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
Minkowski 34D	0.253 2	0.463 2	0.154 2	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
CSC-Pretrain	0.249 3	0.455 3	0.171 3	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

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

Method	Info	avg ap 50%	head ap 50%	common ap 50%	tail ap 50%	alarm clock	armchair	backpack	bag	ball	bar	basket	bathroom cabinet	bathroom counter	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	cd case	ceiling	ceiling light	chair	clock	closet	closet door	closet rod	closet wall	clothes	clothes dryer	coat rack	coffee kettle	coffee maker	coffee table	column	computer tower	container	copier	couch	counter	crate	cup	curtain	cushion	decoration	desk	dining table	dish rack	dishwasher	divider	door	doorframe	dresser	dumbbell	dustpan	end table	fan	file cabinet	fire alarm	fire extinguisher	fireplace	folded chair	furniture	guitar	guitar case	hair dryer	handicap bar	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	luggage	machine	mailbox	mat	mattress	microwave	mini fridge	mirror	monitor	mouse	music stand	nightstand	object	office chair	ottoman	oven	paper	paper bag	paper cutter	paper towel dispenser	paper towel roll	person	piano	picture	pillar	pillow	pipe	plant	plate	plunger	poster	potted plant	power outlet	power strip	printer	projector	projector screen	purse	rack	radiator	rail	range hood	recycling bin	refrigerator	scale	seat	shelf	shoe	shower	shower curtain	shower curtain rod	shower door	shower floor	shower head	shower wall	sign	sink	soap dish	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	toaster oven	toilet	toilet paper	toilet paper dispenser	toilet paper holder	toilet seat cover 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

No results yet.

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 8	0.781 1	0.858 6	0.575 2	0.831 12	0.685 4	0.714 1	0.979 1	0.594 3	0.310 14	0.801 1	0.892 5	0.841 2	0.819 3	0.723 2	0.940 5	0.887 1	0.725 8
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
PointConvFormer	0.749 4	0.793 24	0.790 15	0.807 17	0.750 5	0.856 7	0.524 8	0.881 3	0.588 29	0.642 10	0.977 4	0.591 5	0.274 27	0.781 2	0.929 1	0.804 3	0.796 11	0.642 13	0.947 3	0.885 2	0.715 10

OccuSeg+Semantic	0.764 2	0.758 38	0.796 12	0.839 9	0.746 6	0.907 1	0.562 3	0.850 7	0.680 5	0.672 3	0.978 2	0.610 1	0.335 7	0.777 3	0.819 22	0.847 1	0.830 1	0.691 6	0.972 1	0.885 2	0.727 6

IPCA	0.731 11	0.890 5	0.837 3	0.864 1	0.726 10	0.873 2	0.530 7	0.824 14	0.489 61	0.647 6	0.978 2	0.609 2	0.336 6	0.624 27	0.733 35	0.758 6	0.776 20	0.570 41	0.949 2	0.877 4	0.728 4

EQ-Net	0.743 9	0.620 67	0.799 11	0.849 3	0.730 8	0.822 23	0.493 19	0.897 2	0.664 7	0.681 2	0.955 12	0.562 10	0.378 1	0.760 7	0.903 2	0.738 9	0.801 9	0.673 8	0.907 15	0.877 4	0.745 1
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
O-CNN	0.762 3	0.924 2	0.823 4	0.844 7	0.770 2	0.852 8	0.577 1	0.847 8	0.711 1	0.640 11	0.958 7	0.592 4	0.217 46	0.762 6	0.888 6	0.758 6	0.813 5	0.726 1	0.932 11	0.868 6	0.744 2
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
Virtual MVFusion	0.746 7	0.771 32	0.819 6	0.848 4	0.702 16	0.865 5	0.397 58	0.899 1	0.699 2	0.664 4	0.948 30	0.588 6	0.330 8	0.746 10	0.851 15	0.764 5	0.796 11	0.704 4	0.935 8	0.866 7	0.728 4
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
SparseConvNet	0.725 12	0.647 63	0.821 5	0.846 5	0.721 11	0.869 3	0.533 6	0.754 31	0.603 25	0.614 14	0.955 12	0.572 8	0.325 10	0.710 13	0.870 7	0.724 13	0.823 2	0.628 19	0.934 9	0.865 8	0.683 16

StratifiedFormer	0.747 6	0.901 4	0.803 10	0.845 6	0.757 3	0.846 10	0.512 11	0.825 13	0.696 3	0.645 7	0.956 9	0.576 7	0.262 33	0.744 11	0.861 9	0.742 8	0.770 24	0.705 3	0.899 21	0.860 9	0.734 3
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 7	0.870 9	0.838 2	0.858 2	0.729 9	0.850 9	0.501 14	0.874 4	0.587 30	0.658 5	0.956 9	0.564 9	0.299 17	0.765 5	0.900 3	0.716 16	0.812 6	0.631 18	0.939 6	0.858 10	0.709 11
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)
BPNet	0.749 4	0.909 3	0.818 7	0.811 14	0.752 4	0.839 12	0.485 21	0.842 10	0.673 6	0.644 8	0.957 8	0.528 16	0.305 16	0.773 4	0.859 10	0.788 4	0.818 4	0.693 5	0.916 12	0.856 11	0.723 9
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
One-Thing-One-Click	0.693 20	0.743 43	0.794 14	0.655 61	0.684 19	0.822 23	0.497 17	0.719 41	0.622 17	0.617 12	0.977 4	0.447 43	0.339 5	0.750 9	0.664 49	0.703 21	0.790 16	0.596 30	0.946 4	0.855 12	0.647 26
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
MinkowskiNet	0.736 10	0.859 11	0.818 7	0.832 10	0.709 13	0.840 11	0.521 10	0.853 6	0.660 9	0.643 9	0.951 20	0.544 11	0.286 23	0.731 12	0.893 4	0.675 28	0.772 22	0.683 7	0.874 41	0.852 13	0.727 6
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
MatchingNet	0.724 13	0.812 21	0.812 9	0.810 15	0.735 7	0.834 15	0.495 18	0.860 5	0.572 35	0.602 20	0.954 14	0.512 19	0.280 24	0.757 8	0.845 18	0.725 12	0.780 18	0.606 27	0.937 7	0.851 14	0.700 13

PicassoNet-II	0.696 19	0.704 53	0.790 15	0.787 23	0.709 13	0.837 13	0.459 31	0.815 17	0.543 45	0.615 13	0.956 9	0.529 14	0.250 36	0.551 47	0.790 27	0.703 21	0.799 10	0.619 22	0.908 14	0.848 15	0.700 13
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
contrastBoundary	0.705 15	0.769 35	0.775 21	0.809 16	0.687 18	0.820 26	0.439 45	0.812 19	0.661 8	0.591 23	0.945 39	0.515 18	0.171 63	0.633 24	0.856 11	0.720 14	0.796 11	0.668 9	0.889 29	0.847 16	0.689 15
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
One Thing One Click	0.701 17	0.825 18	0.796 12	0.723 37	0.716 12	0.832 16	0.433 47	0.816 15	0.634 14	0.609 16	0.969 6	0.418 55	0.344 4	0.559 44	0.833 19	0.715 17	0.808 7	0.560 45	0.902 18	0.847 16	0.680 17

INS-Conv-semantic	0.717 14	0.751 41	0.759 27	0.812 13	0.704 15	0.868 4	0.537 5	0.842 10	0.609 21	0.608 17	0.953 16	0.534 12	0.293 19	0.616 28	0.864 8	0.719 15	0.793 14	0.640 14	0.933 10	0.845 18	0.663 20

CU-Hybrid Net	0.693 20	0.596 71	0.789 17	0.803 19	0.677 20	0.800 43	0.469 25	0.846 9	0.554 43	0.591 23	0.948 30	0.500 22	0.316 12	0.609 29	0.847 17	0.732 10	0.808 7	0.593 33	0.894 25	0.839 19	0.652 24

VI-PointConv	0.676 28	0.770 34	0.754 31	0.783 26	0.621 34	0.814 33	0.552 4	0.758 29	0.571 37	0.557 29	0.954 14	0.529 14	0.268 32	0.530 51	0.682 45	0.675 28	0.719 40	0.603 28	0.888 30	0.833 20	0.665 19
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
VACNN++	0.684 24	0.728 49	0.757 30	0.776 27	0.690 17	0.804 41	0.464 29	0.816 15	0.577 34	0.587 25	0.945 39	0.508 21	0.276 26	0.671 14	0.710 40	0.663 33	0.750 32	0.589 36	0.881 35	0.832 21	0.653 23

JSENet	0.699 18	0.881 8	0.762 25	0.821 11	0.667 22	0.800 43	0.522 9	0.792 23	0.613 18	0.607 18	0.935 57	0.492 24	0.205 51	0.576 38	0.853 13	0.691 23	0.758 29	0.652 11	0.872 44	0.828 22	0.649 25
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
Superpoint Network	0.683 26	0.851 13	0.728 44	0.800 21	0.653 25	0.806 39	0.468 26	0.804 20	0.572 35	0.602 20	0.946 36	0.453 40	0.239 41	0.519 53	0.822 20	0.689 26	0.762 27	0.595 32	0.895 24	0.827 23	0.630 32

PointContrast_LA_SEM	0.683 26	0.757 39	0.784 18	0.786 24	0.639 30	0.824 22	0.408 53	0.775 25	0.604 24	0.541 33	0.934 61	0.532 13	0.269 30	0.552 45	0.777 28	0.645 43	0.793 14	0.640 14	0.913 13	0.824 24	0.671 18

ROSMRF3D	0.673 29	0.789 25	0.748 33	0.763 32	0.635 32	0.814 33	0.407 55	0.747 33	0.581 33	0.573 26	0.950 24	0.484 25	0.271 29	0.607 30	0.754 31	0.649 38	0.774 21	0.596 30	0.883 32	0.823 25	0.606 40

RFCR	0.702 16	0.889 6	0.745 35	0.813 12	0.672 21	0.818 30	0.493 19	0.815 17	0.623 16	0.610 15	0.947 33	0.470 31	0.249 38	0.594 32	0.848 16	0.705 20	0.779 19	0.646 12	0.892 27	0.823 25	0.611 36
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
Feature_GeometricNet	0.690 22	0.884 7	0.754 31	0.795 22	0.647 27	0.818 30	0.422 49	0.802 22	0.612 19	0.604 19	0.945 39	0.462 34	0.189 58	0.563 43	0.853 13	0.726 11	0.765 25	0.632 17	0.904 16	0.821 27	0.606 40
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
KP-FCNN	0.684 24	0.847 14	0.758 29	0.784 25	0.647 27	0.814 33	0.473 23	0.772 26	0.605 23	0.594 22	0.935 57	0.450 41	0.181 61	0.587 33	0.805 25	0.690 24	0.785 17	0.614 23	0.882 33	0.819 28	0.632 31
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
joint point-based	0.634 46	0.614 68	0.778 20	0.667 57	0.633 33	0.825 21	0.420 50	0.804 20	0.467 66	0.561 28	0.951 20	0.494 23	0.291 20	0.566 41	0.458 65	0.579 62	0.764 26	0.559 47	0.838 56	0.814 29	0.598 44
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
FusionNet	0.688 23	0.704 53	0.741 39	0.754 34	0.656 23	0.829 18	0.501 14	0.741 36	0.609 21	0.548 31	0.950 24	0.522 17	0.371 2	0.633 24	0.756 30	0.715 17	0.771 23	0.623 20	0.861 51	0.814 29	0.658 21
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PointConv	0.666 31	0.781 27	0.759 27	0.699 45	0.644 29	0.822 23	0.475 22	0.779 24	0.564 40	0.504 49	0.953 16	0.428 49	0.203 53	0.586 35	0.754 31	0.661 34	0.753 30	0.588 37	0.902 18	0.813 31	0.642 27
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++	0.663 33	0.746 42	0.708 47	0.722 38	0.638 31	0.820 26	0.451 33	0.566 68	0.599 27	0.541 33	0.950 24	0.510 20	0.313 13	0.648 19	0.819 22	0.616 52	0.682 55	0.590 35	0.869 47	0.810 32	0.656 22
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
PointASNL	0.666 31	0.703 55	0.781 19	0.751 36	0.655 24	0.830 17	0.471 24	0.769 27	0.474 64	0.537 35	0.951 20	0.475 29	0.279 25	0.635 22	0.698 44	0.675 28	0.751 31	0.553 50	0.816 62	0.806 33	0.703 12
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
HPEIN	0.618 56	0.729 48	0.668 64	0.647 64	0.597 41	0.766 60	0.414 51	0.680 50	0.520 50	0.525 40	0.946 36	0.432 46	0.215 47	0.493 60	0.599 54	0.638 44	0.617 71	0.570 41	0.897 22	0.806 33	0.605 42
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
DCM-Net	0.658 34	0.778 28	0.702 50	0.806 18	0.619 35	0.813 36	0.468 26	0.693 48	0.494 57	0.524 41	0.941 49	0.449 42	0.298 18	0.510 55	0.821 21	0.675 28	0.727 39	0.568 43	0.826 59	0.803 35	0.637 29
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
SConv	0.636 44	0.830 16	0.697 54	0.752 35	0.572 52	0.780 55	0.445 39	0.716 42	0.529 48	0.530 38	0.951 20	0.446 44	0.170 64	0.507 57	0.666 48	0.636 45	0.682 55	0.541 57	0.886 31	0.799 36	0.594 46

FPConv	0.639 41	0.785 26	0.760 26	0.713 43	0.603 38	0.798 46	0.392 60	0.534 73	0.603 25	0.524 41	0.948 30	0.457 36	0.250 36	0.538 49	0.723 38	0.598 57	0.696 51	0.614 23	0.872 44	0.799 36	0.567 54
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
APCF-Net	0.631 49	0.742 44	0.687 63	0.672 53	0.557 56	0.792 50	0.408 53	0.665 54	0.545 44	0.508 46	0.952 19	0.428 49	0.186 59	0.634 23	0.702 42	0.620 48	0.706 47	0.555 49	0.873 42	0.798 38	0.581 48
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
DenSeR	0.628 53	0.800 22	0.625 74	0.719 40	0.545 58	0.806 39	0.445 39	0.597 62	0.448 70	0.519 44	0.938 54	0.481 26	0.328 9	0.489 61	0.499 64	0.657 36	0.759 28	0.592 34	0.881 35	0.797 39	0.634 30

MCCNN	0.633 47	0.866 10	0.731 42	0.771 28	0.576 49	0.809 37	0.410 52	0.684 49	0.497 56	0.491 51	0.949 27	0.466 33	0.105 77	0.581 36	0.646 51	0.620 48	0.680 57	0.542 56	0.817 61	0.795 40	0.618 35
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
FusionAwareConv	0.630 52	0.604 70	0.741 39	0.766 31	0.590 43	0.747 66	0.501 14	0.734 38	0.503 55	0.527 39	0.919 71	0.454 38	0.323 11	0.550 48	0.420 70	0.678 27	0.688 54	0.544 53	0.896 23	0.795 40	0.627 33
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
SALANet	0.670 30	0.816 20	0.770 23	0.768 30	0.652 26	0.807 38	0.451 33	0.747 33	0.659 10	0.545 32	0.924 67	0.473 30	0.149 73	0.571 40	0.811 24	0.635 46	0.746 33	0.623 20	0.892 27	0.794 42	0.570 52

SegGroup_sem	0.627 54	0.818 19	0.747 34	0.701 44	0.602 39	0.764 61	0.385 65	0.629 59	0.490 59	0.508 46	0.931 64	0.409 57	0.201 54	0.564 42	0.725 37	0.618 50	0.692 52	0.539 58	0.873 42	0.794 42	0.548 61
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation.
SAFNet-seg	0.654 36	0.752 40	0.734 41	0.664 58	0.583 47	0.815 32	0.399 57	0.754 31	0.639 12	0.535 37	0.942 47	0.470 31	0.309 15	0.665 15	0.539 57	0.650 37	0.708 46	0.635 16	0.857 53	0.793 44	0.642 27
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
PD-Net	0.638 42	0.797 23	0.769 24	0.641 67	0.590 43	0.820 26	0.461 30	0.537 72	0.637 13	0.536 36	0.947 33	0.388 62	0.206 50	0.656 16	0.668 47	0.647 41	0.732 38	0.585 38	0.868 48	0.793 44	0.473 74

PointMRNet	0.640 40	0.717 52	0.701 51	0.692 48	0.576 49	0.801 42	0.467 28	0.716 42	0.563 41	0.459 58	0.953 16	0.429 48	0.169 65	0.581 36	0.854 12	0.605 53	0.710 43	0.550 51	0.894 25	0.793 44	0.575 50

MVPNet	0.641 38	0.831 15	0.715 45	0.671 55	0.590 43	0.781 53	0.394 59	0.679 51	0.642 11	0.553 30	0.937 55	0.462 34	0.256 34	0.649 18	0.406 71	0.626 47	0.691 53	0.666 10	0.877 37	0.792 47	0.608 39
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
Supervoxel-CNN	0.635 45	0.656 61	0.711 46	0.719 40	0.613 36	0.757 64	0.444 42	0.765 28	0.534 47	0.566 27	0.928 65	0.478 28	0.272 28	0.636 21	0.531 59	0.664 32	0.645 66	0.508 64	0.864 50	0.792 47	0.611 36

RandLA-Net	0.645 37	0.778 28	0.731 42	0.699 45	0.577 48	0.829 18	0.446 37	0.736 37	0.477 63	0.523 43	0.945 39	0.454 38	0.269 30	0.484 62	0.749 34	0.618 50	0.738 34	0.599 29	0.827 58	0.792 47	0.621 34

PointMTL	0.632 48	0.731 47	0.688 61	0.675 52	0.591 42	0.784 52	0.444 42	0.565 69	0.610 20	0.492 50	0.949 27	0.456 37	0.254 35	0.587 33	0.706 41	0.599 56	0.665 62	0.612 26	0.868 48	0.791 50	0.579 49

PointConv-SFPN	0.641 38	0.776 30	0.703 49	0.721 39	0.557 56	0.826 20	0.451 33	0.672 53	0.563 41	0.483 53	0.943 46	0.425 52	0.162 68	0.644 20	0.726 36	0.659 35	0.709 45	0.572 40	0.875 39	0.786 51	0.559 57

SIConv	0.625 55	0.830 16	0.694 56	0.757 33	0.563 54	0.772 59	0.448 36	0.647 57	0.520 50	0.509 45	0.949 27	0.431 47	0.191 57	0.496 59	0.614 53	0.647 41	0.672 60	0.535 60	0.876 38	0.783 52	0.571 51

DVVNet	0.562 66	0.648 62	0.700 52	0.770 29	0.586 46	0.687 73	0.333 71	0.650 55	0.514 53	0.475 56	0.906 75	0.359 67	0.223 44	0.340 74	0.442 69	0.422 78	0.668 61	0.501 65	0.708 73	0.779 53	0.534 63

ROSMRF	0.580 63	0.772 31	0.707 48	0.681 51	0.563 54	0.764 61	0.362 67	0.515 74	0.465 67	0.465 57	0.936 56	0.427 51	0.207 49	0.438 65	0.577 55	0.536 67	0.675 59	0.486 69	0.723 72	0.779 53	0.524 65

PointSPNet	0.637 43	0.734 46	0.692 58	0.714 42	0.576 49	0.797 47	0.446 37	0.743 35	0.598 28	0.437 63	0.942 47	0.403 58	0.150 72	0.626 26	0.800 26	0.649 38	0.697 50	0.557 48	0.846 55	0.777 55	0.563 55

HPGCNN	0.656 35	0.698 56	0.743 37	0.650 62	0.564 53	0.820 26	0.505 13	0.758 29	0.631 15	0.479 54	0.945 39	0.480 27	0.226 42	0.572 39	0.774 29	0.690 24	0.735 36	0.614 23	0.853 54	0.776 56	0.597 45
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SPH3D-GCN	0.610 57	0.858 12	0.772 22	0.489 79	0.532 59	0.792 50	0.404 56	0.643 58	0.570 38	0.507 48	0.935 57	0.414 56	0.046 83	0.510 55	0.702 42	0.602 55	0.705 48	0.549 52	0.859 52	0.773 57	0.534 63
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
PointNet2-SFPN	0.631 49	0.771 32	0.692 58	0.672 53	0.524 60	0.837 13	0.440 44	0.706 46	0.538 46	0.446 60	0.944 44	0.421 54	0.219 45	0.552 45	0.751 33	0.591 59	0.737 35	0.543 55	0.901 20	0.768 58	0.557 58

AttAN	0.609 58	0.760 37	0.667 65	0.649 63	0.521 61	0.793 48	0.457 32	0.648 56	0.528 49	0.434 65	0.947 33	0.401 59	0.153 71	0.454 64	0.721 39	0.648 40	0.717 41	0.536 59	0.904 16	0.765 59	0.485 70
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
CCRFNet	0.589 62	0.766 36	0.659 68	0.683 50	0.470 68	0.740 68	0.387 64	0.620 61	0.490 59	0.476 55	0.922 69	0.355 69	0.245 39	0.511 54	0.511 62	0.571 63	0.643 67	0.493 68	0.872 44	0.762 60	0.600 43

wsss-transformer	0.600 59	0.634 64	0.743 37	0.697 47	0.601 40	0.781 53	0.437 46	0.585 66	0.493 58	0.446 60	0.933 62	0.394 60	0.011 85	0.654 17	0.661 50	0.603 54	0.733 37	0.526 61	0.832 57	0.761 61	0.480 71

Pointnet++ & Feature	0.557 67	0.735 45	0.661 67	0.686 49	0.491 64	0.744 67	0.392 60	0.539 71	0.451 69	0.375 71	0.946 36	0.376 64	0.205 51	0.403 70	0.356 74	0.553 66	0.643 67	0.497 66	0.824 60	0.756 62	0.515 66

DPC	0.592 61	0.720 50	0.700 52	0.602 72	0.480 65	0.762 63	0.380 66	0.713 44	0.585 32	0.437 63	0.940 51	0.369 65	0.288 21	0.434 67	0.509 63	0.590 61	0.639 69	0.567 44	0.772 67	0.755 63	0.592 47
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
PCNN	0.498 74	0.559 74	0.644 72	0.560 76	0.420 74	0.711 71	0.229 81	0.414 76	0.436 72	0.352 75	0.941 49	0.324 73	0.155 70	0.238 80	0.387 73	0.493 70	0.529 79	0.509 62	0.813 63	0.751 64	0.504 68

LAP-D	0.594 60	0.720 50	0.692 58	0.637 68	0.456 69	0.773 58	0.391 62	0.730 39	0.587 30	0.445 62	0.940 51	0.381 63	0.288 21	0.434 67	0.453 67	0.591 59	0.649 64	0.581 39	0.777 66	0.749 65	0.610 38

3DSM_DMMF	0.631 49	0.626 66	0.745 35	0.801 20	0.607 37	0.751 65	0.506 12	0.729 40	0.565 39	0.491 51	0.866 80	0.434 45	0.197 56	0.595 31	0.630 52	0.709 19	0.705 48	0.560 45	0.875 39	0.740 66	0.491 69

GMLPs	0.538 69	0.495 79	0.693 57	0.647 64	0.471 67	0.793 48	0.300 73	0.477 75	0.505 54	0.358 73	0.903 77	0.327 72	0.081 80	0.472 63	0.529 60	0.448 76	0.710 43	0.509 62	0.746 69	0.737 67	0.554 60

3DMV, FTSDF	0.501 73	0.558 75	0.608 77	0.424 83	0.478 66	0.690 72	0.246 79	0.586 65	0.468 65	0.450 59	0.911 73	0.394 60	0.160 69	0.438 65	0.212 80	0.432 77	0.541 78	0.475 71	0.742 70	0.727 68	0.477 72

subcloud_weak	0.516 71	0.676 58	0.591 79	0.609 69	0.442 70	0.774 57	0.335 70	0.597 62	0.422 75	0.357 74	0.932 63	0.341 71	0.094 79	0.298 76	0.528 61	0.473 74	0.676 58	0.495 67	0.602 80	0.721 69	0.349 81

PointMRNet-lite	0.553 68	0.633 65	0.648 69	0.659 59	0.430 72	0.800 43	0.390 63	0.592 64	0.454 68	0.371 72	0.939 53	0.368 66	0.136 75	0.368 72	0.448 68	0.560 65	0.715 42	0.486 69	0.882 33	0.720 70	0.462 75

PointCNN with RGB	0.458 76	0.577 73	0.611 76	0.356 85	0.321 82	0.715 70	0.299 75	0.376 79	0.328 82	0.319 76	0.944 44	0.285 77	0.164 67	0.216 83	0.229 79	0.484 72	0.545 77	0.456 74	0.755 68	0.709 71	0.475 73
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
Online SegFusion	0.515 72	0.607 69	0.644 72	0.579 74	0.434 71	0.630 79	0.353 68	0.628 60	0.440 71	0.410 66	0.762 84	0.307 74	0.167 66	0.520 52	0.403 72	0.516 68	0.565 73	0.447 76	0.678 76	0.701 72	0.514 67
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
SPLAT Net	0.393 82	0.472 82	0.511 82	0.606 70	0.311 83	0.656 75	0.245 80	0.405 77	0.328 82	0.197 84	0.927 66	0.227 83	0.000 87	0.001 88	0.249 78	0.271 85	0.510 80	0.383 83	0.593 81	0.699 73	0.267 83
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
SSC-UNet	0.308 85	0.353 84	0.290 86	0.278 86	0.166 86	0.553 83	0.169 85	0.286 81	0.147 86	0.148 86	0.908 74	0.182 85	0.064 82	0.023 87	0.018 87	0.354 82	0.363 84	0.345 84	0.546 84	0.685 74	0.278 82

TextureNet	0.566 65	0.672 60	0.664 66	0.671 55	0.494 63	0.719 69	0.445 39	0.678 52	0.411 76	0.396 68	0.935 57	0.356 68	0.225 43	0.412 69	0.535 58	0.565 64	0.636 70	0.464 72	0.794 65	0.680 75	0.568 53
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
SurfaceConvPF	0.442 78	0.505 78	0.622 75	0.380 84	0.342 80	0.654 76	0.227 82	0.397 78	0.367 79	0.276 80	0.924 67	0.240 81	0.198 55	0.359 73	0.262 77	0.366 80	0.581 72	0.435 78	0.640 78	0.668 76	0.398 77
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
FCPN	0.447 77	0.679 57	0.604 78	0.578 75	0.380 76	0.682 74	0.291 76	0.106 85	0.483 62	0.258 83	0.920 70	0.258 80	0.025 84	0.231 82	0.325 75	0.480 73	0.560 75	0.463 73	0.725 71	0.666 77	0.231 85
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
SQN_0.1%	0.569 64	0.676 58	0.696 55	0.657 60	0.497 62	0.779 56	0.424 48	0.548 70	0.515 52	0.376 70	0.902 78	0.422 53	0.357 3	0.379 71	0.456 66	0.596 58	0.659 63	0.544 53	0.685 75	0.665 78	0.556 59

Tangent Convolutions	0.438 80	0.437 83	0.646 71	0.474 80	0.369 77	0.645 77	0.353 68	0.258 82	0.282 84	0.279 79	0.918 72	0.298 76	0.147 74	0.283 77	0.294 76	0.487 71	0.562 74	0.427 79	0.619 79	0.633 79	0.352 80
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
PNET2	0.442 78	0.548 76	0.548 80	0.597 73	0.363 78	0.628 80	0.300 73	0.292 80	0.374 78	0.307 77	0.881 79	0.268 79	0.186 59	0.238 80	0.204 82	0.407 79	0.506 83	0.449 75	0.667 77	0.620 80	0.462 75

PanopticFusion-label	0.529 70	0.491 80	0.688 61	0.604 71	0.386 75	0.632 78	0.225 83	0.705 47	0.434 73	0.293 78	0.815 81	0.348 70	0.241 40	0.499 58	0.669 46	0.507 69	0.649 64	0.442 77	0.796 64	0.602 81	0.561 56
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3DWSSS	0.425 81	0.525 77	0.647 70	0.522 77	0.324 81	0.488 85	0.077 86	0.712 45	0.353 80	0.401 67	0.636 86	0.281 78	0.176 62	0.340 74	0.565 56	0.175 86	0.551 76	0.398 81	0.370 86	0.602 81	0.361 79

3DMV	0.484 75	0.484 81	0.538 81	0.643 66	0.424 73	0.606 82	0.310 72	0.574 67	0.433 74	0.378 69	0.796 82	0.301 75	0.214 48	0.537 50	0.208 81	0.472 75	0.507 82	0.413 80	0.693 74	0.602 81	0.539 62
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
ScanNet+FTSDF	0.383 83	0.297 85	0.491 83	0.432 82	0.358 79	0.612 81	0.274 77	0.116 84	0.411 76	0.265 81	0.904 76	0.229 82	0.079 81	0.250 78	0.185 83	0.320 83	0.510 80	0.385 82	0.548 82	0.597 84	0.394 78

PointNet++	0.339 84	0.584 72	0.478 84	0.458 81	0.256 85	0.360 86	0.250 78	0.247 83	0.278 85	0.261 82	0.677 85	0.183 84	0.117 76	0.212 84	0.145 85	0.364 81	0.346 86	0.232 86	0.548 82	0.523 85	0.252 84
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
ScanNet	0.306 86	0.203 86	0.366 85	0.501 78	0.311 83	0.524 84	0.211 84	0.002 87	0.342 81	0.189 85	0.786 83	0.145 86	0.102 78	0.245 79	0.152 84	0.318 84	0.348 85	0.300 85	0.460 85	0.437 86	0.182 86
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 87	0.000 87	0.041 87	0.172 87	0.030 87	0.062 88	0.001 88	0.035 86	0.004 87	0.051 87	0.143 87	0.019 88	0.003 86	0.041 86	0.050 86	0.003 88	0.054 87	0.018 88	0.005 87	0.264 87	0.082 87

Feature-Geometry Net	0.024 88	0.000 87	0.000 88	0.001 88	0.010 88	0.098 87	0.007 87	0.000 88	0.000 88	0.026 88	0.072 88	0.059 87	0.000 87	0.060 85	0.000 88	0.013 87	0.040 88	0.045 87	0.000 88	0.038 88	0.006 88

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

SoftGroup++	0.769 1	1.000 1	0.803 15	0.937 1	0.684 3	0.865 3	0.213 13	0.870 2	0.664 2	0.571 4	0.758 1	0.702 4	0.807 1	1.000 1	0.653 12	0.902 1	0.792 2	1.000 1	0.626 1

SoftGroup	0.761 2	1.000 1	0.808 12	0.845 6	0.716 1	0.862 5	0.243 10	0.824 3	0.655 4	0.620 2	0.734 2	0.699 5	0.791 3	0.981 19	0.716 4	0.844 4	0.769 3	1.000 1	0.594 5
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 3	1.000 1	0.788 18	0.724 18	0.642 6	0.859 6	0.248 9	0.787 9	0.618 8	0.596 3	0.653 4	0.722 2	0.583 23	1.000 1	0.766 2	0.861 2	0.825 1	1.000 1	0.504 15

IPCA-Inst	0.731 4	1.000 1	0.788 19	0.884 5	0.698 2	0.788 20	0.252 8	0.760 11	0.646 5	0.511 12	0.637 6	0.665 6	0.804 2	1.000 1	0.644 13	0.778 10	0.747 5	1.000 1	0.561 10

TopoSeg	0.725 5	1.000 1	0.806 14	0.933 2	0.668 5	0.758 23	0.272 6	0.734 15	0.630 6	0.549 8	0.654 3	0.606 7	0.697 6	0.966 21	0.612 16	0.839 5	0.754 4	1.000 1	0.573 6

DKNet	0.718 6	1.000 1	0.814 9	0.782 10	0.619 7	0.872 2	0.224 11	0.751 13	0.569 10	0.677 1	0.585 9	0.724 1	0.633 15	0.981 19	0.515 23	0.819 7	0.736 6	1.000 1	0.617 2

SDSC	0.700 7	1.000 1	0.848 4	0.763 16	0.609 10	0.792 18	0.262 7	0.824 3	0.627 7	0.535 10	0.547 17	0.493 13	0.600 17	1.000 1	0.712 6	0.731 22	0.689 10	1.000 1	0.563 9

HAIS	0.699 8	1.000 1	0.849 3	0.820 7	0.675 4	0.808 13	0.279 4	0.757 12	0.465 15	0.517 11	0.596 7	0.559 9	0.600 17	1.000 1	0.654 11	0.767 12	0.676 11	0.994 26	0.560 11
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNet	0.698 9	1.000 1	0.697 34	0.888 4	0.556 16	0.803 14	0.387 2	0.626 22	0.417 19	0.556 7	0.585 10	0.702 3	0.600 17	1.000 1	0.824 1	0.720 24	0.692 8	1.000 1	0.509 14
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SphereSeg	0.680 10	1.000 1	0.856 2	0.744 17	0.618 8	0.893 1	0.151 15	0.651 20	0.713 1	0.537 9	0.579 12	0.430 21	0.651 7	1.000 1	0.389 32	0.744 19	0.697 7	0.991 27	0.601 4

MaskVoteNet_Coarse	0.677 11	1.000 1	0.847 5	0.771 12	0.509 22	0.816 9	0.277 5	0.558 29	0.482 12	0.562 6	0.640 5	0.448 17	0.700 4	1.000 1	0.666 7	0.852 3	0.578 22	0.997 21	0.488 19

OccuSeg+instance	0.672 12	1.000 1	0.758 26	0.682 20	0.576 14	0.842 7	0.477 1	0.504 32	0.524 11	0.567 5	0.585 11	0.451 16	0.557 24	1.000 1	0.751 3	0.797 9	0.563 25	1.000 1	0.467 22
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group	0.664 13	1.000 1	0.822 8	0.764 15	0.616 9	0.815 10	0.139 19	0.694 17	0.597 9	0.459 17	0.566 13	0.599 8	0.600 17	0.516 38	0.715 5	0.819 8	0.635 15	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 14	1.000 1	0.760 24	0.667 22	0.581 12	0.863 4	0.323 3	0.655 19	0.477 13	0.473 15	0.549 15	0.432 20	0.650 8	1.000 1	0.655 10	0.738 20	0.585 21	0.944 31	0.472 21

CSC-Pretrained	0.648 15	1.000 1	0.810 10	0.768 13	0.523 21	0.813 11	0.143 18	0.819 5	0.389 20	0.422 24	0.511 20	0.443 18	0.650 8	1.000 1	0.624 15	0.732 21	0.634 16	1.000 1	0.375 28

PE	0.645 16	1.000 1	0.773 21	0.798 9	0.538 18	0.786 21	0.088 26	0.799 8	0.350 24	0.435 23	0.547 16	0.545 10	0.646 14	0.933 22	0.562 19	0.761 15	0.556 30	0.997 21	0.501 17
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN	0.643 17	1.000 1	0.758 25	0.582 30	0.539 17	0.826 8	0.046 30	0.765 10	0.372 22	0.436 22	0.588 8	0.539 12	0.650 8	1.000 1	0.577 17	0.750 17	0.653 14	0.997 21	0.495 18

Dyco3D	0.641 18	1.000 1	0.841 6	0.893 3	0.531 19	0.802 15	0.115 23	0.588 27	0.448 16	0.438 20	0.537 19	0.430 22	0.550 25	0.857 24	0.534 21	0.764 14	0.657 12	0.987 28	0.568 7
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN	0.638 19	1.000 1	0.895 1	0.800 8	0.480 25	0.676 27	0.144 17	0.737 14	0.354 23	0.447 18	0.400 29	0.365 27	0.700 4	1.000 1	0.569 18	0.836 6	0.599 18	1.000 1	0.473 20

PointGroup	0.636 20	1.000 1	0.765 22	0.624 24	0.505 24	0.797 16	0.116 22	0.696 16	0.384 21	0.441 19	0.559 14	0.476 14	0.596 21	1.000 1	0.666 7	0.756 16	0.556 29	0.997 21	0.513 13
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 21	0.667 31	0.797 17	0.714 19	0.562 15	0.774 22	0.146 16	0.810 7	0.429 18	0.476 14	0.546 18	0.399 24	0.633 15	1.000 1	0.632 14	0.722 23	0.609 17	1.000 1	0.514 12
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 22	1.000 1	0.797 16	0.608 25	0.589 11	0.627 31	0.219 12	0.882 1	0.310 26	0.402 28	0.383 31	0.396 25	0.650 8	1.000 1	0.663 9	0.543 39	0.691 9	1.000 1	0.568 8

3D-MPA	0.611 23	1.000 1	0.833 7	0.765 14	0.526 20	0.756 24	0.136 21	0.588 27	0.470 14	0.438 21	0.432 27	0.358 28	0.650 8	0.857 24	0.429 28	0.765 13	0.557 28	1.000 1	0.430 24
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 24	1.000 1	0.810 11	0.583 29	0.449 28	0.813 12	0.042 31	0.603 25	0.341 25	0.490 13	0.465 23	0.410 23	0.650 8	0.835 30	0.264 37	0.694 28	0.561 26	0.889 35	0.504 16

SSEN	0.575 25	1.000 1	0.761 23	0.473 32	0.477 26	0.795 17	0.066 27	0.529 30	0.658 3	0.460 16	0.461 24	0.380 26	0.331 37	0.859 23	0.401 31	0.692 29	0.653 13	1.000 1	0.348 30
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 26	0.528 40	0.708 33	0.626 23	0.580 13	0.745 25	0.063 28	0.627 21	0.240 30	0.400 29	0.497 21	0.464 15	0.515 26	1.000 1	0.475 25	0.745 18	0.571 23	1.000 1	0.429 25

MTML	0.549 27	1.000 1	0.807 13	0.588 28	0.327 33	0.647 29	0.004 36	0.815 6	0.180 32	0.418 25	0.364 33	0.182 32	0.445 30	1.000 1	0.442 27	0.688 30	0.571 24	1.000 1	0.396 26
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 28	0.667 31	0.718 29	0.777 11	0.399 29	0.683 26	0.000 39	0.669 18	0.138 35	0.391 30	0.374 32	0.539 11	0.360 36	0.641 35	0.556 20	0.774 11	0.593 19	0.997 21	0.251 35
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 29	1.000 1	0.538 41	0.282 35	0.468 27	0.790 19	0.173 14	0.345 37	0.429 17	0.413 27	0.484 22	0.176 33	0.595 22	0.591 36	0.522 22	0.668 31	0.476 34	0.986 29	0.327 31

Occipital-SCS	0.512 30	1.000 1	0.716 30	0.509 31	0.506 23	0.611 32	0.092 25	0.602 26	0.177 33	0.346 33	0.383 30	0.165 34	0.442 31	0.850 29	0.386 33	0.618 35	0.543 31	0.889 35	0.389 27

3D-BoNet	0.488 31	1.000 1	0.672 36	0.590 27	0.301 35	0.484 42	0.098 24	0.620 23	0.306 27	0.341 34	0.259 37	0.125 36	0.434 33	0.796 31	0.402 30	0.499 41	0.513 33	0.909 34	0.439 23
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 32	0.667 31	0.712 32	0.595 26	0.259 38	0.550 38	0.000 39	0.613 24	0.175 34	0.250 39	0.434 25	0.437 19	0.411 35	0.857 24	0.485 24	0.591 38	0.267 44	0.944 31	0.359 29
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 33	0.667 31	0.685 35	0.677 21	0.372 31	0.562 36	0.000 39	0.482 33	0.244 29	0.316 36	0.298 34	0.052 42	0.442 32	0.857 24	0.267 36	0.702 25	0.559 27	1.000 1	0.287 33

SALoss-ResNet	0.459 34	1.000 1	0.737 28	0.159 45	0.259 37	0.587 34	0.138 20	0.475 34	0.217 31	0.416 26	0.408 28	0.128 35	0.315 38	0.714 32	0.411 29	0.536 40	0.590 20	0.873 38	0.304 32
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 35	0.528 40	0.555 39	0.381 33	0.382 30	0.633 30	0.002 37	0.509 31	0.260 28	0.361 32	0.432 26	0.327 29	0.451 29	0.571 37	0.367 34	0.639 33	0.386 35	0.980 30	0.276 34
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_ins	0.445 36	0.667 31	0.773 20	0.185 42	0.317 34	0.656 28	0.000 39	0.407 36	0.134 36	0.381 31	0.267 36	0.217 31	0.476 28	0.714 32	0.452 26	0.629 34	0.514 32	1.000 1	0.222 38
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation.
3D-SIS	0.382 37	1.000 1	0.432 43	0.245 37	0.190 39	0.577 35	0.013 34	0.263 39	0.033 42	0.320 35	0.240 38	0.075 38	0.422 34	0.857 24	0.117 41	0.699 26	0.271 43	0.883 37	0.235 37
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3D	0.323 38	0.667 31	0.542 40	0.264 36	0.157 42	0.550 37	0.000 39	0.205 42	0.009 43	0.270 38	0.218 39	0.075 38	0.500 27	0.688 34	0.007 47	0.698 27	0.301 40	0.459 44	0.200 39
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone	0.319 39	0.667 31	0.715 31	0.233 38	0.189 40	0.479 43	0.008 35	0.218 40	0.067 41	0.201 41	0.173 40	0.107 37	0.123 43	0.438 39	0.150 39	0.615 36	0.355 36	0.916 33	0.093 46

R-PointNet	0.306 40	0.500 42	0.405 44	0.311 34	0.348 32	0.589 33	0.054 29	0.068 45	0.126 37	0.283 37	0.290 35	0.028 43	0.219 41	0.214 42	0.331 35	0.396 45	0.275 41	0.821 40	0.245 36

Region-18class	0.284 41	0.250 46	0.751 27	0.228 40	0.270 36	0.521 39	0.000 39	0.468 35	0.008 45	0.205 40	0.127 41	0.000 47	0.068 45	0.070 45	0.262 38	0.652 32	0.323 38	0.740 41	0.173 40

SemRegionNet-20cls	0.250 42	0.333 43	0.613 37	0.229 39	0.163 41	0.493 40	0.000 39	0.304 38	0.107 38	0.147 43	0.100 42	0.052 41	0.231 39	0.119 43	0.039 43	0.445 43	0.325 37	0.654 42	0.141 42

3D-BEVIS	0.248 43	0.667 31	0.566 38	0.076 46	0.035 47	0.394 45	0.027 33	0.035 46	0.098 39	0.099 45	0.030 46	0.025 44	0.098 44	0.375 41	0.126 40	0.604 37	0.181 45	0.854 39	0.171 41
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
tmp	0.248 43	0.667 31	0.437 42	0.188 41	0.153 43	0.491 41	0.000 39	0.208 41	0.094 40	0.153 42	0.099 43	0.057 40	0.217 42	0.119 43	0.039 43	0.466 42	0.302 39	0.640 43	0.140 43

ASIS	0.199 45	0.333 43	0.253 46	0.167 44	0.140 44	0.438 44	0.000 39	0.177 43	0.008 44	0.121 44	0.069 44	0.004 46	0.231 40	0.429 40	0.036 45	0.445 44	0.273 42	0.333 46	0.119 45

Sgpn_scannet	0.143 46	0.208 47	0.390 45	0.169 43	0.065 45	0.275 46	0.029 32	0.069 44	0.000 46	0.087 46	0.043 45	0.014 45	0.027 47	0.000 46	0.112 42	0.351 46	0.168 46	0.438 45	0.138 44

MaskRCNN 2d->3d Proj	0.058 47	0.333 43	0.002 47	0.000 47	0.053 46	0.002 47	0.002 38	0.021 47	0.000 46	0.045 47	0.024 47	0.238 30	0.065 46	0.000 46	0.014 46	0.107 47	0.020 47	0.110 47	0.006 47

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 11	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
CU-Hybrid-2D Net	0.636 3	0.825 2	0.820 2	0.179 17	0.648 3	0.463 3	0.549 1	0.742 4	0.676 2	0.628 2	0.961 1	0.420 2	0.379 5	0.684 4	0.381 11	0.732 2	0.723 3	0.599 2	0.827 9	0.851 2	0.634 4

BPNet_2D	0.670 2	0.822 3	0.795 3	0.836 2	0.659 2	0.481 2	0.451 7	0.769 3	0.656 3	0.567 3	0.931 3	0.395 3	0.390 4	0.700 2	0.534 3	0.689 6	0.770 2	0.574 3	0.865 4	0.831 3	0.675 3
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
CMX	0.613 4	0.681 6	0.725 8	0.502 11	0.634 5	0.297 13	0.478 5	0.830 2	0.651 4	0.537 5	0.924 4	0.375 4	0.315 10	0.686 3	0.451 9	0.714 3	0.543 15	0.504 5	0.894 3	0.823 4	0.688 2

RFBNet	0.592 8	0.616 8	0.758 4	0.659 6	0.581 8	0.330 9	0.469 6	0.655 11	0.543 10	0.524 6	0.924 4	0.355 8	0.336 8	0.572 9	0.479 8	0.671 9	0.648 6	0.480 8	0.814 11	0.814 5	0.614 7

DCRedNet	0.583 9	0.682 5	0.723 9	0.542 10	0.510 12	0.310 11	0.451 7	0.668 9	0.549 9	0.520 7	0.920 6	0.375 4	0.446 2	0.528 12	0.417 10	0.670 10	0.577 13	0.478 9	0.862 5	0.806 6	0.628 6

SSMA	0.577 10	0.695 4	0.716 11	0.439 13	0.563 9	0.314 10	0.444 9	0.719 6	0.551 8	0.503 8	0.887 11	0.346 10	0.348 7	0.603 5	0.353 13	0.709 4	0.600 11	0.457 11	0.901 2	0.786 7	0.599 8
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
FuseNet	0.535 12	0.570 11	0.681 13	0.182 16	0.512 11	0.290 14	0.431 10	0.659 10	0.504 13	0.495 10	0.903 10	0.308 11	0.428 3	0.523 13	0.365 12	0.676 7	0.621 10	0.470 10	0.762 14	0.779 8	0.541 10
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
DMMF	0.597 6	0.543 12	0.755 6	0.749 4	0.585 7	0.338 6	0.494 4	0.704 7	0.598 5	0.494 11	0.911 7	0.347 9	0.327 9	0.593 8	0.527 4	0.675 8	0.646 8	0.513 4	0.842 7	0.774 9	0.527 12

MCA-Net	0.595 7	0.533 13	0.756 5	0.746 5	0.590 6	0.334 8	0.506 3	0.670 8	0.587 7	0.500 9	0.905 9	0.366 6	0.352 6	0.601 6	0.506 6	0.669 11	0.648 6	0.501 6	0.839 8	0.769 10	0.516 13

SN_RN152pyrx8_RVC	0.546 11	0.572 10	0.663 14	0.638 8	0.518 10	0.298 12	0.366 16	0.633 13	0.510 12	0.446 13	0.864 12	0.296 12	0.267 13	0.542 11	0.346 14	0.704 5	0.575 14	0.431 13	0.853 6	0.766 11	0.630 5

DMMF_3d	0.605 5	0.651 7	0.744 7	0.782 3	0.637 4	0.387 4	0.536 2	0.732 5	0.590 6	0.540 4	0.856 14	0.359 7	0.306 11	0.596 7	0.539 2	0.627 13	0.706 4	0.497 7	0.785 13	0.757 12	0.476 14

ILC-PSPNet	0.475 16	0.490 15	0.581 16	0.289 15	0.507 13	0.067 18	0.379 14	0.610 15	0.417 16	0.435 14	0.822 17	0.278 13	0.267 13	0.503 14	0.228 15	0.616 15	0.533 16	0.375 15	0.820 10	0.729 13	0.560 9

MSeg1080_RVC	0.485 15	0.505 14	0.709 12	0.092 18	0.427 15	0.241 15	0.411 12	0.654 12	0.385 18	0.457 12	0.861 13	0.053 18	0.279 12	0.503 14	0.481 7	0.645 12	0.626 9	0.365 16	0.748 16	0.725 14	0.529 11
John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
AdapNet++	0.503 13	0.613 9	0.722 10	0.418 14	0.358 18	0.337 7	0.370 15	0.479 16	0.443 14	0.368 16	0.907 8	0.207 15	0.213 17	0.464 16	0.525 5	0.618 14	0.657 5	0.450 12	0.788 12	0.721 15	0.408 17
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
Enet (reimpl)	0.376 17	0.264 18	0.452 18	0.452 12	0.365 16	0.181 16	0.143 18	0.456 17	0.409 17	0.346 17	0.769 18	0.164 16	0.218 16	0.359 17	0.123 18	0.403 18	0.381 18	0.313 18	0.571 17	0.685 16	0.472 15
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
3DMV (2d proj)	0.498 14	0.481 16	0.612 15	0.579 9	0.456 14	0.343 5	0.384 13	0.623 14	0.525 11	0.381 15	0.845 15	0.254 14	0.264 15	0.557 10	0.182 16	0.581 16	0.598 12	0.429 14	0.760 15	0.661 17	0.446 16
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
ScanNet (2d proj)	0.330 18	0.293 17	0.521 17	0.657 7	0.361 17	0.161 17	0.250 17	0.004 18	0.440 15	0.183 18	0.836 16	0.125 17	0.060 18	0.319 18	0.132 17	0.417 17	0.412 17	0.344 17	0.541 18	0.427 18	0.109 18
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17

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

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

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
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

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