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

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

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

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

Mask3D Scannet200	0.388 1	0.542 1	0.357 1	0.237 1	0.610 1	0.091 1	0.125 4	0.000 1	0.000 1	0.000 1	0.065 2	0.668 1	0.451 1	1.000 1	0.955 1	0.640 1	0.500 1	0.039 1	0.125 2	0.063 1	0.409 1	0.311 1	0.291 1	0.609 2	0.266 1	0.000 1	0.163 1	0.000 1	0.008 1	0.044 1	0.496 1	1.000 1	0.000 1	0.018 1	0.000 1	0.756 1	0.573 1	0.808 1	0.000 1	0.010 1	0.042 2	0.130 2	0.552 1	0.042 1	0.000 1	1.000 1	0.725 3	0.750 1	0.883 1	1.000 1	0.832 3	0.024 1	0.107 1	0.614 2	0.226 1	0.250 1	0.628 1	0.792 1	0.677 2	0.400 1	0.741 1	0.278 1	0.511 1	0.077 4	0.111 1	0.313 1	0.715 1	0.302 1	0.017 2	0.200 1	0.000 1	0.188 1	0.000 1	0.178 1	0.736 1	1.000 1	0.615 1	0.514 1	0.409 1	0.380 4	0.600 1	0.000 1	0.000 1	0.400 1	0.013 1	0.254 1	0.381 1	0.000 1	0.123 3	0.400 1	0.839 1	0.258 1	0.463 1	0.926 1	0.265 1	0.000 1	0.857 1	0.099 1	0.021 1	0.500 1	0.027 1	0.028 1	1.000 1	0.502 4	0.016 1	0.076 3	0.500 1	0.612 1	0.578 1	0.005 1	0.597 1	0.194 1	0.497 1	0.000 1	0.500 1	0.000 1	0.323 3	0.000 1	1.000 1	0.000 1	0.748 1	0.708 2	0.050 3	0.890 1	1.000 1	0.008 1	0.151 2	0.301 1	1.000 1	1.000 1	0.792 2	0.945 1	1.000 1	0.511 1	0.004 1	0.753 1	0.776 1	0.287 1	0.020 1	0.003 3	0.974 2	0.033 1	0.412 4	0.000 1	0.000 1	0.000 1	0.667 1	0.000 1	0.000 1	0.491 1	0.676 1	0.352 1	0.335 1	0.060 1	0.822 4	0.527 1	1.000 1	0.517 1	0.606 1	0.853 1	0.000 1	0.004 1	0.806 1	1.000 1	0.727 1	0.000 1	0.042 1	0.739 1	0.000 1	0.399 2	0.391 1	0.504 1	0.591 1	0.571 1

LGround Inst.	0.246 2	0.413 2	0.170 2	0.130 2	0.455 4	0.003 4	0.500 1	0.000 1	0.000 1	0.000 1	0.017 3	0.333 3	0.111 4	1.000 1	0.681 3	0.400 2	0.000 2	0.000 2	1.000 1	0.003 4	0.000 2	0.167 2	0.190 2	0.637 1	0.067 2	0.000 1	0.081 2	0.000 1	0.000 2	0.000 2	0.264 3	0.000 2	0.000 1	0.000 2	0.000 1	0.387 3	0.031 4	0.754 2	0.000 1	0.000 2	0.151 1	0.135 1	0.056 3	0.000 2	0.000 1	0.582 3	0.589 4	0.500 2	0.815 2	1.000 1	0.903 1	0.000 2	0.097 2	0.588 3	0.000 2	0.000 2	0.234 2	0.000 2	0.500 3	0.400 1	0.682 3	0.156 2	0.159 3	0.750 1	0.046 2	0.125 3	0.660 2	0.000 2	0.200 1	0.000 4	0.000 1	0.000 2	0.000 1	0.164 2	0.402 2	0.500 2	0.373 2	0.025 2	0.143 4	0.426 2	0.317 2	0.000 1	0.000 1	0.000 2	0.000 2	0.063 2	0.000 2	0.000 1	0.000 4	0.000 3	0.575 3	0.250 2	0.241 2	0.772 2	0.000 2	0.000 1	0.653 3	0.034 2	0.000 2	0.000 2	0.000 2	0.000 2	1.000 1	0.561 3	0.000 2	0.100 2	0.500 1	0.541 4	0.452 2	0.000 2	0.581 2	0.000 2	0.364 2	0.000 1	0.000 2	0.000 1	0.571 1	0.000 1	0.000 2	0.000 1	0.568 4	0.511 3	0.167 2	0.857 2	0.000 2	0.000 2	0.164 1	0.112 2	0.000 4	0.530 4	1.000 1	0.286 2	0.000 2	0.125 2	0.000 2	0.464 4	0.706 2	0.208 3	0.000 2	0.125 1	0.744 3	0.000 2	0.500 1	0.000 1	0.000 1	0.000 1	0.511 2	0.000 1	0.000 1	0.344 2	0.541 2	0.068 2	0.333 2	0.000 2	1.000 1	0.196 3	0.533 3	0.318 2	0.000 3	0.748 3	0.000 1	0.000 2	0.690 2	1.000 1	0.400 3	0.000 1	0.000 2	0.667 2	0.000 1	0.333 3	0.333 2	0.270 3	0.399 2	0.083 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
CSC-Pretrain Inst.	0.209 3	0.361 4	0.157 3	0.085 3	0.506 2	0.007 2	0.500 1	0.000 1	0.000 1	0.000 1	0.000 4	0.093 4	0.221 3	0.667 3	0.524 4	0.400 2	0.000 2	0.000 2	0.000 3	0.004 3	0.000 2	0.000 4	0.109 4	0.589 3	0.000 3	0.000 1	0.059 4	0.000 1	0.000 2	0.000 2	0.322 2	0.000 2	0.000 1	0.000 2	0.000 1	0.405 2	0.055 3	0.700 4	0.000 1	0.000 2	0.028 3	0.091 4	0.083 2	0.000 2	0.000 1	0.667 2	0.768 1	0.000 3	0.807 3	1.000 1	0.776 4	0.000 2	0.000 4	0.340 4	0.000 2	0.000 2	0.103 4	0.000 2	0.750 1	0.200 3	0.634 4	0.053 4	0.246 2	0.677 2	0.006 4	0.198 2	0.432 3	0.000 2	0.000 3	0.050 3	0.000 1	0.000 2	0.000 1	0.111 4	0.356 3	0.500 2	0.188 4	0.000 3	0.220 3	0.448 1	0.050 4	0.000 1	0.000 1	0.000 2	0.000 2	0.032 4	0.000 2	0.000 1	0.396 1	0.000 3	0.573 4	0.000 4	0.228 3	0.747 3	0.000 2	0.000 1	0.573 4	0.021 4	0.000 2	0.000 2	0.000 2	0.000 2	0.500 3	0.573 2	0.000 2	0.000 4	0.125 4	0.592 3	0.364 4	0.000 2	0.450 4	0.000 2	0.364 2	0.000 1	0.000 2	0.000 1	0.340 2	0.000 1	0.000 2	0.000 1	0.610 3	0.833 1	0.221 1	0.702 4	0.000 2	0.000 2	0.135 4	0.094 3	0.125 2	0.571 3	0.500 3	0.143 4	0.000 2	0.125 2	0.000 2	0.618 2	0.667 3	0.115 4	0.000 2	0.125 1	1.000 1	0.000 2	0.500 1	0.000 1	0.000 1	0.000 1	0.502 3	0.000 1	0.000 1	0.312 3	0.248 4	0.050 3	0.000 4	0.000 2	0.997 2	0.420 2	0.500 4	0.149 4	0.451 2	0.748 2	0.000 1	0.000 2	0.636 3	0.667 4	0.600 2	0.000 1	0.000 2	0.278 4	0.000 1	0.333 3	0.000 4	0.294 2	0.381 4	0.110 2
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34D Inst.	0.203 4	0.369 3	0.134 4	0.078 4	0.479 3	0.003 3	0.500 1	0.000 1	0.000 1	0.000 1	0.100 1	0.371 2	0.300 2	0.667 3	0.746 2	0.400 2	0.000 2	0.000 2	0.000 3	0.031 2	0.000 2	0.074 3	0.165 3	0.413 4	0.000 3	0.000 1	0.070 3	0.000 1	0.000 2	0.000 2	0.221 4	0.000 2	0.000 1	0.000 2	0.000 1	0.372 4	0.070 2	0.706 3	0.000 1	0.000 2	0.000 4	0.123 3	0.033 4	0.000 2	0.000 1	0.422 4	0.732 2	0.000 3	0.778 4	1.000 1	0.845 2	0.000 2	0.090 3	0.636 1	0.000 2	0.000 2	0.158 3	0.000 2	0.250 4	0.050 4	0.693 2	0.123 3	0.051 4	0.385 3	0.009 3	0.118 4	0.406 4	0.000 2	0.000 3	0.200 1	0.000 1	0.000 2	0.000 1	0.133 3	0.307 4	0.500 2	0.251 3	0.000 3	0.281 2	0.402 3	0.317 2	0.000 1	0.000 1	0.000 2	0.000 2	0.060 3	0.000 2	0.000 1	0.396 1	0.200 2	0.669 2	0.021 3	0.218 4	0.720 4	0.000 2	0.000 1	0.696 2	0.025 3	0.000 2	0.000 2	0.000 2	0.000 2	0.125 4	0.596 1	0.000 2	0.191 1	0.500 1	0.595 2	0.369 3	0.000 2	0.500 3	0.000 2	0.143 4	0.000 1	0.000 2	0.000 1	0.226 4	0.000 1	0.000 2	0.000 1	0.701 2	0.511 3	0.000 4	0.851 3	0.000 2	0.000 2	0.150 3	0.052 4	0.100 3	0.981 2	0.500 3	0.286 2	0.000 2	0.000 4	0.000 2	0.545 3	0.522 4	0.250 2	0.000 2	0.000 4	0.522 4	0.000 2	0.500 1	0.000 1	0.000 1	0.000 1	0.282 4	0.000 1	0.000 1	0.178 4	0.382 3	0.018 4	0.056 3	0.000 2	0.997 2	0.107 4	0.677 2	0.313 3	0.000 3	0.726 4	0.000 1	0.000 2	0.583 4	0.903 3	0.200 4	0.000 1	0.000 2	0.333 3	0.000 1	0.442 1	0.083 3	0.109 4	0.387 3	0.000 4
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019

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 2	0.831 15	0.685 5	0.714 1	0.979 1	0.594 3	0.310 15	0.801 1	0.892 7	0.841 2	0.819 3	0.723 2	0.940 7	0.887 1	0.725 9
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
IPCA	0.731 14	0.890 5	0.837 3	0.864 2	0.726 13	0.873 2	0.530 9	0.824 17	0.489 65	0.647 8	0.978 2	0.609 2	0.336 6	0.624 30	0.733 39	0.758 7	0.776 23	0.570 45	0.949 2	0.877 5	0.728 5

OccuSeg+Semantic	0.764 2	0.758 40	0.796 15	0.839 11	0.746 7	0.907 1	0.562 3	0.850 10	0.680 6	0.672 5	0.978 2	0.610 1	0.335 7	0.777 3	0.819 26	0.847 1	0.830 1	0.691 6	0.972 1	0.885 2	0.727 7

One-Thing-One-Click	0.693 23	0.743 46	0.794 17	0.655 65	0.684 22	0.822 26	0.497 20	0.719 45	0.622 19	0.617 15	0.977 4	0.447 47	0.339 5	0.750 12	0.664 54	0.703 24	0.790 19	0.596 34	0.946 4	0.855 15	0.647 29
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PointConvFormer	0.749 5	0.793 26	0.790 18	0.807 20	0.750 6	0.856 8	0.524 10	0.881 6	0.588 32	0.642 12	0.977 4	0.591 5	0.274 29	0.781 2	0.929 1	0.804 3	0.796 14	0.642 16	0.947 3	0.885 2	0.715 13
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
One Thing One Click	0.701 20	0.825 20	0.796 15	0.723 41	0.716 15	0.832 18	0.433 51	0.816 18	0.634 16	0.609 19	0.969 6	0.418 60	0.344 4	0.559 47	0.833 23	0.715 20	0.808 7	0.560 49	0.902 22	0.847 19	0.680 20

PointFormerV2	0.752 4	0.742 47	0.809 10	0.872 1	0.758 3	0.860 6	0.552 4	0.891 5	0.610 22	0.687 2	0.960 7	0.559 12	0.304 18	0.766 7	0.926 2	0.767 5	0.797 13	0.644 15	0.942 5	0.876 7	0.722 11

Retro-FPN	0.744 11	0.842 16	0.800 13	0.767 34	0.740 9	0.836 16	0.541 6	0.914 1	0.672 8	0.626 14	0.958 8	0.552 13	0.272 30	0.777 3	0.886 9	0.696 26	0.801 10	0.674 9	0.941 6	0.858 12	0.717 12

O-CNN	0.762 3	0.924 2	0.823 4	0.844 9	0.770 2	0.852 9	0.577 1	0.847 11	0.711 1	0.640 13	0.958 8	0.592 4	0.217 50	0.762 9	0.888 8	0.758 7	0.813 5	0.726 1	0.932 13	0.868 8	0.744 3
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
BPNet	0.749 5	0.909 3	0.818 7	0.811 17	0.752 5	0.839 13	0.485 24	0.842 13	0.673 7	0.644 10	0.957 10	0.528 19	0.305 17	0.773 5	0.859 13	0.788 4	0.818 4	0.693 5	0.916 15	0.856 14	0.723 10
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PicassoNet-II	0.696 22	0.704 57	0.790 18	0.787 26	0.709 16	0.837 14	0.459 34	0.815 20	0.543 49	0.615 16	0.956 11	0.529 17	0.250 40	0.551 52	0.790 31	0.703 24	0.799 12	0.619 25	0.908 17	0.848 18	0.700 16
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
MSP	0.748 7	0.623 71	0.804 11	0.859 3	0.745 8	0.824 24	0.501 16	0.912 2	0.690 4	0.685 3	0.956 11	0.567 9	0.320 12	0.768 6	0.918 3	0.720 16	0.802 9	0.676 8	0.921 14	0.881 4	0.779 1

StratifiedFormer	0.747 8	0.901 4	0.803 12	0.845 8	0.757 4	0.846 11	0.512 13	0.825 16	0.696 3	0.645 9	0.956 11	0.576 7	0.262 37	0.744 14	0.861 12	0.742 9	0.770 27	0.705 3	0.899 25	0.860 11	0.734 4
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 9	0.870 9	0.838 2	0.858 4	0.729 12	0.850 10	0.501 16	0.874 7	0.587 33	0.658 7	0.956 11	0.564 10	0.299 19	0.765 8	0.900 5	0.716 19	0.812 6	0.631 21	0.939 8	0.858 12	0.709 14
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)
SparseConvNet	0.725 15	0.647 67	0.821 5	0.846 7	0.721 14	0.869 3	0.533 8	0.754 35	0.603 28	0.614 17	0.955 15	0.572 8	0.325 10	0.710 16	0.870 10	0.724 14	0.823 2	0.628 22	0.934 11	0.865 10	0.683 19

EQ-Net	0.743 12	0.620 72	0.799 14	0.849 5	0.730 11	0.822 26	0.493 22	0.897 4	0.664 9	0.681 4	0.955 15	0.562 11	0.378 1	0.760 10	0.903 4	0.738 10	0.801 10	0.673 10	0.907 18	0.877 5	0.745 2
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
VI-PointConv	0.676 32	0.770 36	0.754 34	0.783 29	0.621 38	0.814 36	0.552 4	0.758 33	0.571 41	0.557 33	0.954 17	0.529 17	0.268 35	0.530 56	0.682 49	0.675 32	0.719 44	0.603 31	0.888 34	0.833 23	0.665 22
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
MatchingNet	0.724 16	0.812 23	0.812 9	0.810 18	0.735 10	0.834 17	0.495 21	0.860 8	0.572 39	0.602 24	0.954 17	0.512 22	0.280 26	0.757 11	0.845 21	0.725 13	0.780 21	0.606 30	0.937 9	0.851 17	0.700 16

INS-Conv-semantic	0.717 17	0.751 43	0.759 30	0.812 16	0.704 18	0.868 4	0.537 7	0.842 13	0.609 24	0.608 20	0.953 19	0.534 15	0.293 21	0.616 31	0.864 11	0.719 18	0.793 17	0.640 17	0.933 12	0.845 21	0.663 23

PointConv	0.666 35	0.781 29	0.759 30	0.699 49	0.644 33	0.822 26	0.475 25	0.779 28	0.564 44	0.504 53	0.953 19	0.428 54	0.203 57	0.586 38	0.754 35	0.661 38	0.753 33	0.588 41	0.902 22	0.813 35	0.642 30
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointMRNet	0.640 44	0.717 56	0.701 55	0.692 52	0.576 53	0.801 45	0.467 31	0.716 46	0.563 45	0.459 63	0.953 19	0.429 53	0.169 70	0.581 39	0.854 15	0.605 57	0.710 47	0.550 55	0.894 29	0.793 48	0.575 54

APCF-Net	0.631 53	0.742 47	0.687 67	0.672 57	0.557 60	0.792 54	0.408 57	0.665 59	0.545 48	0.508 50	0.952 22	0.428 54	0.186 64	0.634 26	0.702 46	0.620 52	0.706 51	0.555 53	0.873 46	0.798 42	0.581 52
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointASNL	0.666 35	0.703 59	0.781 22	0.751 40	0.655 27	0.830 19	0.471 27	0.769 31	0.474 68	0.537 39	0.951 23	0.475 32	0.279 27	0.635 25	0.698 48	0.675 32	0.751 34	0.553 54	0.816 66	0.806 37	0.703 15
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
SConv	0.636 48	0.830 18	0.697 58	0.752 39	0.572 56	0.780 59	0.445 43	0.716 46	0.529 52	0.530 42	0.951 23	0.446 48	0.170 69	0.507 62	0.666 53	0.636 49	0.682 60	0.541 61	0.886 35	0.799 40	0.594 50

MinkowskiNet	0.736 13	0.859 12	0.818 7	0.832 12	0.709 16	0.840 12	0.521 12	0.853 9	0.660 11	0.643 11	0.951 23	0.544 14	0.286 25	0.731 15	0.893 6	0.675 32	0.772 25	0.683 7	0.874 45	0.852 16	0.727 7
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
joint point-based	0.634 50	0.614 73	0.778 23	0.667 61	0.633 37	0.825 23	0.420 54	0.804 23	0.467 70	0.561 32	0.951 23	0.494 26	0.291 22	0.566 44	0.458 70	0.579 67	0.764 29	0.559 51	0.838 60	0.814 33	0.598 48
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
ROSMRF3D	0.673 33	0.789 27	0.748 36	0.763 36	0.635 36	0.814 36	0.407 59	0.747 37	0.581 37	0.573 30	0.950 27	0.484 28	0.271 32	0.607 33	0.754 35	0.649 42	0.774 24	0.596 34	0.883 36	0.823 28	0.606 43

FusionNet	0.688 26	0.704 57	0.741 43	0.754 38	0.656 26	0.829 20	0.501 16	0.741 40	0.609 24	0.548 35	0.950 27	0.522 20	0.371 2	0.633 27	0.756 34	0.715 20	0.771 26	0.623 23	0.861 55	0.814 33	0.658 24
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PPCNN++	0.663 37	0.746 44	0.708 51	0.722 42	0.638 35	0.820 29	0.451 36	0.566 73	0.599 30	0.541 37	0.950 27	0.510 23	0.313 14	0.648 22	0.819 26	0.616 56	0.682 60	0.590 39	0.869 51	0.810 36	0.656 25
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
SIConv	0.625 59	0.830 18	0.694 60	0.757 37	0.563 58	0.772 63	0.448 40	0.647 62	0.520 54	0.509 49	0.949 30	0.431 52	0.191 62	0.496 64	0.614 58	0.647 45	0.672 65	0.535 64	0.876 42	0.783 56	0.571 55

MCCNN	0.633 51	0.866 10	0.731 46	0.771 31	0.576 53	0.809 40	0.410 56	0.684 54	0.497 60	0.491 55	0.949 30	0.466 36	0.105 83	0.581 39	0.646 56	0.620 52	0.680 62	0.542 60	0.817 65	0.795 44	0.618 38
P. Hermosilla, T. Ritschel, P.P. Vazquez, A. Vinacua, T. Ropinski: Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds. SIGGRAPH Asia 2018
PointMTL	0.632 52	0.731 51	0.688 65	0.675 56	0.591 46	0.784 56	0.444 46	0.565 74	0.610 22	0.492 54	0.949 30	0.456 41	0.254 39	0.587 36	0.706 45	0.599 60	0.665 67	0.612 29	0.868 52	0.791 54	0.579 53

CU-Hybrid Net	0.693 23	0.596 76	0.789 20	0.803 22	0.677 23	0.800 46	0.469 28	0.846 12	0.554 47	0.591 27	0.948 33	0.500 25	0.316 13	0.609 32	0.847 20	0.732 11	0.808 7	0.593 37	0.894 29	0.839 22	0.652 27

FPConv	0.639 45	0.785 28	0.760 29	0.713 47	0.603 42	0.798 49	0.392 64	0.534 78	0.603 28	0.524 45	0.948 33	0.457 40	0.250 40	0.538 54	0.723 42	0.598 61	0.696 55	0.614 26	0.872 48	0.799 40	0.567 58
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
Virtual MVFusion	0.746 9	0.771 34	0.819 6	0.848 6	0.702 19	0.865 5	0.397 62	0.899 3	0.699 2	0.664 6	0.948 33	0.588 6	0.330 8	0.746 13	0.851 18	0.764 6	0.796 14	0.704 4	0.935 10	0.866 9	0.728 5
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
AttAN	0.609 62	0.760 39	0.667 69	0.649 67	0.521 65	0.793 52	0.457 35	0.648 61	0.528 53	0.434 70	0.947 36	0.401 64	0.153 76	0.454 69	0.721 43	0.648 44	0.717 45	0.536 63	0.904 20	0.765 63	0.485 75
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
RFCR	0.702 19	0.889 6	0.745 39	0.813 15	0.672 24	0.818 33	0.493 22	0.815 20	0.623 18	0.610 18	0.947 36	0.470 34	0.249 42	0.594 35	0.848 19	0.705 23	0.779 22	0.646 14	0.892 31	0.823 28	0.611 39
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
PD-Net	0.638 46	0.797 25	0.769 27	0.641 71	0.590 47	0.820 29	0.461 33	0.537 77	0.637 15	0.536 40	0.947 36	0.388 67	0.206 54	0.656 19	0.668 52	0.647 45	0.732 41	0.585 42	0.868 52	0.793 48	0.473 79

Pointnet++ & Feature	0.557 72	0.735 49	0.661 71	0.686 53	0.491 69	0.744 71	0.392 64	0.539 76	0.451 74	0.375 76	0.946 39	0.376 69	0.205 55	0.403 75	0.356 79	0.553 71	0.643 72	0.497 70	0.824 64	0.756 66	0.515 71

Superpoint Network	0.683 30	0.851 14	0.728 48	0.800 24	0.653 28	0.806 42	0.468 29	0.804 23	0.572 39	0.602 24	0.946 39	0.453 44	0.239 45	0.519 58	0.822 24	0.689 30	0.762 30	0.595 36	0.895 28	0.827 26	0.630 35

HPEIN	0.618 60	0.729 52	0.668 68	0.647 68	0.597 45	0.766 64	0.414 55	0.680 55	0.520 54	0.525 44	0.946 39	0.432 50	0.215 51	0.493 65	0.599 59	0.638 48	0.617 76	0.570 45	0.897 26	0.806 37	0.605 45
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
Feature_GeometricNet	0.690 25	0.884 7	0.754 34	0.795 25	0.647 30	0.818 33	0.422 53	0.802 25	0.612 21	0.604 22	0.945 42	0.462 38	0.189 63	0.563 46	0.853 16	0.726 12	0.765 28	0.632 20	0.904 20	0.821 31	0.606 43
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
VACNN++	0.684 28	0.728 53	0.757 33	0.776 30	0.690 20	0.804 44	0.464 32	0.816 18	0.577 38	0.587 29	0.945 42	0.508 24	0.276 28	0.671 17	0.710 44	0.663 37	0.750 35	0.589 40	0.881 39	0.832 24	0.653 26

contrastBoundary	0.705 18	0.769 37	0.775 24	0.809 19	0.687 21	0.820 29	0.439 49	0.812 22	0.661 10	0.591 27	0.945 42	0.515 21	0.171 68	0.633 27	0.856 14	0.720 16	0.796 14	0.668 11	0.889 33	0.847 19	0.689 18
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RandLA-Net	0.645 41	0.778 30	0.731 46	0.699 49	0.577 52	0.829 20	0.446 41	0.736 41	0.477 67	0.523 47	0.945 42	0.454 42	0.269 33	0.484 67	0.749 38	0.618 54	0.738 37	0.599 33	0.827 62	0.792 51	0.621 37

Feature-Geometry Net	0.685 27	0.866 10	0.748 36	0.819 14	0.645 32	0.794 51	0.450 39	0.802 25	0.587 33	0.604 22	0.945 42	0.464 37	0.201 58	0.554 49	0.840 22	0.723 15	0.732 41	0.602 32	0.907 18	0.822 30	0.603 46

HPGCNN	0.656 39	0.698 60	0.743 41	0.650 66	0.564 57	0.820 29	0.505 15	0.758 33	0.631 17	0.479 58	0.945 42	0.480 30	0.226 46	0.572 42	0.774 33	0.690 28	0.735 39	0.614 26	0.853 58	0.776 60	0.597 49
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
PointNet2-SFPN	0.631 53	0.771 34	0.692 62	0.672 57	0.524 64	0.837 14	0.440 48	0.706 51	0.538 50	0.446 65	0.944 48	0.421 59	0.219 49	0.552 50	0.751 37	0.591 63	0.737 38	0.543 59	0.901 24	0.768 62	0.557 62

PointCNN with RGB	0.458 81	0.577 78	0.611 81	0.356 91	0.321 88	0.715 74	0.299 81	0.376 85	0.328 88	0.319 82	0.944 48	0.285 82	0.164 72	0.216 89	0.229 84	0.484 77	0.545 83	0.456 79	0.755 72	0.709 77	0.475 78
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
PointConv-SFPN	0.641 42	0.776 32	0.703 53	0.721 43	0.557 60	0.826 22	0.451 36	0.672 58	0.563 45	0.483 57	0.943 50	0.425 57	0.162 73	0.644 23	0.726 40	0.659 39	0.709 49	0.572 44	0.875 43	0.786 55	0.559 61

SAFNet-seg	0.654 40	0.752 42	0.734 45	0.664 62	0.583 51	0.815 35	0.399 61	0.754 35	0.639 14	0.535 41	0.942 51	0.470 34	0.309 16	0.665 18	0.539 62	0.650 41	0.708 50	0.635 19	0.857 57	0.793 48	0.642 30
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
PointSPNet	0.637 47	0.734 50	0.692 62	0.714 46	0.576 53	0.797 50	0.446 41	0.743 39	0.598 31	0.437 68	0.942 51	0.403 63	0.150 77	0.626 29	0.800 30	0.649 42	0.697 54	0.557 52	0.846 59	0.777 59	0.563 59

DCM-Net	0.658 38	0.778 30	0.702 54	0.806 21	0.619 39	0.813 39	0.468 29	0.693 53	0.494 61	0.524 45	0.941 53	0.449 46	0.298 20	0.510 60	0.821 25	0.675 32	0.727 43	0.568 47	0.826 63	0.803 39	0.637 32
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
PCNN	0.498 79	0.559 79	0.644 76	0.560 80	0.420 79	0.711 75	0.229 87	0.414 81	0.436 77	0.352 80	0.941 53	0.324 78	0.155 75	0.238 86	0.387 78	0.493 75	0.529 85	0.509 66	0.813 67	0.751 68	0.504 73

DPC	0.592 65	0.720 54	0.700 56	0.602 76	0.480 70	0.762 67	0.380 70	0.713 49	0.585 36	0.437 68	0.940 55	0.369 70	0.288 23	0.434 72	0.509 68	0.590 65	0.639 74	0.567 48	0.772 71	0.755 67	0.592 51
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
LAP-D	0.594 64	0.720 54	0.692 62	0.637 72	0.456 74	0.773 62	0.391 66	0.730 43	0.587 33	0.445 67	0.940 55	0.381 68	0.288 23	0.434 72	0.453 72	0.591 63	0.649 69	0.581 43	0.777 70	0.749 69	0.610 41

PointMRNet-lite	0.553 73	0.633 69	0.648 73	0.659 63	0.430 77	0.800 46	0.390 67	0.592 69	0.454 73	0.371 77	0.939 57	0.368 71	0.136 80	0.368 77	0.448 73	0.560 70	0.715 46	0.486 73	0.882 37	0.720 76	0.462 80

DenSeR	0.628 57	0.800 24	0.625 78	0.719 44	0.545 62	0.806 42	0.445 43	0.597 67	0.448 75	0.519 48	0.938 58	0.481 29	0.328 9	0.489 66	0.499 69	0.657 40	0.759 31	0.592 38	0.881 39	0.797 43	0.634 33

DGCNN_reproduce	0.446 83	0.474 87	0.623 79	0.463 85	0.366 83	0.651 81	0.310 77	0.389 84	0.349 86	0.330 81	0.937 59	0.271 84	0.126 81	0.285 82	0.224 85	0.350 88	0.577 78	0.445 82	0.625 84	0.723 74	0.394 83
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
MVPNet	0.641 42	0.831 17	0.715 49	0.671 59	0.590 47	0.781 57	0.394 63	0.679 56	0.642 13	0.553 34	0.937 59	0.462 38	0.256 38	0.649 21	0.406 76	0.626 51	0.691 57	0.666 12	0.877 41	0.792 51	0.608 42
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
ROSMRF	0.580 67	0.772 33	0.707 52	0.681 55	0.563 58	0.764 65	0.362 72	0.515 79	0.465 71	0.465 62	0.936 61	0.427 56	0.207 53	0.438 70	0.577 60	0.536 72	0.675 64	0.486 73	0.723 77	0.779 57	0.524 70

JSENet	0.699 21	0.881 8	0.762 28	0.821 13	0.667 25	0.800 46	0.522 11	0.792 27	0.613 20	0.607 21	0.935 62	0.492 27	0.205 55	0.576 41	0.853 16	0.691 27	0.758 32	0.652 13	0.872 48	0.828 25	0.649 28
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
SPH3D-GCN	0.610 61	0.858 13	0.772 25	0.489 83	0.532 63	0.792 54	0.404 60	0.643 63	0.570 42	0.507 52	0.935 62	0.414 61	0.046 89	0.510 60	0.702 46	0.602 59	0.705 52	0.549 56	0.859 56	0.773 61	0.534 68
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
TextureNet	0.566 70	0.672 64	0.664 70	0.671 59	0.494 68	0.719 73	0.445 43	0.678 57	0.411 81	0.396 73	0.935 62	0.356 73	0.225 47	0.412 74	0.535 63	0.565 69	0.636 75	0.464 77	0.794 69	0.680 81	0.568 57
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
KP-FCNN	0.684 28	0.847 15	0.758 32	0.784 28	0.647 30	0.814 36	0.473 26	0.772 30	0.605 26	0.594 26	0.935 62	0.450 45	0.181 66	0.587 36	0.805 29	0.690 28	0.785 20	0.614 26	0.882 37	0.819 32	0.632 34
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
PointContrast_LA_SEM	0.683 30	0.757 41	0.784 21	0.786 27	0.639 34	0.824 24	0.408 57	0.775 29	0.604 27	0.541 37	0.934 66	0.532 16	0.269 33	0.552 50	0.777 32	0.645 47	0.793 17	0.640 17	0.913 16	0.824 27	0.671 21

wsss-transformer	0.600 63	0.634 68	0.743 41	0.697 51	0.601 44	0.781 57	0.437 50	0.585 71	0.493 62	0.446 65	0.933 67	0.394 65	0.011 91	0.654 20	0.661 55	0.603 58	0.733 40	0.526 65	0.832 61	0.761 65	0.480 76

subcloud_weak	0.516 76	0.676 62	0.591 85	0.609 73	0.442 75	0.774 61	0.335 75	0.597 67	0.422 80	0.357 79	0.932 68	0.341 76	0.094 85	0.298 81	0.528 66	0.473 79	0.676 63	0.495 71	0.602 86	0.721 75	0.349 87

SegGroup_sem	0.627 58	0.818 21	0.747 38	0.701 48	0.602 43	0.764 65	0.385 69	0.629 64	0.490 63	0.508 50	0.931 69	0.409 62	0.201 58	0.564 45	0.725 41	0.618 54	0.692 56	0.539 62	0.873 46	0.794 46	0.548 65
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
Supervoxel-CNN	0.635 49	0.656 65	0.711 50	0.719 44	0.613 40	0.757 68	0.444 46	0.765 32	0.534 51	0.566 31	0.928 70	0.478 31	0.272 30	0.636 24	0.531 64	0.664 36	0.645 71	0.508 68	0.864 54	0.792 51	0.611 39

SPLAT Net	0.393 88	0.472 88	0.511 88	0.606 74	0.311 89	0.656 79	0.245 86	0.405 82	0.328 88	0.197 90	0.927 71	0.227 89	0.000 93	0.001 93	0.249 83	0.271 91	0.510 86	0.383 89	0.593 87	0.699 79	0.267 89
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
SurfaceConvPF	0.442 84	0.505 83	0.622 80	0.380 90	0.342 86	0.654 80	0.227 88	0.397 83	0.367 84	0.276 86	0.924 72	0.240 87	0.198 60	0.359 78	0.262 82	0.366 85	0.581 77	0.435 84	0.640 83	0.668 82	0.398 82
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
SALANet	0.670 34	0.816 22	0.770 26	0.768 33	0.652 29	0.807 41	0.451 36	0.747 37	0.659 12	0.545 36	0.924 72	0.473 33	0.149 78	0.571 43	0.811 28	0.635 50	0.746 36	0.623 23	0.892 31	0.794 46	0.570 56

CCRFNet	0.589 66	0.766 38	0.659 72	0.683 54	0.470 73	0.740 72	0.387 68	0.620 66	0.490 63	0.476 59	0.922 74	0.355 74	0.245 43	0.511 59	0.511 67	0.571 68	0.643 72	0.493 72	0.872 48	0.762 64	0.600 47

FCPN	0.447 82	0.679 61	0.604 84	0.578 79	0.380 81	0.682 78	0.291 82	0.106 91	0.483 66	0.258 89	0.920 75	0.258 86	0.025 90	0.231 88	0.325 80	0.480 78	0.560 81	0.463 78	0.725 76	0.666 83	0.231 91
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
FusionAwareConv	0.630 56	0.604 75	0.741 43	0.766 35	0.590 47	0.747 70	0.501 16	0.734 42	0.503 59	0.527 43	0.919 76	0.454 42	0.323 11	0.550 53	0.420 75	0.678 31	0.688 58	0.544 57	0.896 27	0.795 44	0.627 36
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
Tangent Convolutions	0.438 86	0.437 89	0.646 75	0.474 84	0.369 82	0.645 82	0.353 73	0.258 88	0.282 90	0.279 85	0.918 77	0.298 81	0.147 79	0.283 83	0.294 81	0.487 76	0.562 80	0.427 85	0.619 85	0.633 85	0.352 86
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DMV, FTSDF	0.501 78	0.558 80	0.608 83	0.424 89	0.478 71	0.690 76	0.246 85	0.586 70	0.468 69	0.450 64	0.911 78	0.394 65	0.160 74	0.438 70	0.212 86	0.432 82	0.541 84	0.475 76	0.742 74	0.727 73	0.477 77

SSC-UNet	0.308 91	0.353 90	0.290 92	0.278 92	0.166 92	0.553 89	0.169 91	0.286 87	0.147 92	0.148 92	0.908 79	0.182 91	0.064 88	0.023 92	0.018 93	0.354 87	0.363 90	0.345 90	0.546 90	0.685 80	0.278 88

DVVNet	0.562 71	0.648 66	0.700 56	0.770 32	0.586 50	0.687 77	0.333 76	0.650 60	0.514 57	0.475 60	0.906 80	0.359 72	0.223 48	0.340 79	0.442 74	0.422 83	0.668 66	0.501 69	0.708 78	0.779 57	0.534 68

ScanNet+FTSDF	0.383 89	0.297 91	0.491 89	0.432 88	0.358 85	0.612 87	0.274 83	0.116 90	0.411 81	0.265 87	0.904 81	0.229 88	0.079 87	0.250 84	0.185 89	0.320 89	0.510 86	0.385 88	0.548 88	0.597 90	0.394 83

GMLPs	0.538 74	0.495 84	0.693 61	0.647 68	0.471 72	0.793 52	0.300 79	0.477 80	0.505 58	0.358 78	0.903 82	0.327 77	0.081 86	0.472 68	0.529 65	0.448 81	0.710 47	0.509 66	0.746 73	0.737 71	0.554 64

SQN_0.1%	0.569 69	0.676 62	0.696 59	0.657 64	0.497 67	0.779 60	0.424 52	0.548 75	0.515 56	0.376 75	0.902 83	0.422 58	0.357 3	0.379 76	0.456 71	0.596 62	0.659 68	0.544 57	0.685 80	0.665 84	0.556 63

PNET2	0.442 84	0.548 81	0.548 86	0.597 77	0.363 84	0.628 86	0.300 79	0.292 86	0.374 83	0.307 83	0.881 84	0.268 85	0.186 64	0.238 86	0.204 88	0.407 84	0.506 89	0.449 80	0.667 82	0.620 86	0.462 80

SD-DETR	0.576 68	0.746 44	0.609 82	0.445 87	0.517 66	0.643 83	0.366 71	0.714 48	0.456 72	0.468 61	0.870 85	0.432 50	0.264 36	0.558 48	0.674 50	0.586 66	0.688 58	0.482 75	0.739 75	0.733 72	0.537 67

3DSM_DMMF	0.631 53	0.626 70	0.745 39	0.801 23	0.607 41	0.751 69	0.506 14	0.729 44	0.565 43	0.491 55	0.866 86	0.434 49	0.197 61	0.595 34	0.630 57	0.709 22	0.705 52	0.560 49	0.875 43	0.740 70	0.491 74

PanopticFusion-label	0.529 75	0.491 85	0.688 65	0.604 75	0.386 80	0.632 84	0.225 89	0.705 52	0.434 78	0.293 84	0.815 87	0.348 75	0.241 44	0.499 63	0.669 51	0.507 74	0.649 69	0.442 83	0.796 68	0.602 87	0.561 60
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3DMV	0.484 80	0.484 86	0.538 87	0.643 70	0.424 78	0.606 88	0.310 77	0.574 72	0.433 79	0.378 74	0.796 88	0.301 80	0.214 52	0.537 55	0.208 87	0.472 80	0.507 88	0.413 86	0.693 79	0.602 87	0.539 66
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
ScanNet	0.306 92	0.203 92	0.366 91	0.501 82	0.311 89	0.524 90	0.211 90	0.002 93	0.342 87	0.189 91	0.786 89	0.145 92	0.102 84	0.245 85	0.152 90	0.318 90	0.348 91	0.300 91	0.460 91	0.437 92	0.182 92
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
Online SegFusion	0.515 77	0.607 74	0.644 76	0.579 78	0.434 76	0.630 85	0.353 73	0.628 65	0.440 76	0.410 71	0.762 90	0.307 79	0.167 71	0.520 57	0.403 77	0.516 73	0.565 79	0.447 81	0.678 81	0.701 78	0.514 72
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
PointNet++	0.339 90	0.584 77	0.478 90	0.458 86	0.256 91	0.360 92	0.250 84	0.247 89	0.278 91	0.261 88	0.677 91	0.183 90	0.117 82	0.212 90	0.145 91	0.364 86	0.346 92	0.232 92	0.548 88	0.523 91	0.252 90
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
3DWSSS	0.425 87	0.525 82	0.647 74	0.522 81	0.324 87	0.488 91	0.077 92	0.712 50	0.353 85	0.401 72	0.636 92	0.281 83	0.176 67	0.340 79	0.565 61	0.175 92	0.551 82	0.398 87	0.370 92	0.602 87	0.361 85

ERROR	0.054 93	0.000 93	0.041 93	0.172 93	0.030 93	0.062 93	0.001 93	0.035 92	0.004 93	0.051 93	0.143 93	0.019 93	0.003 92	0.041 91	0.050 92	0.003 93	0.054 93	0.018 93	0.005 93	0.264 93	0.082 93

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

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

Mask3D	0.780 1	1.000 1	0.786 21	0.716 20	0.696 3	0.885 3	0.500 2	0.714 17	0.810 1	0.672 3	0.715 3	0.679 6	0.809 1	1.000 1	0.831 1	0.833 7	0.787 3	1.000 1	0.602 4

SPFormer	0.770 2	0.903 32	0.903 1	0.806 8	0.609 11	0.886 2	0.568 1	0.815 6	0.705 3	0.711 1	0.655 4	0.652 8	0.685 8	1.000 1	0.789 3	0.809 10	0.776 4	1.000 1	0.583 7

SoftGroup++	0.769 3	1.000 1	0.803 16	0.937 1	0.684 4	0.865 5	0.213 15	0.870 2	0.664 4	0.571 6	0.758 1	0.702 4	0.807 2	1.000 1	0.653 14	0.902 1	0.792 2	1.000 1	0.626 1

SoftGroup	0.761 4	1.000 1	0.808 13	0.845 6	0.716 1	0.862 7	0.243 12	0.824 3	0.655 6	0.620 4	0.734 2	0.699 5	0.791 4	0.981 21	0.716 6	0.844 4	0.769 5	1.000 1	0.594 6
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
GraphCut	0.732 5	1.000 1	0.788 19	0.724 19	0.642 7	0.859 8	0.248 11	0.787 10	0.618 10	0.596 5	0.653 6	0.722 2	0.583 25	1.000 1	0.766 4	0.861 2	0.825 1	1.000 1	0.504 17

IPCA-Inst	0.731 6	1.000 1	0.788 20	0.884 5	0.698 2	0.788 22	0.252 10	0.760 12	0.646 7	0.511 14	0.637 8	0.665 7	0.804 3	1.000 1	0.644 15	0.778 12	0.747 7	1.000 1	0.561 12

TopoSeg	0.725 7	1.000 1	0.806 15	0.933 2	0.668 6	0.758 25	0.272 8	0.734 16	0.630 8	0.549 10	0.654 5	0.606 9	0.697 7	0.966 23	0.612 18	0.839 5	0.754 6	1.000 1	0.573 8

DKNet	0.718 8	1.000 1	0.814 10	0.782 11	0.619 8	0.872 4	0.224 13	0.751 14	0.569 12	0.677 2	0.585 11	0.724 1	0.633 17	0.981 21	0.515 25	0.819 8	0.736 8	1.000 1	0.617 2
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
SSEC	0.700 9	1.000 1	0.848 5	0.763 17	0.609 12	0.792 20	0.262 9	0.824 3	0.627 9	0.535 12	0.547 19	0.493 15	0.600 19	1.000 1	0.712 8	0.731 24	0.689 12	1.000 1	0.563 11

HAIS	0.699 10	1.000 1	0.849 4	0.820 7	0.675 5	0.808 15	0.279 6	0.757 13	0.465 17	0.517 13	0.596 9	0.559 11	0.600 19	1.000 1	0.654 13	0.767 14	0.676 13	0.994 28	0.560 13
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNet	0.698 11	1.000 1	0.697 36	0.888 4	0.556 18	0.803 16	0.387 4	0.626 24	0.417 21	0.556 9	0.585 12	0.702 3	0.600 19	1.000 1	0.824 2	0.720 26	0.692 10	1.000 1	0.509 16
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SphereSeg	0.680 12	1.000 1	0.856 3	0.744 18	0.618 9	0.893 1	0.151 17	0.651 22	0.713 2	0.537 11	0.579 14	0.430 23	0.651 9	1.000 1	0.389 34	0.744 21	0.697 9	0.991 29	0.601 5

Box2Mask	0.677 13	1.000 1	0.847 6	0.771 13	0.509 24	0.816 11	0.277 7	0.558 31	0.482 14	0.562 8	0.640 7	0.448 19	0.700 5	1.000 1	0.666 9	0.852 3	0.578 24	0.997 23	0.488 21
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
OccuSeg+instance	0.672 14	1.000 1	0.758 28	0.682 22	0.576 16	0.842 9	0.477 3	0.504 34	0.524 13	0.567 7	0.585 13	0.451 18	0.557 26	1.000 1	0.751 5	0.797 11	0.563 27	1.000 1	0.467 24
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group	0.664 15	1.000 1	0.822 9	0.764 16	0.616 10	0.815 12	0.139 21	0.694 19	0.597 11	0.459 19	0.566 15	0.599 10	0.600 19	0.516 40	0.715 7	0.819 9	0.635 17	1.000 1	0.603 3
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
INS-Conv-instance	0.657 16	1.000 1	0.760 26	0.667 24	0.581 14	0.863 6	0.323 5	0.655 21	0.477 15	0.473 17	0.549 17	0.432 22	0.650 10	1.000 1	0.655 12	0.738 22	0.585 23	0.944 33	0.472 23

CSC-Pretrained	0.648 17	1.000 1	0.810 11	0.768 14	0.523 23	0.813 13	0.143 20	0.819 5	0.389 22	0.422 26	0.511 22	0.443 20	0.650 10	1.000 1	0.624 17	0.732 23	0.634 18	1.000 1	0.375 30

PE	0.645 18	1.000 1	0.773 23	0.798 10	0.538 20	0.786 23	0.088 28	0.799 9	0.350 26	0.435 25	0.547 18	0.545 12	0.646 16	0.933 24	0.562 21	0.761 17	0.556 32	0.997 23	0.501 19
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN	0.643 19	1.000 1	0.758 27	0.582 32	0.539 19	0.826 10	0.046 32	0.765 11	0.372 24	0.436 24	0.588 10	0.539 14	0.650 10	1.000 1	0.577 19	0.750 19	0.653 16	0.997 23	0.495 20

Dyco3D	0.641 20	1.000 1	0.841 7	0.893 3	0.531 21	0.802 17	0.115 25	0.588 29	0.448 18	0.438 22	0.537 21	0.430 24	0.550 27	0.857 26	0.534 23	0.764 16	0.657 14	0.987 30	0.568 9
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN	0.638 21	1.000 1	0.895 2	0.800 9	0.480 27	0.676 29	0.144 19	0.737 15	0.354 25	0.447 20	0.400 31	0.365 29	0.700 5	1.000 1	0.569 20	0.836 6	0.599 20	1.000 1	0.473 22

PointGroup	0.636 22	1.000 1	0.765 24	0.624 26	0.505 26	0.797 18	0.116 24	0.696 18	0.384 23	0.441 21	0.559 16	0.476 16	0.596 23	1.000 1	0.666 9	0.756 18	0.556 31	0.997 23	0.513 15
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
DD-UNet+Group	0.635 23	0.667 33	0.797 18	0.714 21	0.562 17	0.774 24	0.146 18	0.810 8	0.429 20	0.476 16	0.546 20	0.399 26	0.633 17	1.000 1	0.632 16	0.722 25	0.609 19	1.000 1	0.514 14
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
DENet	0.629 24	1.000 1	0.797 17	0.608 27	0.589 13	0.627 33	0.219 14	0.882 1	0.310 28	0.402 30	0.383 33	0.396 27	0.650 10	1.000 1	0.663 11	0.543 41	0.691 11	1.000 1	0.568 10

3D-MPA	0.611 25	1.000 1	0.833 8	0.765 15	0.526 22	0.756 26	0.136 23	0.588 29	0.470 16	0.438 23	0.432 29	0.358 30	0.650 10	0.857 26	0.429 30	0.765 15	0.557 30	1.000 1	0.430 26
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
PCJC	0.578 26	1.000 1	0.810 12	0.583 31	0.449 30	0.813 14	0.042 33	0.603 27	0.341 27	0.490 15	0.465 25	0.410 25	0.650 10	0.835 32	0.264 39	0.694 30	0.561 28	0.889 37	0.504 18

SSEN	0.575 27	1.000 1	0.761 25	0.473 34	0.477 28	0.795 19	0.066 29	0.529 32	0.658 5	0.460 18	0.461 26	0.380 28	0.331 39	0.859 25	0.401 33	0.692 31	0.653 15	1.000 1	0.348 32
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RWSeg	0.567 28	0.528 42	0.708 35	0.626 25	0.580 15	0.745 27	0.063 30	0.627 23	0.240 32	0.400 31	0.497 23	0.464 17	0.515 28	1.000 1	0.475 27	0.745 20	0.571 25	1.000 1	0.429 27

MTML	0.549 29	1.000 1	0.807 14	0.588 30	0.327 35	0.647 31	0.004 38	0.815 7	0.180 34	0.418 27	0.364 35	0.182 34	0.445 32	1.000 1	0.442 29	0.688 32	0.571 26	1.000 1	0.396 28
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
One_Thing_One_Click	0.529 30	0.667 33	0.718 31	0.777 12	0.399 31	0.683 28	0.000 41	0.669 20	0.138 37	0.391 32	0.374 34	0.539 13	0.360 38	0.641 37	0.556 22	0.774 13	0.593 21	0.997 23	0.251 37
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Sparse R-CNN	0.515 31	1.000 1	0.538 43	0.282 37	0.468 29	0.790 21	0.173 16	0.345 39	0.429 19	0.413 29	0.484 24	0.176 35	0.595 24	0.591 38	0.522 24	0.668 33	0.476 36	0.986 31	0.327 33

Occipital-SCS	0.512 32	1.000 1	0.716 32	0.509 33	0.506 25	0.611 34	0.092 27	0.602 28	0.177 35	0.346 35	0.383 32	0.165 36	0.442 33	0.850 31	0.386 35	0.618 37	0.543 33	0.889 37	0.389 29

3D-BoNet	0.488 33	1.000 1	0.672 38	0.590 29	0.301 37	0.484 44	0.098 26	0.620 25	0.306 29	0.341 36	0.259 39	0.125 38	0.434 35	0.796 33	0.402 32	0.499 43	0.513 35	0.909 36	0.439 25
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
PanopticFusion-inst	0.478 34	0.667 33	0.712 34	0.595 28	0.259 40	0.550 40	0.000 41	0.613 26	0.175 36	0.250 41	0.434 27	0.437 21	0.411 37	0.857 26	0.485 26	0.591 40	0.267 46	0.944 33	0.359 31
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
SPG_WSIS	0.470 35	0.667 33	0.685 37	0.677 23	0.372 33	0.562 38	0.000 41	0.482 35	0.244 31	0.316 38	0.298 36	0.052 44	0.442 34	0.857 26	0.267 38	0.702 27	0.559 29	1.000 1	0.287 35

SALoss-ResNet	0.459 36	1.000 1	0.737 30	0.159 47	0.259 39	0.587 36	0.138 22	0.475 36	0.217 33	0.416 28	0.408 30	0.128 37	0.315 40	0.714 34	0.411 31	0.536 42	0.590 22	0.873 40	0.304 34
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
MASC	0.447 37	0.528 42	0.555 41	0.381 35	0.382 32	0.633 32	0.002 39	0.509 33	0.260 30	0.361 34	0.432 28	0.327 31	0.451 31	0.571 39	0.367 36	0.639 35	0.386 37	0.980 32	0.276 36
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_ins	0.445 38	0.667 33	0.773 22	0.185 44	0.317 36	0.656 30	0.000 41	0.407 38	0.134 38	0.381 33	0.267 38	0.217 33	0.476 30	0.714 34	0.452 28	0.629 36	0.514 34	1.000 1	0.222 40
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
3D-SIS	0.382 39	1.000 1	0.432 45	0.245 39	0.190 41	0.577 37	0.013 36	0.263 41	0.033 44	0.320 37	0.240 40	0.075 40	0.422 36	0.857 26	0.117 43	0.699 28	0.271 45	0.883 39	0.235 39
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3D	0.323 40	0.667 33	0.542 42	0.264 38	0.157 44	0.550 39	0.000 41	0.205 44	0.009 45	0.270 40	0.218 41	0.075 40	0.500 29	0.688 36	0.007 49	0.698 29	0.301 42	0.459 46	0.200 41
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone	0.319 41	0.667 33	0.715 33	0.233 40	0.189 42	0.479 45	0.008 37	0.218 42	0.067 43	0.201 43	0.173 42	0.107 39	0.123 45	0.438 41	0.150 41	0.615 38	0.355 38	0.916 35	0.093 48

R-PointNet	0.306 42	0.500 44	0.405 46	0.311 36	0.348 34	0.589 35	0.054 31	0.068 47	0.126 39	0.283 39	0.290 37	0.028 45	0.219 43	0.214 44	0.331 37	0.396 47	0.275 43	0.821 42	0.245 38

Region-18class	0.284 43	0.250 48	0.751 29	0.228 42	0.270 38	0.521 41	0.000 41	0.468 37	0.008 47	0.205 42	0.127 43	0.000 49	0.068 47	0.070 47	0.262 40	0.652 34	0.323 40	0.740 43	0.173 42

SemRegionNet-20cls	0.250 44	0.333 45	0.613 39	0.229 41	0.163 43	0.493 42	0.000 41	0.304 40	0.107 40	0.147 45	0.100 44	0.052 43	0.231 41	0.119 45	0.039 45	0.445 45	0.325 39	0.654 44	0.141 44

3D-BEVIS	0.248 45	0.667 33	0.566 40	0.076 48	0.035 49	0.394 47	0.027 35	0.035 48	0.098 41	0.099 47	0.030 48	0.025 46	0.098 46	0.375 43	0.126 42	0.604 39	0.181 47	0.854 41	0.171 43
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
tmp	0.248 45	0.667 33	0.437 44	0.188 43	0.153 45	0.491 43	0.000 41	0.208 43	0.094 42	0.153 44	0.099 45	0.057 42	0.217 44	0.119 45	0.039 45	0.466 44	0.302 41	0.640 45	0.140 45

ASIS	0.199 47	0.333 45	0.253 48	0.167 46	0.140 46	0.438 46	0.000 41	0.177 45	0.008 46	0.121 46	0.069 46	0.004 48	0.231 42	0.429 42	0.036 47	0.445 46	0.273 44	0.333 48	0.119 47

Sgpn_scannet	0.143 48	0.208 49	0.390 47	0.169 45	0.065 47	0.275 48	0.029 34	0.069 46	0.000 48	0.087 48	0.043 47	0.014 47	0.027 49	0.000 48	0.112 44	0.351 48	0.168 48	0.438 47	0.138 46

MaskRCNN 2d->3d Proj	0.058 49	0.333 45	0.002 49	0.000 49	0.053 48	0.002 49	0.002 40	0.021 49	0.000 48	0.045 49	0.024 49	0.238 32	0.065 48	0.000 48	0.014 48	0.107 49	0.020 49	0.110 49	0.006 49

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

CU-Hybrid-2D Net	0.636 3	0.825 2	0.820 2	0.179 18	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 13	0.732 2	0.723 3	0.599 2	0.827 11	0.851 2	0.634 5

Virtual MVFusion (R)	0.745 1	0.861 1	0.839 1	0.881 1	0.672 1	0.512 1	0.422 14	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 10	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 8	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)
RFBNet	0.592 7	0.616 9	0.758 5	0.659 5	0.581 9	0.330 8	0.469 9	0.655 13	0.543 12	0.524 7	0.924 4	0.355 10	0.336 9	0.572 12	0.479 7	0.671 11	0.648 7	0.480 9	0.814 14	0.814 5	0.614 8

CMX	0.613 4	0.681 7	0.725 8	0.502 11	0.634 5	0.297 15	0.478 8	0.830 2	0.651 4	0.537 6	0.924 4	0.375 5	0.315 10	0.686 5	0.451 10	0.714 4	0.543 17	0.504 5	0.894 4	0.823 4	0.688 3

DCRedNet	0.583 9	0.682 6	0.723 9	0.542 10	0.510 15	0.310 12	0.451 10	0.668 11	0.549 11	0.520 8	0.920 6	0.375 5	0.446 2	0.528 15	0.417 11	0.670 12	0.577 14	0.478 10	0.862 7	0.806 7	0.628 7

AdapNet++	0.503 16	0.613 10	0.722 10	0.418 14	0.358 21	0.337 6	0.370 18	0.479 19	0.443 17	0.368 19	0.907 7	0.207 18	0.213 20	0.464 19	0.525 4	0.618 17	0.657 6	0.450 14	0.788 15	0.721 18	0.408 20
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
MCA-Net	0.595 6	0.533 15	0.756 6	0.746 4	0.590 8	0.334 7	0.506 5	0.670 10	0.587 7	0.500 10	0.905 8	0.366 8	0.352 7	0.601 9	0.506 5	0.669 13	0.648 7	0.501 6	0.839 10	0.769 10	0.516 16

FuseNet	0.535 15	0.570 14	0.681 15	0.182 17	0.512 14	0.290 16	0.431 13	0.659 12	0.504 15	0.495 12	0.903 9	0.308 14	0.428 3	0.523 16	0.365 14	0.676 9	0.621 10	0.470 11	0.762 17	0.779 9	0.541 12
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
MIX6D_RVC	0.582 10	0.695 4	0.687 13	0.225 16	0.632 6	0.328 10	0.550 1	0.748 5	0.623 5	0.494 13	0.890 10	0.350 11	0.254 18	0.688 4	0.454 8	0.716 3	0.597 13	0.489 8	0.881 5	0.768 11	0.575 10

SSMA	0.577 11	0.695 4	0.716 11	0.439 13	0.563 11	0.314 11	0.444 12	0.719 8	0.551 10	0.503 9	0.887 11	0.346 12	0.348 8	0.603 8	0.353 15	0.709 5	0.600 11	0.457 12	0.901 2	0.786 8	0.599 9
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
FAN_NV_RVC	0.586 8	0.510 16	0.764 4	0.079 21	0.620 7	0.330 8	0.494 6	0.753 4	0.573 8	0.556 4	0.884 12	0.405 3	0.303 12	0.718 2	0.452 9	0.672 10	0.658 5	0.509 4	0.898 3	0.813 6	0.727 2

segfomer with 6d	0.542 14	0.594 12	0.687 13	0.146 19	0.579 10	0.308 13	0.515 4	0.703 9	0.472 16	0.498 11	0.868 13	0.369 7	0.282 13	0.589 11	0.390 12	0.701 7	0.556 16	0.416 17	0.860 8	0.759 13	0.539 14

SN_RN152pyrx8_RVC	0.546 12	0.572 13	0.663 16	0.638 7	0.518 13	0.298 14	0.366 19	0.633 16	0.510 14	0.446 16	0.864 14	0.296 15	0.267 15	0.542 14	0.346 16	0.704 6	0.575 15	0.431 15	0.853 9	0.766 12	0.630 6

MSeg1080_RVC	0.485 18	0.505 17	0.709 12	0.092 20	0.427 18	0.241 18	0.411 15	0.654 14	0.385 21	0.457 15	0.861 15	0.053 21	0.279 14	0.503 17	0.481 6	0.645 14	0.626 9	0.365 19	0.748 19	0.725 17	0.529 15
John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
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 16	0.359 9	0.306 11	0.596 10	0.539 2	0.627 16	0.706 4	0.497 7	0.785 16	0.757 14	0.476 17

3DMV (2d proj)	0.498 17	0.481 19	0.612 18	0.579 9	0.456 17	0.343 5	0.384 16	0.623 17	0.525 13	0.381 18	0.845 17	0.254 17	0.264 17	0.557 13	0.182 19	0.581 19	0.598 12	0.429 16	0.760 18	0.661 20	0.446 19
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
UDSSEG_RVC	0.545 13	0.610 11	0.661 17	0.588 8	0.556 12	0.268 17	0.482 7	0.642 15	0.572 9	0.475 14	0.836 18	0.312 13	0.367 6	0.630 7	0.189 18	0.639 15	0.495 19	0.452 13	0.826 12	0.756 15	0.541 12

ScanNet (2d proj)	0.330 21	0.293 20	0.521 20	0.657 6	0.361 20	0.161 20	0.250 20	0.004 21	0.440 18	0.183 21	0.836 18	0.125 20	0.060 21	0.319 21	0.132 20	0.417 20	0.412 20	0.344 20	0.541 21	0.427 21	0.109 21
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ILC-PSPNet	0.475 19	0.490 18	0.581 19	0.289 15	0.507 16	0.067 21	0.379 17	0.610 18	0.417 19	0.435 17	0.822 20	0.278 16	0.267 15	0.503 17	0.228 17	0.616 18	0.533 18	0.375 18	0.820 13	0.729 16	0.560 11

Enet (reimpl)	0.376 20	0.264 21	0.452 21	0.452 12	0.365 19	0.181 19	0.143 21	0.456 20	0.409 20	0.346 20	0.769 21	0.164 19	0.218 19	0.359 20	0.123 21	0.403 21	0.381 21	0.313 21	0.571 20	0.685 19	0.472 18
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
DMMF	0.003 22	0.000 22	0.005 22	0.000 22	0.000 22	0.037 22	0.001 22	0.000 22	0.001 22	0.005 22	0.003 22	0.000 22	0.000 22	0.000 22	0.000 22	0.000 22	0.002 22	0.001 22	0.000 22	0.006 22	0.000 22

Presenting the ScanNet200 Benchmark

ScanNet200 Benchmark

ScanNet200 3D Semantic Label Benchmark

ScanNet200 3D Semantic Instance Benchmark

ScanNet Benchmark

3D Semantic Label Benchmark

3D Semantic Instance Benchmark

2D Semantic Label Benchmark

2D Semantic Instance Benchmark

Scene Type Classification Benchmark

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

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

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

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

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

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