773 26	0.613 31	0.611 29	0.610 21	0.650 16	0.835 46	0.881 18	0.879 13	0.750 25	1.000 1	0.675 24

PointGroup	0.778 25	1.000 1	0.900 37	0.798 27	0.715 35	0.863 22	0.493 32	0.706 29	0.895 7	0.569 41	0.701 12	0.576 23	0.639 28	1.000 1	0.880 20	0.851 28	0.719 31	0.997 30	0.709 20
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
PE	0.776 26	1.000 1	0.900 38	0.860 12	0.728 32	0.869 18	0.400 41	0.857 7	0.774 25	0.568 42	0.701 13	0.602 22	0.646 25	0.933 34	0.843 28	0.890 7	0.691 38	0.997 30	0.709 19
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA	0.767 27	1.000 1	0.937 22	0.810 23	0.740 30	0.906 10	0.550 27	0.800 21	0.706 35	0.577 40	0.624 27	0.544 28	0.596 37	0.857 38	0.879 22	0.880 12	0.750 24	0.992 36	0.658 25

DD-UNet+Group	0.764 28	1.000 1	0.897 40	0.837 15	0.753 25	0.830 32	0.459 36	0.824 13	0.699 37	0.629 28	0.653 20	0.438 40	0.650 16	1.000 1	0.880 20	0.858 25	0.690 39	1.000 1	0.650 27
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
INS-Conv-instance	0.762 29	1.000 1	0.923 30	0.765 35	0.785 14	0.905 11	0.600 17	0.655 35	0.646 42	0.683 19	0.647 23	0.530 31	0.650 16	1.000 1	0.824 30	0.830 35	0.693 37	0.944 44	0.644 28

Dyco3D	0.761 30	1.000 1	0.935 23	0.893 5	0.752 27	0.863 23	0.600 17	0.588 41	0.742 32	0.641 26	0.633 26	0.546 27	0.550 39	0.857 38	0.789 39	0.853 27	0.762 20	0.987 38	0.699 21
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance	0.742 31	1.000 1	0.923 30	0.785 29	0.745 29	0.867 19	0.557 23	0.578 44	0.729 33	0.670 23	0.644 24	0.488 35	0.577 38	1.000 1	0.794 37	0.830 35	0.620 47	1.000 1	0.550 40
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg	0.739 32	1.000 1	0.899 39	0.759 37	0.753 26	0.823 34	0.282 45	0.691 32	0.658 40	0.582 39	0.594 32	0.547 26	0.628 30	1.000 1	0.795 36	0.868 20	0.728 29	1.000 1	0.692 22

3D-MPA	0.737 33	1.000 1	0.933 24	0.785 29	0.794 13	0.831 31	0.279 47	0.588 41	0.695 38	0.616 29	0.559 38	0.556 24	0.650 16	1.000 1	0.809 34	0.875 15	0.696 35	1.000 1	0.608 37
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML	0.731 34	1.000 1	0.992 4	0.779 34	0.609 46	0.746 44	0.308 44	0.867 6	0.601 46	0.607 32	0.539 41	0.519 33	0.550 39	1.000 1	0.824 30	0.869 19	0.729 28	1.000 1	0.616 33
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS	0.725 35	1.000 1	0.885 43	0.653 48	0.657 43	0.801 37	0.576 21	0.695 31	0.828 18	0.698 17	0.534 42	0.457 39	0.500 46	0.857 38	0.831 29	0.841 32	0.627 45	1.000 1	0.619 32

SSEN	0.724 36	1.000 1	0.926 28	0.781 33	0.661 41	0.845 28	0.596 20	0.529 47	0.764 31	0.653 25	0.489 48	0.461 38	0.500 46	0.859 37	0.765 40	0.872 17	0.761 21	1.000 1	0.577 38
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF	0.718 37	1.000 1	0.945 21	0.901 4	0.754 24	0.817 35	0.460 34	0.700 30	0.772 27	0.688 18	0.568 36	0.000 58	0.500 46	0.981 30	0.606 49	0.872 16	0.740 26	1.000 1	0.614 34
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Sparse R-CNN	0.714 38	1.000 1	0.926 29	0.694 43	0.699 39	0.890 15	0.636 15	0.516 48	0.693 39	0.743 10	0.588 33	0.369 44	0.601 31	0.594 51	0.800 35	0.886 9	0.676 40	0.986 39	0.546 41

SALoss-ResNet	0.695 39	1.000 1	0.855 45	0.579 53	0.589 48	0.735 47	0.484 33	0.588 41	0.856 14	0.634 27	0.571 35	0.298 45	0.500 46	1.000 1	0.824 30	0.818 38	0.702 34	0.935 49	0.545 42
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
PanopticFusion-inst	0.693 40	1.000 1	0.852 46	0.655 47	0.616 45	0.788 39	0.334 43	0.763 22	0.771 28	0.457 53	0.555 39	0.652 16	0.518 43	0.857 38	0.765 40	0.732 53	0.631 43	0.944 44	0.577 39
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Occipital-SCS	0.688 41	1.000 1	0.913 34	0.730 41	0.737 31	0.743 46	0.442 37	0.855 9	0.655 41	0.546 44	0.546 40	0.263 47	0.508 45	0.889 36	0.568 50	0.771 50	0.705 33	0.889 52	0.625 31

3D-BoNet	0.687 42	1.000 1	0.887 42	0.836 17	0.587 49	0.643 56	0.550 27	0.620 37	0.724 34	0.522 48	0.501 46	0.243 48	0.512 44	1.000 1	0.751 42	0.807 43	0.661 42	0.909 51	0.612 36
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
ClickSeg_Instance	0.685 43	1.000 1	0.818 49	0.600 51	0.715 36	0.795 38	0.557 23	0.533 46	0.591 48	0.601 33	0.519 44	0.429 42	0.638 29	0.938 33	0.706 44	0.817 40	0.624 46	0.944 44	0.502 46

PCJC	0.684 44	1.000 1	0.895 41	0.757 38	0.659 42	0.862 24	0.189 54	0.739 25	0.606 45	0.712 16	0.581 34	0.515 34	0.650 16	0.857 38	0.357 55	0.785 48	0.631 44	0.889 52	0.635 30

SPG_WSIS	0.678 45	1.000 1	0.880 44	0.836 17	0.701 38	0.727 48	0.273 49	0.607 39	0.706 36	0.541 46	0.515 45	0.174 50	0.600 32	0.857 38	0.716 43	0.846 31	0.711 32	1.000 1	0.506 45

One_Thing_One_Click	0.675 46	1.000 1	0.823 48	0.782 31	0.621 44	0.766 41	0.211 51	0.736 26	0.560 50	0.586 37	0.522 43	0.636 20	0.453 50	0.641 50	0.853 25	0.850 29	0.694 36	0.997 30	0.411 50
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_ins	0.637 47	1.000 1	0.923 32	0.593 52	0.561 50	0.746 45	0.143 56	0.504 49	0.766 30	0.485 51	0.442 49	0.372 43	0.530 42	0.714 47	0.815 33	0.775 49	0.673 41	1.000 1	0.431 49
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASC	0.615 48	0.711 54	0.802 50	0.540 54	0.757 23	0.777 40	0.029 57	0.577 45	0.588 49	0.521 49	0.600 30	0.436 41	0.534 41	0.697 48	0.616 48	0.838 33	0.526 49	0.980 41	0.534 43
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone	0.605 49	1.000 1	0.909 35	0.764 36	0.603 47	0.704 50	0.415 39	0.301 54	0.548 51	0.461 52	0.394 50	0.267 46	0.386 52	0.857 38	0.649 47	0.817 39	0.504 50	0.959 42	0.356 53

3D-SIS	0.558 50	1.000 1	0.773 51	0.614 50	0.503 52	0.691 52	0.200 52	0.412 50	0.498 54	0.546 45	0.311 55	0.103 54	0.600 32	0.857 38	0.382 52	0.799 46	0.445 56	0.938 48	0.371 51
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet	0.544 51	0.500 57	0.655 57	0.661 46	0.663 40	0.765 42	0.432 38	0.214 56	0.612 44	0.584 38	0.499 47	0.204 49	0.286 56	0.429 54	0.655 46	0.650 58	0.539 48	0.950 43	0.499 47

Hier3D	0.540 52	1.000 1	0.727 52	0.626 49	0.467 55	0.693 51	0.200 52	0.412 50	0.480 55	0.528 47	0.318 54	0.077 57	0.600 32	0.688 49	0.382 52	0.768 51	0.472 52	0.941 47	0.350 54
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class	0.497 53	0.250 59	0.902 36	0.689 44	0.540 51	0.747 43	0.276 48	0.610 38	0.268 58	0.489 50	0.348 51	0.000 58	0.243 58	0.220 57	0.663 45	0.814 41	0.459 54	0.928 50	0.496 48

tmp	0.474 54	1.000 1	0.727 52	0.433 57	0.481 54	0.673 54	0.022 59	0.380 52	0.517 53	0.436 55	0.338 53	0.128 52	0.343 54	0.429 54	0.291 57	0.728 54	0.473 51	0.833 55	0.300 56

SemRegionNet-20cls	0.470 55	1.000 1	0.727 52	0.447 56	0.481 53	0.678 53	0.024 58	0.380 52	0.518 52	0.440 54	0.339 52	0.128 52	0.350 53	0.429 54	0.212 58	0.711 55	0.465 53	0.833 55	0.290 57

ASIS	0.422 56	0.333 58	0.707 55	0.676 45	0.401 56	0.650 55	0.350 42	0.177 57	0.594 47	0.376 56	0.202 56	0.077 56	0.404 51	0.571 52	0.197 59	0.674 57	0.447 55	0.500 58	0.260 58

3D-BEVIS	0.401 57	0.667 55	0.687 56	0.419 58	0.137 59	0.587 57	0.188 55	0.235 55	0.359 57	0.211 58	0.093 59	0.080 55	0.311 55	0.571 52	0.382 52	0.754 52	0.300 58	0.874 54	0.357 52
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet	0.390 58	0.556 56	0.636 58	0.493 55	0.353 57	0.539 58	0.271 50	0.160 58	0.450 56	0.359 57	0.178 57	0.146 51	0.250 57	0.143 58	0.347 56	0.698 56	0.436 57	0.667 57	0.331 55

MaskRCNN 2d->3d Proj	0.261 59	0.903 53	0.081 59	0.008 59	0.233 58	0.175 59	0.280 46	0.106 59	0.150 59	0.203 59	0.175 58	0.480 36	0.218 59	0.143 58	0.542 51	0.404 59	0.153 59	0.393 59	0.049 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
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)
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

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

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

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

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

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

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

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

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
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

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

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

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

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

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
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
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
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

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

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

Presenting the ScanNet200 Benchmark

ScanNet200 Benchmark

ScanNet200 3D Semantic Label Benchmark

ScanNet200 3D Semantic Instance Benchmark

ScanNet Benchmark

3D Semantic Label Benchmark

3D Semantic Instance Benchmark

2D Semantic Label Benchmark

2D Semantic Instance Benchmark

Scene Type Classification Benchmark

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

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