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

Minkowski 34D	0.253 4	0.463 4	0.154 5	0.102 4	0.381 5	0.084 1	0.134 5	0.000 1	0.000 1	0.000 1	0.386 4	0.141 5	0.279 5	0.737 5	0.703 4	0.014 5	0.164 3	0.000 3	0.663 1	0.092 4	0.000 3	0.224 4	0.291 1	0.531 2	0.056 5	0.000 3	0.242 4	0.000 1	0.000 2	0.013 3	0.331 4	0.000 3	0.000 1	0.035 5	0.001 1	0.858 3	0.059 5	0.650 4	0.000 3	0.056 4	0.353 4	0.299 3	0.670 4	0.000 1	0.000 1	0.284 4	0.484 4	0.071 3	0.594 4	0.720 4	0.710 4	0.027 5	0.068 5	0.813 2	0.000 1	0.005 1	0.492 3	0.164 1	0.274 4	0.111 5	0.571 4	0.307 5	0.293 3	0.307 5	0.150 2	0.163 5	0.531 4	0.002 1	0.545 1	0.932 3	0.093 5	0.000 1	0.000 3	0.002 3	0.159 3	0.368 5	0.581 4	0.440 5	0.228 5	0.406 2	0.282 5	0.294 4	0.000 1	0.000 1	0.189 4	0.060 1	0.036 3	0.000 3	0.000 2	0.897 2	0.000 5	0.525 4	0.025 5	0.205 5	0.771 5	0.000 3	0.000 1	0.593 4	0.108 4	0.044 3	0.000 3	0.000 1	0.000 1	0.282 5	0.589 4	0.094 4	0.169 4	0.466 5	0.227 5	0.419 5	0.125 3	0.757 2	0.002 1	0.334 4	0.000 1	0.000 2	0.000 1	0.357 3	0.000 1	0.000 2	0.000 1	0.582 3	0.513 5	0.337 2	0.612 5	0.000 2	0.000 1	0.250 4	0.352 5	0.136 5	0.724 4	0.655 1	0.280 2	0.000 3	0.046 5	0.000 1	0.606 5	0.559 3	0.159 2	0.102 1	0.445 1	0.655 1	0.000 1	0.310 5	0.117 1	0.000 3	0.000 1	0.581 5	0.026 1	0.000 1	0.265 5	0.483 4	0.084 5	0.097 5	0.044 3	0.865 5	0.142 5	0.588 2	0.351 3	0.272 2	0.596 5	0.000 1	0.003 2	0.622 4	0.720 2	0.096 5	0.000 1	0.771 4	0.016 4	0.772 3	0.000 1	0.302 3	0.194 2	0.214 4	0.621 4	0.197 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CeCo	0.340 1	0.551 1	0.247 1	0.181 1	0.475 2	0.057 5	0.142 4	0.000 1	0.000 1	0.000 1	0.387 3	0.463 2	0.499 3	0.924 1	0.774 1	0.213 1	0.257 1	0.000 3	0.546 5	0.100 2	0.006 2	0.615 1	0.177 5	0.534 1	0.246 1	0.000 3	0.400 1	0.000 1	0.338 1	0.006 4	0.484 1	0.609 1	0.000 1	0.083 1	0.000 2	0.873 1	0.089 3	0.661 2	0.000 3	0.048 5	0.560 1	0.408 1	0.892 1	0.000 1	0.000 1	0.586 1	0.616 2	0.000 5	0.692 3	0.900 1	0.721 1	0.162 1	0.228 1	0.860 1	0.000 1	0.000 2	0.575 1	0.083 2	0.550 1	0.347 1	0.624 1	0.410 2	0.360 1	0.740 1	0.109 3	0.321 3	0.660 1	0.000 2	0.121 2	0.939 1	0.143 2	0.000 1	0.400 1	0.003 2	0.190 1	0.564 1	0.652 1	0.615 1	0.421 1	0.304 4	0.579 1	0.547 1	0.000 1	0.000 1	0.296 2	0.000 5	0.030 4	0.096 1	0.000 2	0.916 1	0.037 2	0.551 2	0.171 2	0.376 1	0.865 2	0.286 1	0.000 1	0.633 1	0.102 5	0.027 4	0.011 2	0.000 1	0.000 1	0.474 3	0.742 1	0.133 2	0.311 1	0.824 1	0.242 2	0.503 2	0.068 4	0.828 1	0.000 2	0.429 1	0.000 1	0.063 1	0.000 1	0.781 1	0.000 1	0.000 2	0.000 1	0.665 1	0.633 1	0.450 1	0.818 1	0.000 2	0.000 1	0.429 1	0.532 1	0.226 1	0.825 1	0.510 4	0.377 1	0.709 1	0.079 3	0.000 1	0.753 1	0.683 1	0.102 5	0.063 2	0.401 4	0.620 3	0.000 1	0.619 1	0.000 5	0.000 3	0.000 1	0.595 3	0.000 2	0.000 1	0.345 2	0.564 1	0.411 1	0.603 1	0.384 2	0.945 1	0.266 1	0.643 1	0.367 2	0.304 1	0.663 1	0.000 1	0.010 1	0.726 3	0.767 1	0.898 1	0.000 1	0.784 1	0.435 1	0.861 2	0.000 1	0.447 1	0.000 5	0.257 1	0.656 1	0.377 4
: Understanding Imbalanced Semantic Segmentation Through Neural Collapse.
LGround	0.272 3	0.485 3	0.184 3	0.106 3	0.476 1	0.077 2	0.218 1	0.000 1	0.000 1	0.000 1	0.547 1	0.295 3	0.540 1	0.746 4	0.745 3	0.058 4	0.112 4	0.005 1	0.658 2	0.077 5	0.000 3	0.322 3	0.178 4	0.512 3	0.190 2	0.199 1	0.277 3	0.000 1	0.000 2	0.173 1	0.399 2	0.000 3	0.000 1	0.039 4	0.000 2	0.858 3	0.085 4	0.676 1	0.002 1	0.103 1	0.498 2	0.323 2	0.703 3	0.000 1	0.000 1	0.296 3	0.549 3	0.216 1	0.702 2	0.768 3	0.718 3	0.028 4	0.092 4	0.786 4	0.000 1	0.000 2	0.453 4	0.022 3	0.251 5	0.252 2	0.572 3	0.348 3	0.321 2	0.514 2	0.063 4	0.279 4	0.552 3	0.000 2	0.019 4	0.932 3	0.132 4	0.000 1	0.000 3	0.000 4	0.156 5	0.457 3	0.623 2	0.518 2	0.265 4	0.358 3	0.381 3	0.395 3	0.000 1	0.000 1	0.127 5	0.012 3	0.051 1	0.000 3	0.000 2	0.886 4	0.014 3	0.437 5	0.179 1	0.244 3	0.826 3	0.000 3	0.000 1	0.599 3	0.136 1	0.085 2	0.000 3	0.000 1	0.000 1	0.565 2	0.612 3	0.143 1	0.207 3	0.566 3	0.232 4	0.446 3	0.127 2	0.708 3	0.000 2	0.384 3	0.000 1	0.000 2	0.000 1	0.402 2	0.000 1	0.059 1	0.000 1	0.525 5	0.566 3	0.229 3	0.659 3	0.000 2	0.000 1	0.265 3	0.446 2	0.147 4	0.720 5	0.597 2	0.066 4	0.000 3	0.187 1	0.000 1	0.726 2	0.467 5	0.134 4	0.000 4	0.413 3	0.629 2	0.000 1	0.363 4	0.055 3	0.022 2	0.000 1	0.626 2	0.000 2	0.000 1	0.323 3	0.479 5	0.154 4	0.117 3	0.028 4	0.901 3	0.243 3	0.415 5	0.295 5	0.143 4	0.610 4	0.000 1	0.000 3	0.777 2	0.397 5	0.324 4	0.000 1	0.778 3	0.179 3	0.702 4	0.000 1	0.274 5	0.404 1	0.233 2	0.622 3	0.398 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrain	0.249 5	0.455 5	0.171 4	0.079 5	0.418 4	0.059 4	0.186 3	0.000 1	0.000 1	0.000 1	0.335 5	0.250 4	0.316 4	0.766 3	0.697 5	0.142 2	0.170 2	0.003 2	0.553 4	0.112 1	0.097 1	0.201 5	0.186 2	0.476 5	0.081 4	0.000 3	0.216 5	0.000 1	0.000 2	0.001 5	0.314 5	0.000 3	0.000 1	0.055 3	0.000 2	0.832 5	0.094 1	0.659 3	0.002 1	0.076 2	0.310 5	0.293 5	0.664 5	0.000 1	0.000 1	0.175 5	0.634 1	0.130 2	0.552 5	0.686 5	0.700 5	0.076 3	0.110 3	0.770 5	0.000 1	0.000 2	0.430 5	0.000 5	0.319 3	0.166 4	0.542 5	0.327 4	0.205 4	0.332 4	0.052 5	0.375 1	0.444 5	0.000 2	0.012 5	0.930 5	0.203 1	0.000 1	0.000 3	0.046 1	0.175 2	0.413 4	0.592 3	0.471 4	0.299 3	0.152 5	0.340 4	0.247 5	0.000 1	0.000 1	0.225 3	0.058 2	0.037 2	0.000 3	0.207 1	0.862 5	0.014 3	0.548 3	0.033 4	0.233 4	0.816 4	0.000 3	0.000 1	0.542 5	0.123 2	0.121 1	0.019 1	0.000 1	0.000 1	0.463 4	0.454 5	0.045 5	0.128 5	0.557 4	0.235 3	0.441 4	0.063 5	0.484 5	0.000 2	0.308 5	0.000 1	0.000 2	0.000 1	0.318 5	0.000 1	0.000 2	0.000 1	0.545 4	0.543 4	0.164 5	0.734 2	0.000 2	0.000 1	0.215 5	0.371 4	0.198 2	0.743 2	0.205 5	0.062 5	0.000 3	0.079 3	0.000 1	0.683 4	0.547 4	0.142 3	0.000 4	0.441 2	0.579 5	0.000 1	0.464 3	0.098 2	0.041 1	0.000 1	0.590 4	0.000 2	0.000 1	0.373 1	0.494 2	0.174 3	0.105 4	0.001 5	0.895 4	0.222 4	0.537 3	0.307 4	0.180 3	0.625 2	0.000 1	0.000 3	0.591 5	0.609 4	0.398 3	0.000 1	0.766 5	0.014 5	0.638 5	0.000 1	0.377 2	0.004 4	0.206 5	0.609 5	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 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 10	0.781 1	0.858 7	0.575 3	0.831 19	0.685 7	0.714 1	0.979 1	0.594 3	0.310 17	0.801 1	0.892 8	0.841 2	0.819 3	0.723 3	0.940 8	0.887 1	0.725 12
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
OccuSeg+Semantic	0.764 2	0.758 46	0.796 20	0.839 12	0.746 11	0.907 1	0.562 5	0.850 13	0.680 9	0.672 5	0.978 2	0.610 1	0.335 8	0.777 4	0.819 32	0.847 1	0.830 1	0.691 8	0.972 1	0.885 2	0.727 10

CU-Hybrid Net	0.764 2	0.924 2	0.819 8	0.840 11	0.757 6	0.853 9	0.580 1	0.848 14	0.709 2	0.643 12	0.958 10	0.587 7	0.295 23	0.753 14	0.884 12	0.758 11	0.815 6	0.725 2	0.927 17	0.867 10	0.743 5

O-CNN	0.762 4	0.924 2	0.823 5	0.844 9	0.770 2	0.852 10	0.577 2	0.847 15	0.711 1	0.640 16	0.958 10	0.592 4	0.217 58	0.762 10	0.888 9	0.758 11	0.813 7	0.726 1	0.932 15	0.868 9	0.744 4
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
PointTransformerV2	0.752 5	0.742 53	0.809 14	0.872 1	0.758 5	0.860 6	0.552 7	0.891 5	0.610 30	0.687 2	0.960 8	0.559 14	0.304 20	0.766 8	0.926 2	0.767 8	0.797 14	0.644 22	0.942 6	0.876 7	0.722 14
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 5	0.906 6	0.793 23	0.802 29	0.689 27	0.825 31	0.556 6	0.867 9	0.681 8	0.602 30	0.960 8	0.555 16	0.365 3	0.779 3	0.859 17	0.747 14	0.795 18	0.717 4	0.917 20	0.856 18	0.764 2

PointConvFormer	0.749 7	0.793 32	0.790 24	0.807 24	0.750 10	0.856 8	0.524 16	0.881 7	0.588 41	0.642 15	0.977 4	0.591 5	0.274 34	0.781 2	0.929 1	0.804 3	0.796 15	0.642 23	0.947 3	0.885 2	0.715 17
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNet	0.749 7	0.909 4	0.818 10	0.811 21	0.752 8	0.839 19	0.485 32	0.842 16	0.673 10	0.644 11	0.957 13	0.528 25	0.305 19	0.773 6	0.859 17	0.788 4	0.818 5	0.693 7	0.916 21	0.856 18	0.723 13
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 9	0.623 79	0.804 16	0.859 3	0.745 12	0.824 33	0.501 23	0.912 2	0.690 6	0.685 3	0.956 14	0.567 11	0.320 13	0.768 7	0.918 3	0.720 22	0.802 10	0.676 12	0.921 18	0.881 4	0.779 1

StratifiedFormer	0.747 10	0.901 7	0.803 17	0.845 8	0.757 6	0.846 14	0.512 19	0.825 22	0.696 5	0.645 10	0.956 14	0.576 9	0.262 44	0.744 18	0.861 16	0.742 15	0.770 30	0.705 5	0.899 33	0.860 15	0.734 6
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 11	0.870 12	0.838 2	0.858 4	0.729 17	0.850 12	0.501 23	0.874 8	0.587 42	0.658 8	0.956 14	0.564 12	0.299 21	0.765 9	0.900 5	0.716 25	0.812 8	0.631 28	0.939 9	0.858 16	0.709 18
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 11	0.771 40	0.819 8	0.848 6	0.702 25	0.865 5	0.397 70	0.899 3	0.699 3	0.664 7	0.948 41	0.588 6	0.330 9	0.746 17	0.851 24	0.764 9	0.796 15	0.704 6	0.935 11	0.866 11	0.728 8
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 13	0.842 19	0.800 18	0.767 41	0.740 13	0.836 22	0.541 10	0.914 1	0.672 11	0.626 19	0.958 10	0.552 17	0.272 36	0.777 4	0.886 11	0.696 32	0.801 11	0.674 14	0.941 7	0.858 16	0.717 15

EQ-Net	0.743 14	0.620 80	0.799 19	0.849 5	0.730 16	0.822 35	0.493 30	0.897 4	0.664 12	0.681 4	0.955 18	0.562 13	0.378 1	0.760 11	0.903 4	0.738 16	0.801 11	0.673 15	0.907 26	0.877 5	0.745 3
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet	0.742 15	0.816 27	0.806 15	0.807 24	0.752 8	0.828 29	0.575 3	0.839 18	0.699 3	0.637 17	0.954 23	0.520 27	0.320 13	0.755 13	0.834 28	0.760 10	0.772 27	0.676 12	0.915 22	0.862 13	0.717 15

SAT	0.742 15	0.860 14	0.765 35	0.819 16	0.769 3	0.848 13	0.533 12	0.829 20	0.663 13	0.631 18	0.955 18	0.586 8	0.274 34	0.753 14	0.896 6	0.729 17	0.760 37	0.666 17	0.921 18	0.855 20	0.733 7

TXC	0.740 17	0.842 19	0.832 4	0.805 28	0.715 21	0.846 14	0.473 34	0.885 6	0.615 26	0.671 6	0.971 6	0.547 18	0.320 13	0.697 22	0.799 37	0.777 6	0.819 3	0.682 10	0.946 4	0.871 8	0.696 23

LargeKernel3D	0.739 18	0.909 4	0.820 7	0.806 26	0.740 13	0.852 10	0.545 9	0.826 21	0.594 40	0.643 12	0.955 18	0.541 20	0.263 43	0.723 20	0.858 19	0.775 7	0.767 31	0.678 11	0.933 13	0.848 24	0.694 24

MinkowskiNet	0.736 19	0.859 15	0.818 10	0.832 13	0.709 22	0.840 18	0.521 18	0.853 12	0.660 15	0.643 12	0.951 31	0.544 19	0.286 28	0.731 19	0.893 7	0.675 39	0.772 27	0.683 9	0.874 51	0.852 22	0.727 10
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA	0.731 20	0.890 8	0.837 3	0.864 2	0.726 18	0.873 2	0.530 15	0.824 23	0.489 73	0.647 9	0.978 2	0.609 2	0.336 7	0.624 37	0.733 46	0.758 11	0.776 25	0.570 53	0.949 2	0.877 5	0.728 8

SparseConvNet	0.725 21	0.647 76	0.821 6	0.846 7	0.721 19	0.869 3	0.533 12	0.754 43	0.603 36	0.614 23	0.955 18	0.572 10	0.325 11	0.710 21	0.870 13	0.724 20	0.823 2	0.628 29	0.934 12	0.865 12	0.683 27

PointTransformer++	0.725 21	0.727 60	0.811 13	0.819 16	0.765 4	0.841 17	0.502 22	0.814 29	0.621 25	0.623 20	0.955 18	0.556 15	0.284 29	0.620 38	0.866 14	0.781 5	0.757 40	0.648 20	0.932 15	0.862 13	0.709 18

MatchingNet	0.724 23	0.812 29	0.812 12	0.810 22	0.735 15	0.834 24	0.495 29	0.860 11	0.572 48	0.602 30	0.954 23	0.512 29	0.280 31	0.757 12	0.845 26	0.725 19	0.780 23	0.606 39	0.937 10	0.851 23	0.700 21

INS-Conv-semantic	0.717 24	0.751 49	0.759 38	0.812 20	0.704 24	0.868 4	0.537 11	0.842 16	0.609 32	0.608 26	0.953 26	0.534 21	0.293 24	0.616 39	0.864 15	0.719 24	0.793 19	0.640 24	0.933 13	0.845 29	0.663 32

PointMetaBase	0.714 25	0.835 21	0.785 26	0.821 14	0.684 29	0.846 14	0.531 14	0.865 10	0.614 27	0.596 34	0.953 26	0.500 32	0.246 50	0.674 23	0.888 9	0.692 33	0.764 33	0.624 30	0.849 66	0.844 30	0.675 29

contrastBoundary	0.705 26	0.769 43	0.775 31	0.809 23	0.687 28	0.820 38	0.439 58	0.812 30	0.661 14	0.591 36	0.945 49	0.515 28	0.171 76	0.633 34	0.856 20	0.720 22	0.796 15	0.668 16	0.889 40	0.847 26	0.689 25
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RFCR	0.702 27	0.889 9	0.745 47	0.813 19	0.672 31	0.818 42	0.493 30	0.815 27	0.623 23	0.610 24	0.947 43	0.470 42	0.249 49	0.594 42	0.848 25	0.705 29	0.779 24	0.646 21	0.892 38	0.823 36	0.611 46
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 28	0.825 25	0.796 20	0.723 48	0.716 20	0.832 25	0.433 60	0.816 25	0.634 21	0.609 25	0.969 7	0.418 67	0.344 5	0.559 54	0.833 29	0.715 26	0.808 9	0.560 57	0.902 30	0.847 26	0.680 28

JSENet	0.699 29	0.881 11	0.762 36	0.821 14	0.667 32	0.800 55	0.522 17	0.792 35	0.613 28	0.607 27	0.935 69	0.492 34	0.205 63	0.576 47	0.853 22	0.691 34	0.758 39	0.652 19	0.872 54	0.828 33	0.649 36
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
PicassoNet-II	0.696 30	0.704 65	0.790 24	0.787 33	0.709 22	0.837 20	0.459 42	0.815 27	0.543 57	0.615 22	0.956 14	0.529 23	0.250 47	0.551 59	0.790 38	0.703 30	0.799 13	0.619 34	0.908 25	0.848 24	0.700 21
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One-Thing-One-Click	0.693 31	0.743 52	0.794 22	0.655 72	0.684 29	0.822 35	0.497 28	0.719 53	0.622 24	0.617 21	0.977 4	0.447 54	0.339 6	0.750 16	0.664 61	0.703 30	0.790 21	0.596 43	0.946 4	0.855 20	0.647 37
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Feature_GeometricNet	0.690 32	0.884 10	0.754 42	0.795 32	0.647 38	0.818 42	0.422 62	0.802 33	0.612 29	0.604 28	0.945 49	0.462 45	0.189 71	0.563 53	0.853 22	0.726 18	0.765 32	0.632 27	0.904 28	0.821 39	0.606 50
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 33	0.704 65	0.741 51	0.754 45	0.656 34	0.829 27	0.501 23	0.741 48	0.609 32	0.548 43	0.950 35	0.522 26	0.371 2	0.633 34	0.756 41	0.715 26	0.771 29	0.623 31	0.861 62	0.814 41	0.658 33
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 34	0.866 13	0.748 44	0.819 16	0.645 40	0.794 58	0.450 47	0.802 33	0.587 42	0.604 28	0.945 49	0.464 44	0.201 66	0.554 56	0.840 27	0.723 21	0.732 49	0.602 41	0.907 26	0.822 38	0.603 53

KP-FCNN	0.684 35	0.847 18	0.758 40	0.784 35	0.647 38	0.814 45	0.473 34	0.772 38	0.605 34	0.594 35	0.935 69	0.450 52	0.181 74	0.587 43	0.805 35	0.690 35	0.785 22	0.614 35	0.882 44	0.819 40	0.632 42
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 35	0.712 64	0.784 27	0.782 37	0.658 33	0.835 23	0.499 27	0.823 24	0.641 18	0.597 33	0.950 35	0.487 35	0.281 30	0.575 48	0.619 64	0.647 52	0.764 33	0.620 33	0.871 57	0.846 28	0.688 26

VACNN++	0.684 35	0.728 59	0.757 41	0.776 38	0.690 26	0.804 52	0.464 40	0.816 25	0.577 47	0.587 37	0.945 49	0.508 31	0.276 33	0.671 24	0.710 51	0.663 44	0.750 43	0.589 48	0.881 45	0.832 32	0.653 35

Superpoint Network	0.683 38	0.851 17	0.728 55	0.800 31	0.653 36	0.806 50	0.468 37	0.804 31	0.572 48	0.602 30	0.946 46	0.453 51	0.239 53	0.519 65	0.822 30	0.689 37	0.762 36	0.595 45	0.895 36	0.827 34	0.630 43

PointContrast_LA_SEM	0.683 38	0.757 47	0.784 27	0.786 34	0.639 42	0.824 33	0.408 65	0.775 37	0.604 35	0.541 45	0.934 73	0.532 22	0.269 39	0.552 57	0.777 39	0.645 55	0.793 19	0.640 24	0.913 23	0.824 35	0.671 30

VI-PointConv	0.676 40	0.770 42	0.754 42	0.783 36	0.621 46	0.814 45	0.552 7	0.758 41	0.571 50	0.557 41	0.954 23	0.529 23	0.268 41	0.530 63	0.682 56	0.675 39	0.719 52	0.603 40	0.888 41	0.833 31	0.665 31
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 41	0.789 33	0.748 44	0.763 43	0.635 44	0.814 45	0.407 67	0.747 45	0.581 46	0.573 38	0.950 35	0.484 36	0.271 38	0.607 40	0.754 42	0.649 49	0.774 26	0.596 43	0.883 43	0.823 36	0.606 50

SALANet	0.670 42	0.816 27	0.770 33	0.768 40	0.652 37	0.807 49	0.451 44	0.747 45	0.659 16	0.545 44	0.924 79	0.473 41	0.149 86	0.571 50	0.811 34	0.635 58	0.746 44	0.623 31	0.892 38	0.794 53	0.570 63

PointASNL	0.666 43	0.703 67	0.781 29	0.751 47	0.655 35	0.830 26	0.471 36	0.769 39	0.474 76	0.537 47	0.951 31	0.475 40	0.279 32	0.635 32	0.698 55	0.675 39	0.751 42	0.553 62	0.816 73	0.806 45	0.703 20
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PointConv	0.666 43	0.781 35	0.759 38	0.699 57	0.644 41	0.822 35	0.475 33	0.779 36	0.564 53	0.504 61	0.953 26	0.428 61	0.203 65	0.586 45	0.754 42	0.661 45	0.753 41	0.588 49	0.902 30	0.813 43	0.642 38
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++	0.663 45	0.746 50	0.708 59	0.722 49	0.638 43	0.820 38	0.451 44	0.566 80	0.599 38	0.541 45	0.950 35	0.510 30	0.313 16	0.648 29	0.819 32	0.616 63	0.682 68	0.590 47	0.869 58	0.810 44	0.656 34
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 46	0.778 36	0.702 62	0.806 26	0.619 47	0.813 48	0.468 37	0.693 61	0.494 68	0.524 53	0.941 60	0.449 53	0.298 22	0.510 67	0.821 31	0.675 39	0.727 51	0.568 55	0.826 71	0.803 47	0.637 40
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN	0.656 47	0.698 68	0.743 49	0.650 73	0.564 64	0.820 38	0.505 21	0.758 41	0.631 22	0.479 66	0.945 49	0.480 38	0.226 54	0.572 49	0.774 40	0.690 35	0.735 47	0.614 35	0.853 65	0.776 68	0.597 56
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 48	0.752 48	0.734 53	0.664 70	0.583 59	0.815 44	0.399 69	0.754 43	0.639 19	0.535 49	0.942 58	0.470 42	0.309 18	0.665 25	0.539 70	0.650 48	0.708 57	0.635 26	0.857 64	0.793 55	0.642 38
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 49	0.778 36	0.731 54	0.699 57	0.577 60	0.829 27	0.446 49	0.736 49	0.477 75	0.523 55	0.945 49	0.454 49	0.269 39	0.484 74	0.749 45	0.618 61	0.738 45	0.599 42	0.827 70	0.792 58	0.621 45

MVPNet	0.641 50	0.831 22	0.715 57	0.671 67	0.590 55	0.781 64	0.394 71	0.679 63	0.642 17	0.553 42	0.937 66	0.462 45	0.256 45	0.649 28	0.406 83	0.626 59	0.691 65	0.666 17	0.877 47	0.792 58	0.608 49
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN	0.641 50	0.776 38	0.703 61	0.721 50	0.557 67	0.826 30	0.451 44	0.672 65	0.563 54	0.483 65	0.943 57	0.425 64	0.162 81	0.644 30	0.726 47	0.659 46	0.709 56	0.572 52	0.875 49	0.786 63	0.559 68

PointMRNet	0.640 52	0.717 63	0.701 63	0.692 60	0.576 61	0.801 54	0.467 39	0.716 54	0.563 54	0.459 71	0.953 26	0.429 60	0.169 78	0.581 46	0.854 21	0.605 64	0.710 54	0.550 63	0.894 37	0.793 55	0.575 61

FPConv	0.639 53	0.785 34	0.760 37	0.713 55	0.603 50	0.798 56	0.392 72	0.534 85	0.603 36	0.524 53	0.948 41	0.457 47	0.250 47	0.538 61	0.723 49	0.598 68	0.696 63	0.614 35	0.872 54	0.799 48	0.567 65
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 54	0.797 31	0.769 34	0.641 78	0.590 55	0.820 38	0.461 41	0.537 84	0.637 20	0.536 48	0.947 43	0.388 75	0.206 62	0.656 26	0.668 59	0.647 52	0.732 49	0.585 50	0.868 59	0.793 55	0.473 87

PointSPNet	0.637 55	0.734 56	0.692 70	0.714 54	0.576 61	0.797 57	0.446 49	0.743 47	0.598 39	0.437 76	0.942 58	0.403 71	0.150 85	0.626 36	0.800 36	0.649 49	0.697 62	0.557 60	0.846 67	0.777 67	0.563 66

SConv	0.636 56	0.830 23	0.697 66	0.752 46	0.572 63	0.780 66	0.445 51	0.716 54	0.529 60	0.530 50	0.951 31	0.446 55	0.170 77	0.507 69	0.666 60	0.636 57	0.682 68	0.541 68	0.886 42	0.799 48	0.594 57

Supervoxel-CNN	0.635 57	0.656 74	0.711 58	0.719 51	0.613 48	0.757 75	0.444 54	0.765 40	0.534 59	0.566 39	0.928 77	0.478 39	0.272 36	0.636 31	0.531 72	0.664 43	0.645 78	0.508 76	0.864 61	0.792 58	0.611 46

joint point-based	0.634 58	0.614 81	0.778 30	0.667 69	0.633 45	0.825 31	0.420 63	0.804 31	0.467 78	0.561 40	0.951 31	0.494 33	0.291 25	0.566 51	0.458 78	0.579 75	0.764 33	0.559 59	0.838 68	0.814 41	0.598 55
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 59	0.731 57	0.688 73	0.675 64	0.591 54	0.784 63	0.444 54	0.565 81	0.610 30	0.492 63	0.949 39	0.456 48	0.254 46	0.587 43	0.706 52	0.599 67	0.665 74	0.612 38	0.868 59	0.791 62	0.579 60

3DSM_DMMF	0.631 60	0.626 78	0.745 47	0.801 30	0.607 49	0.751 76	0.506 20	0.729 52	0.565 52	0.491 64	0.866 93	0.434 56	0.197 69	0.595 41	0.630 63	0.709 28	0.705 59	0.560 57	0.875 49	0.740 78	0.491 82

PointNet2-SFPN	0.631 60	0.771 40	0.692 70	0.672 65	0.524 72	0.837 20	0.440 57	0.706 59	0.538 58	0.446 73	0.944 55	0.421 66	0.219 57	0.552 57	0.751 44	0.591 71	0.737 46	0.543 67	0.901 32	0.768 70	0.557 69

APCF-Net	0.631 60	0.742 53	0.687 75	0.672 65	0.557 67	0.792 61	0.408 65	0.665 66	0.545 56	0.508 58	0.952 30	0.428 61	0.186 72	0.634 33	0.702 53	0.620 60	0.706 58	0.555 61	0.873 52	0.798 50	0.581 59
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv	0.630 63	0.604 83	0.741 51	0.766 42	0.590 55	0.747 77	0.501 23	0.734 50	0.503 67	0.527 51	0.919 83	0.454 49	0.323 12	0.550 60	0.420 82	0.678 38	0.688 66	0.544 65	0.896 35	0.795 52	0.627 44
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 64	0.800 30	0.625 85	0.719 51	0.545 70	0.806 50	0.445 51	0.597 75	0.448 82	0.519 56	0.938 65	0.481 37	0.328 10	0.489 73	0.499 77	0.657 47	0.759 38	0.592 46	0.881 45	0.797 51	0.634 41

SegGroup_sem	0.627 65	0.818 26	0.747 46	0.701 56	0.602 51	0.764 72	0.385 76	0.629 72	0.490 71	0.508 58	0.931 76	0.409 69	0.201 66	0.564 52	0.725 48	0.618 61	0.692 64	0.539 69	0.873 52	0.794 53	0.548 72
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 66	0.830 23	0.694 68	0.757 44	0.563 65	0.772 70	0.448 48	0.647 69	0.520 62	0.509 57	0.949 39	0.431 59	0.191 70	0.496 71	0.614 65	0.647 52	0.672 72	0.535 71	0.876 48	0.783 64	0.571 62

HPEIN	0.618 67	0.729 58	0.668 76	0.647 75	0.597 53	0.766 71	0.414 64	0.680 62	0.520 62	0.525 52	0.946 46	0.432 57	0.215 59	0.493 72	0.599 66	0.638 56	0.617 83	0.570 53	0.897 34	0.806 45	0.605 52
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 68	0.858 16	0.772 32	0.489 90	0.532 71	0.792 61	0.404 68	0.643 71	0.570 51	0.507 60	0.935 69	0.414 68	0.046 95	0.510 67	0.702 53	0.602 66	0.705 59	0.549 64	0.859 63	0.773 69	0.534 75
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 69	0.760 45	0.667 77	0.649 74	0.521 73	0.793 59	0.457 43	0.648 68	0.528 61	0.434 78	0.947 43	0.401 72	0.153 84	0.454 76	0.721 50	0.648 51	0.717 53	0.536 70	0.904 28	0.765 71	0.485 83
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 70	0.634 77	0.743 49	0.697 59	0.601 52	0.781 64	0.437 59	0.585 78	0.493 69	0.446 73	0.933 74	0.394 73	0.011 97	0.654 27	0.661 62	0.603 65	0.733 48	0.526 72	0.832 69	0.761 73	0.480 84

dtc_net	0.596 71	0.683 69	0.725 56	0.715 53	0.549 69	0.803 53	0.444 54	0.647 69	0.493 69	0.495 62	0.941 60	0.409 69	0.000 99	0.424 81	0.544 69	0.598 68	0.703 61	0.522 73	0.912 24	0.792 58	0.520 78

LAP-D	0.594 72	0.720 61	0.692 70	0.637 79	0.456 82	0.773 69	0.391 74	0.730 51	0.587 42	0.445 75	0.940 63	0.381 76	0.288 26	0.434 79	0.453 80	0.591 71	0.649 76	0.581 51	0.777 77	0.749 77	0.610 48

DPC	0.592 73	0.720 61	0.700 64	0.602 83	0.480 78	0.762 74	0.380 77	0.713 57	0.585 45	0.437 76	0.940 63	0.369 78	0.288 26	0.434 79	0.509 76	0.590 73	0.639 81	0.567 56	0.772 78	0.755 75	0.592 58
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 74	0.766 44	0.659 80	0.683 62	0.470 81	0.740 79	0.387 75	0.620 74	0.490 71	0.476 67	0.922 81	0.355 81	0.245 51	0.511 66	0.511 75	0.571 76	0.643 79	0.493 80	0.872 54	0.762 72	0.600 54

ROSMRF	0.580 75	0.772 39	0.707 60	0.681 63	0.563 65	0.764 72	0.362 79	0.515 86	0.465 79	0.465 70	0.936 68	0.427 63	0.207 61	0.438 77	0.577 67	0.536 79	0.675 71	0.486 81	0.723 84	0.779 65	0.524 77

SD-DETR	0.576 76	0.746 50	0.609 89	0.445 94	0.517 74	0.643 90	0.366 78	0.714 56	0.456 80	0.468 69	0.870 92	0.432 57	0.264 42	0.558 55	0.674 57	0.586 74	0.688 66	0.482 82	0.739 82	0.733 80	0.537 74

SQN_0.1%	0.569 77	0.676 71	0.696 67	0.657 71	0.497 75	0.779 67	0.424 61	0.548 82	0.515 64	0.376 83	0.902 90	0.422 65	0.357 4	0.379 84	0.456 79	0.596 70	0.659 75	0.544 65	0.685 87	0.665 91	0.556 70

TextureNet	0.566 78	0.672 73	0.664 78	0.671 67	0.494 76	0.719 80	0.445 51	0.678 64	0.411 88	0.396 81	0.935 69	0.356 80	0.225 55	0.412 82	0.535 71	0.565 77	0.636 82	0.464 84	0.794 76	0.680 88	0.568 64
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 79	0.648 75	0.700 64	0.770 39	0.586 58	0.687 84	0.333 83	0.650 67	0.514 65	0.475 68	0.906 87	0.359 79	0.223 56	0.340 86	0.442 81	0.422 90	0.668 73	0.501 77	0.708 85	0.779 65	0.534 75

Pointnet++ & Feature	0.557 80	0.735 55	0.661 79	0.686 61	0.491 77	0.744 78	0.392 72	0.539 83	0.451 81	0.375 84	0.946 46	0.376 77	0.205 63	0.403 83	0.356 86	0.553 78	0.643 79	0.497 78	0.824 72	0.756 74	0.515 79

GMLPs	0.538 81	0.495 91	0.693 69	0.647 75	0.471 80	0.793 59	0.300 86	0.477 87	0.505 66	0.358 85	0.903 89	0.327 84	0.081 92	0.472 75	0.529 73	0.448 88	0.710 54	0.509 74	0.746 80	0.737 79	0.554 71

PanopticFusion-label	0.529 82	0.491 92	0.688 73	0.604 82	0.386 87	0.632 91	0.225 96	0.705 60	0.434 85	0.293 91	0.815 94	0.348 82	0.241 52	0.499 70	0.669 58	0.507 81	0.649 76	0.442 90	0.796 75	0.602 94	0.561 67
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 83	0.676 71	0.591 92	0.609 80	0.442 83	0.774 68	0.335 82	0.597 75	0.422 87	0.357 86	0.932 75	0.341 83	0.094 91	0.298 88	0.528 74	0.473 86	0.676 70	0.495 79	0.602 93	0.721 83	0.349 94

Online SegFusion	0.515 84	0.607 82	0.644 83	0.579 85	0.434 84	0.630 92	0.353 80	0.628 73	0.440 83	0.410 79	0.762 97	0.307 86	0.167 79	0.520 64	0.403 84	0.516 80	0.565 86	0.447 88	0.678 88	0.701 85	0.514 80
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 85	0.558 87	0.608 90	0.424 96	0.478 79	0.690 83	0.246 92	0.586 77	0.468 77	0.450 72	0.911 85	0.394 73	0.160 82	0.438 77	0.212 93	0.432 89	0.541 91	0.475 83	0.742 81	0.727 81	0.477 85

PCNN	0.498 86	0.559 86	0.644 83	0.560 87	0.420 86	0.711 82	0.229 94	0.414 88	0.436 84	0.352 87	0.941 60	0.324 85	0.155 83	0.238 93	0.387 85	0.493 82	0.529 92	0.509 74	0.813 74	0.751 76	0.504 81

3DMV	0.484 87	0.484 93	0.538 94	0.643 77	0.424 85	0.606 95	0.310 84	0.574 79	0.433 86	0.378 82	0.796 95	0.301 87	0.214 60	0.537 62	0.208 94	0.472 87	0.507 95	0.413 93	0.693 86	0.602 94	0.539 73
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 88	0.577 85	0.611 88	0.356 98	0.321 95	0.715 81	0.299 88	0.376 92	0.328 95	0.319 89	0.944 55	0.285 89	0.164 80	0.216 96	0.229 91	0.484 84	0.545 90	0.456 86	0.755 79	0.709 84	0.475 86
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 89	0.679 70	0.604 91	0.578 86	0.380 88	0.682 85	0.291 89	0.106 98	0.483 74	0.258 96	0.920 82	0.258 93	0.025 96	0.231 95	0.325 87	0.480 85	0.560 88	0.463 85	0.725 83	0.666 90	0.231 98
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 90	0.474 94	0.623 86	0.463 92	0.366 90	0.651 88	0.310 84	0.389 91	0.349 93	0.330 88	0.937 66	0.271 91	0.126 88	0.285 89	0.224 92	0.350 95	0.577 85	0.445 89	0.625 91	0.723 82	0.394 90
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 91	0.548 88	0.548 93	0.597 84	0.363 91	0.628 93	0.300 86	0.292 93	0.374 90	0.307 90	0.881 91	0.268 92	0.186 72	0.238 93	0.204 95	0.407 91	0.506 96	0.449 87	0.667 89	0.620 93	0.462 88

SurfaceConvPF	0.442 91	0.505 90	0.622 87	0.380 97	0.342 93	0.654 87	0.227 95	0.397 90	0.367 91	0.276 93	0.924 79	0.240 94	0.198 68	0.359 85	0.262 89	0.366 92	0.581 84	0.435 91	0.640 90	0.668 89	0.398 89
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutions	0.438 93	0.437 96	0.646 82	0.474 91	0.369 89	0.645 89	0.353 80	0.258 95	0.282 97	0.279 92	0.918 84	0.298 88	0.147 87	0.283 90	0.294 88	0.487 83	0.562 87	0.427 92	0.619 92	0.633 92	0.352 93
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 94	0.525 89	0.647 81	0.522 88	0.324 94	0.488 98	0.077 99	0.712 58	0.353 92	0.401 80	0.636 99	0.281 90	0.176 75	0.340 86	0.565 68	0.175 99	0.551 89	0.398 94	0.370 99	0.602 94	0.361 92

SPLAT Net	0.393 95	0.472 95	0.511 95	0.606 81	0.311 96	0.656 86	0.245 93	0.405 89	0.328 95	0.197 97	0.927 78	0.227 96	0.000 99	0.001 100	0.249 90	0.271 98	0.510 93	0.383 96	0.593 94	0.699 86	0.267 96
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 96	0.297 98	0.491 96	0.432 95	0.358 92	0.612 94	0.274 90	0.116 97	0.411 88	0.265 94	0.904 88	0.229 95	0.079 93	0.250 91	0.185 96	0.320 96	0.510 93	0.385 95	0.548 95	0.597 97	0.394 90

PointNet++	0.339 97	0.584 84	0.478 97	0.458 93	0.256 98	0.360 99	0.250 91	0.247 96	0.278 98	0.261 95	0.677 98	0.183 97	0.117 89	0.212 97	0.145 98	0.364 93	0.346 99	0.232 99	0.548 95	0.523 98	0.252 97
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 98	0.353 97	0.290 99	0.278 99	0.166 99	0.553 96	0.169 98	0.286 94	0.147 99	0.148 99	0.908 86	0.182 98	0.064 94	0.023 99	0.018 100	0.354 94	0.363 97	0.345 97	0.546 97	0.685 87	0.278 95

ScanNet	0.306 99	0.203 99	0.366 98	0.501 89	0.311 96	0.524 97	0.211 97	0.002 100	0.342 94	0.189 98	0.786 96	0.145 99	0.102 90	0.245 92	0.152 97	0.318 97	0.348 98	0.300 98	0.460 98	0.437 99	0.182 99
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 100	0.000 100	0.041 100	0.172 100	0.030 100	0.062 100	0.001 100	0.035 99	0.004 100	0.051 100	0.143 100	0.019 100	0.003 98	0.041 98	0.050 99	0.003 100	0.054 100	0.018 100	0.005 100	0.264 100	0.082 100

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 14	0.970 1	0.889 1	0.828 12	0.945 3	0.803 6	0.713 10	0.720 10	0.709 8	1.000 1	0.936 6	0.934 3	0.873 7	1.000 1	0.791 5

Queryformer	0.874 2	1.000 1	0.978 10	0.809 24	0.876 1	0.936 5	0.702 8	0.716 26	0.920 5	0.875 3	0.766 4	0.772 2	0.818 4	1.000 1	0.995 1	0.916 4	0.892 1	1.000 1	0.767 8

SoftGroup++	0.874 2	1.000 1	0.972 13	0.947 1	0.839 5	0.898 12	0.556 23	0.913 2	0.881 11	0.756 8	0.828 2	0.748 6	0.821 2	1.000 1	0.937 5	0.937 1	0.887 2	1.000 1	0.821 2

Mask3D	0.870 4	1.000 1	0.985 6	0.782 32	0.818 8	0.938 4	0.760 4	0.749 23	0.923 4	0.877 2	0.760 5	0.785 1	0.820 3	1.000 1	0.912 9	0.864 23	0.878 5	0.983 39	0.825 1
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 8	0.558 21	0.899 3	0.911 6	0.760 7	0.828 1	0.736 7	0.802 6	0.981 29	0.919 8	0.875 14	0.877 6	1.000 1	0.820 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]
IPCA-Inst	0.851 6	1.000 1	0.968 15	0.884 8	0.842 4	0.862 24	0.693 10	0.812 17	0.888 9	0.677 20	0.783 3	0.698 11	0.807 5	1.000 1	0.911 13	0.865 22	0.865 9	1.000 1	0.757 10

SPFormer	0.851 6	1.000 1	0.994 2	0.806 25	0.774 16	0.942 3	0.637 13	0.849 10	0.859 14	0.889 1	0.720 8	0.730 8	0.665 13	1.000 1	0.911 13	0.868 21	0.873 8	1.000 1	0.796 4
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
ISBNet	0.845 8	1.000 1	0.976 11	0.798 26	0.794 11	0.916 6	0.757 5	0.667 33	0.882 10	0.842 4	0.715 9	0.757 4	0.832 1	1.000 1	0.905 16	0.803 43	0.843 12	1.000 1	0.715 17
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
SphereSeg	0.835 9	1.000 1	0.963 18	0.891 6	0.794 10	0.954 2	0.822 3	0.710 27	0.961 2	0.721 12	0.693 16	0.530 31	0.653 15	1.000 1	0.867 23	0.857 26	0.859 10	0.991 36	0.771 7

TopoSeg	0.832 10	1.000 1	0.981 8	0.933 2	0.819 7	0.826 32	0.524 29	0.841 11	0.811 19	0.681 19	0.759 6	0.687 12	0.727 7	0.981 29	0.911 13	0.883 10	0.853 11	1.000 1	0.756 11

GraphCut	0.832 10	1.000 1	0.922 32	0.724 41	0.798 9	0.902 11	0.701 9	0.856 8	0.859 13	0.715 13	0.706 11	0.748 5	0.640 26	1.000 1	0.934 7	0.862 24	0.880 3	1.000 1	0.729 13

PBNet	0.825 12	1.000 1	0.963 17	0.837 16	0.843 3	0.865 19	0.822 2	0.647 35	0.878 12	0.733 10	0.639 24	0.683 13	0.650 16	1.000 1	0.853 24	0.870 18	0.820 13	1.000 1	0.744 12

SSEC	0.820 13	1.000 1	0.983 7	0.924 3	0.826 6	0.817 35	0.415 38	0.899 4	0.793 23	0.673 21	0.731 7	0.636 18	0.653 14	1.000 1	0.939 4	0.804 41	0.878 4	1.000 1	0.780 6

DKNet	0.815 14	1.000 1	0.930 24	0.844 14	0.765 20	0.915 7	0.534 27	0.805 19	0.805 21	0.807 5	0.654 18	0.763 3	0.650 16	1.000 1	0.794 36	0.881 11	0.766 17	1.000 1	0.758 9
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN	0.806 15	1.000 1	0.992 4	0.789 28	0.723 32	0.891 13	0.650 12	0.810 18	0.832 16	0.665 23	0.699 14	0.658 14	0.700 9	1.000 1	0.881 18	0.832 33	0.774 15	0.997 29	0.613 34
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAIS	0.803 16	1.000 1	0.994 2	0.820 20	0.759 21	0.855 25	0.554 24	0.882 5	0.827 18	0.615 29	0.676 17	0.638 17	0.646 24	1.000 1	0.912 9	0.797 45	0.767 16	0.994 34	0.726 14
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask	0.803 16	1.000 1	0.962 19	0.874 10	0.707 35	0.887 16	0.686 11	0.598 39	0.961 1	0.715 14	0.694 15	0.469 36	0.700 9	1.000 1	0.912 9	0.902 5	0.753 22	0.997 29	0.637 28
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 18	1.000 1	0.968 16	0.812 21	0.766 19	0.864 20	0.460 32	0.815 16	0.888 8	0.598 32	0.651 21	0.639 16	0.600 30	0.918 33	0.941 2	0.896 6	0.721 29	1.000 1	0.723 15
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 19	1.000 1	0.996 1	0.829 19	0.767 18	0.889 15	0.600 16	0.819 15	0.770 28	0.594 33	0.620 27	0.541 28	0.700 9	1.000 1	0.941 2	0.889 8	0.763 18	1.000 1	0.526 43

SSTNet	0.789 20	1.000 1	0.840 46	0.888 7	0.717 33	0.835 28	0.717 7	0.684 32	0.627 42	0.724 11	0.652 20	0.727 9	0.600 30	1.000 1	0.912 9	0.822 36	0.757 21	1.000 1	0.691 22
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN	0.788 21	1.000 1	0.978 9	0.867 11	0.781 15	0.833 29	0.527 28	0.824 13	0.806 20	0.549 41	0.596 30	0.551 24	0.700 9	1.000 1	0.853 24	0.935 2	0.733 26	1.000 1	0.651 25

DENet	0.786 22	1.000 1	0.929 25	0.736 39	0.750 27	0.720 47	0.755 6	0.934 1	0.794 22	0.590 34	0.561 36	0.537 29	0.650 16	1.000 1	0.882 17	0.804 42	0.789 14	1.000 1	0.719 16

DualGroup	0.782 23	1.000 1	0.927 26	0.811 22	0.772 17	0.853 26	0.631 15	0.805 19	0.773 25	0.613 30	0.611 28	0.610 20	0.650 16	0.835 44	0.881 18	0.879 13	0.750 24	1.000 1	0.675 23

PointGroup	0.778 24	1.000 1	0.900 36	0.798 27	0.715 34	0.863 21	0.493 30	0.706 28	0.895 7	0.569 39	0.701 12	0.576 22	0.639 27	1.000 1	0.880 20	0.851 28	0.719 30	0.997 29	0.709 19
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 25	1.000 1	0.900 37	0.860 12	0.728 31	0.869 17	0.400 39	0.857 7	0.774 24	0.568 40	0.701 13	0.602 21	0.646 24	0.933 32	0.843 27	0.890 7	0.691 37	0.997 29	0.709 18
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA	0.767 26	1.000 1	0.937 21	0.810 23	0.740 29	0.906 9	0.550 25	0.800 21	0.706 34	0.577 38	0.624 26	0.544 27	0.596 35	0.857 36	0.879 22	0.880 12	0.750 23	0.992 35	0.658 24

DD-UNet+Group	0.764 27	1.000 1	0.897 39	0.837 15	0.753 24	0.830 31	0.459 34	0.824 13	0.699 36	0.629 27	0.653 19	0.438 39	0.650 16	1.000 1	0.880 20	0.858 25	0.690 38	1.000 1	0.650 26
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 28	1.000 1	0.923 29	0.765 35	0.785 13	0.905 10	0.600 16	0.655 34	0.646 41	0.683 18	0.647 22	0.530 30	0.650 16	1.000 1	0.824 29	0.830 34	0.693 36	0.944 43	0.644 27

Dyco3D	0.761 29	1.000 1	0.935 22	0.893 5	0.752 26	0.863 22	0.600 16	0.588 40	0.742 31	0.641 25	0.633 25	0.546 26	0.550 37	0.857 36	0.789 38	0.853 27	0.762 19	0.987 37	0.699 20
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance	0.742 30	1.000 1	0.923 29	0.785 29	0.745 28	0.867 18	0.557 22	0.578 43	0.729 32	0.670 22	0.644 23	0.488 34	0.577 36	1.000 1	0.794 36	0.830 34	0.620 45	1.000 1	0.550 39
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg	0.739 31	1.000 1	0.899 38	0.759 37	0.753 25	0.823 33	0.282 43	0.691 31	0.658 39	0.582 37	0.594 31	0.547 25	0.628 28	1.000 1	0.795 35	0.868 20	0.728 28	1.000 1	0.692 21

3D-MPA	0.737 32	1.000 1	0.933 23	0.785 29	0.794 12	0.831 30	0.279 45	0.588 40	0.695 37	0.616 28	0.559 37	0.556 23	0.650 16	1.000 1	0.809 33	0.875 15	0.696 34	1.000 1	0.608 36
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 33	1.000 1	0.992 4	0.779 34	0.609 44	0.746 42	0.308 42	0.867 6	0.601 45	0.607 31	0.539 40	0.519 32	0.550 37	1.000 1	0.824 29	0.869 19	0.729 27	1.000 1	0.616 32
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS	0.725 34	1.000 1	0.885 42	0.653 47	0.657 41	0.801 36	0.576 20	0.695 30	0.828 17	0.698 16	0.534 41	0.457 38	0.500 44	0.857 36	0.831 28	0.841 31	0.627 44	1.000 1	0.619 31

SSEN	0.724 35	1.000 1	0.926 27	0.781 33	0.661 39	0.845 27	0.596 19	0.529 45	0.764 30	0.653 24	0.489 46	0.461 37	0.500 44	0.859 35	0.765 39	0.872 17	0.761 20	1.000 1	0.577 37
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 36	1.000 1	0.945 20	0.901 4	0.754 23	0.817 34	0.460 32	0.700 29	0.772 26	0.688 17	0.568 35	0.000 56	0.500 44	0.981 29	0.606 47	0.872 16	0.740 25	1.000 1	0.614 33
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 37	1.000 1	0.926 28	0.694 42	0.699 37	0.890 14	0.636 14	0.516 46	0.693 38	0.743 9	0.588 32	0.369 42	0.601 29	0.594 49	0.800 34	0.886 9	0.676 39	0.986 38	0.546 40

SALoss-ResNet	0.695 38	1.000 1	0.855 44	0.579 51	0.589 46	0.735 45	0.484 31	0.588 40	0.856 15	0.634 26	0.571 34	0.298 43	0.500 44	1.000 1	0.824 29	0.818 37	0.702 33	0.935 47	0.545 41
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 39	1.000 1	0.852 45	0.655 46	0.616 43	0.788 37	0.334 41	0.763 22	0.771 27	0.457 51	0.555 38	0.652 15	0.518 41	0.857 36	0.765 39	0.732 51	0.631 42	0.944 43	0.577 38
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 40	1.000 1	0.913 33	0.730 40	0.737 30	0.743 44	0.442 35	0.855 9	0.655 40	0.546 42	0.546 39	0.263 45	0.508 43	0.889 34	0.568 48	0.771 48	0.705 32	0.889 50	0.625 30

3D-BoNet	0.687 41	1.000 1	0.887 41	0.836 17	0.587 47	0.643 54	0.550 25	0.620 36	0.724 33	0.522 46	0.501 44	0.243 46	0.512 42	1.000 1	0.751 41	0.807 40	0.661 41	0.909 49	0.612 35
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
PCJC	0.684 42	1.000 1	0.895 40	0.757 38	0.659 40	0.862 23	0.189 52	0.739 24	0.606 44	0.712 15	0.581 33	0.515 33	0.650 16	0.857 36	0.357 53	0.785 46	0.631 43	0.889 50	0.635 29

SPG_WSIS	0.678 43	1.000 1	0.880 43	0.836 17	0.701 36	0.727 46	0.273 47	0.607 38	0.706 35	0.541 44	0.515 43	0.174 48	0.600 30	0.857 36	0.716 42	0.846 30	0.711 31	1.000 1	0.506 44

One_Thing_One_Click	0.675 44	1.000 1	0.823 47	0.782 31	0.621 42	0.766 39	0.211 49	0.736 25	0.560 48	0.586 35	0.522 42	0.636 19	0.453 48	0.641 48	0.853 24	0.850 29	0.694 35	0.997 29	0.411 48
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 45	1.000 1	0.923 31	0.593 50	0.561 48	0.746 43	0.143 54	0.504 47	0.766 29	0.485 49	0.442 47	0.372 41	0.530 40	0.714 45	0.815 32	0.775 47	0.673 40	1.000 1	0.431 47
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 46	0.711 52	0.802 48	0.540 52	0.757 22	0.777 38	0.029 55	0.577 44	0.588 47	0.521 47	0.600 29	0.436 40	0.534 39	0.697 46	0.616 46	0.838 32	0.526 47	0.980 40	0.534 42
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone	0.605 47	1.000 1	0.909 34	0.764 36	0.603 45	0.704 48	0.415 37	0.301 52	0.548 49	0.461 50	0.394 48	0.267 44	0.386 50	0.857 36	0.649 45	0.817 38	0.504 48	0.959 41	0.356 51

3D-SIS	0.558 48	1.000 1	0.773 49	0.614 49	0.503 50	0.691 50	0.200 50	0.412 48	0.498 52	0.546 43	0.311 53	0.103 52	0.600 30	0.857 36	0.382 50	0.799 44	0.445 54	0.938 46	0.371 49
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet	0.544 49	0.500 55	0.655 55	0.661 45	0.663 38	0.765 40	0.432 36	0.214 54	0.612 43	0.584 36	0.499 45	0.204 47	0.286 54	0.429 52	0.655 44	0.650 56	0.539 46	0.950 42	0.499 45

Hier3D	0.540 50	1.000 1	0.727 50	0.626 48	0.467 53	0.693 49	0.200 50	0.412 48	0.480 53	0.528 45	0.318 52	0.077 55	0.600 30	0.688 47	0.382 50	0.768 49	0.472 50	0.941 45	0.350 52
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class	0.497 51	0.250 57	0.902 35	0.689 43	0.540 49	0.747 41	0.276 46	0.610 37	0.268 56	0.489 48	0.348 49	0.000 56	0.243 56	0.220 55	0.663 43	0.814 39	0.459 52	0.928 48	0.496 46

tmp	0.474 52	1.000 1	0.727 50	0.433 55	0.481 52	0.673 52	0.022 57	0.380 50	0.517 51	0.436 53	0.338 51	0.128 50	0.343 52	0.429 52	0.291 55	0.728 52	0.473 49	0.833 53	0.300 54

SemRegionNet-20cls	0.470 53	1.000 1	0.727 50	0.447 54	0.481 51	0.678 51	0.024 56	0.380 50	0.518 50	0.440 52	0.339 50	0.128 50	0.350 51	0.429 52	0.212 56	0.711 53	0.465 51	0.833 53	0.290 55

ASIS	0.422 54	0.333 56	0.707 53	0.676 44	0.401 54	0.650 53	0.350 40	0.177 55	0.594 46	0.376 54	0.202 54	0.077 54	0.404 49	0.571 50	0.197 57	0.674 55	0.447 53	0.500 56	0.260 56

3D-BEVIS	0.401 55	0.667 53	0.687 54	0.419 56	0.137 57	0.587 55	0.188 53	0.235 53	0.359 55	0.211 56	0.093 57	0.080 53	0.311 53	0.571 50	0.382 50	0.754 50	0.300 56	0.874 52	0.357 50
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet	0.390 56	0.556 54	0.636 56	0.493 53	0.353 55	0.539 56	0.271 48	0.160 56	0.450 54	0.359 55	0.178 55	0.146 49	0.250 55	0.143 56	0.347 54	0.698 54	0.436 55	0.667 55	0.331 53

MaskRCNN 2d->3d Proj	0.261 57	0.903 51	0.081 57	0.008 57	0.233 56	0.175 57	0.280 44	0.106 57	0.150 57	0.203 57	0.175 56	0.480 35	0.218 57	0.143 56	0.542 49	0.404 57	0.153 57	0.393 57	0.049 57

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