Benchmark Results - 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

BPNet	0.749 2	0.909 1	0.818 4	0.811 8	0.752 1	0.839 6	0.485 13	0.842 7	0.673 3	0.644 4	0.957 3	0.528 8	0.305 9	0.773 2	0.859 4	0.788 2	0.818 3	0.693 2	0.916 6	0.856 5	0.723 4
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
OccuSeg+Semantic	0.764 1	0.758 30	0.796 7	0.839 4	0.746 2	0.907 1	0.562 1	0.850 5	0.680 2	0.672 1	0.978 1	0.610 1	0.335 3	0.777 1	0.819 15	0.847 1	0.830 1	0.691 3	0.972 1	0.885 1	0.727 2

MatchingNet	0.724 7	0.812 17	0.812 6	0.810 9	0.735 3	0.834 8	0.495 11	0.860 3	0.572 26	0.602 11	0.954 6	0.512 10	0.280 16	0.757 4	0.845 11	0.725 6	0.780 10	0.606 19	0.937 3	0.851 7	0.700 7

VMNet	0.746 3	0.870 5	0.838 1	0.858 1	0.729 4	0.850 4	0.501 8	0.874 2	0.587 20	0.658 3	0.956 4	0.564 4	0.299 10	0.765 3	0.900 1	0.716 8	0.812 4	0.631 11	0.939 2	0.858 4	0.709 5

SparseConvNet	0.725 6	0.647 49	0.821 2	0.846 3	0.721 5	0.869 2	0.533 3	0.754 22	0.603 17	0.614 6	0.955 5	0.572 3	0.325 5	0.710 7	0.870 3	0.724 7	0.823 2	0.628 12	0.934 5	0.865 3	0.683 8

One Thing One Click	0.701 9	0.825 15	0.796 7	0.723 28	0.716 6	0.832 9	0.433 34	0.816 8	0.634 8	0.609 8	0.969 2	0.418 42	0.344 2	0.559 31	0.833 12	0.715 9	0.808 5	0.560 33	0.902 10	0.847 8	0.680 9

MinkowskiNet	0.736 5	0.859 7	0.818 4	0.832 5	0.709 7	0.840 5	0.521 5	0.853 4	0.660 4	0.643 5	0.951 11	0.544 5	0.286 15	0.731 6	0.893 2	0.675 18	0.772 13	0.683 4	0.874 30	0.852 6	0.727 2
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
Virtual MVFusion	0.746 3	0.771 25	0.819 3	0.848 2	0.702 8	0.865 3	0.397 44	0.899 1	0.699 1	0.664 2	0.948 20	0.588 2	0.330 4	0.746 5	0.851 8	0.764 3	0.796 7	0.704 1	0.935 4	0.866 2	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
VACNN++	0.684 14	0.728 38	0.757 19	0.776 18	0.690 9	0.804 28	0.464 21	0.816 8	0.577 24	0.587 15	0.945 28	0.508 11	0.276 18	0.671 8	0.710 29	0.663 23	0.750 21	0.589 25	0.881 25	0.832 11	0.653 13

CU-Hybrid Net	0.693 11	0.596 54	0.789 9	0.803 11	0.677 10	0.800 30	0.469 17	0.846 6	0.554 34	0.591 14	0.948 20	0.500 12	0.316 7	0.609 17	0.847 10	0.732 4	0.808 5	0.593 24	0.894 16	0.839 9	0.652 14

RFCR	0.702 8	0.889 2	0.745 23	0.813 7	0.672 11	0.818 18	0.493 12	0.815 10	0.623 10	0.610 7	0.947 23	0.470 20	0.249 27	0.594 20	0.848 9	0.705 12	0.779 11	0.646 7	0.892 18	0.823 15	0.611 24

JSENet	0.699 10	0.881 4	0.762 15	0.821 6	0.667 12	0.800 30	0.522 4	0.792 14	0.613 11	0.607 9	0.935 45	0.492 14	0.205 38	0.576 26	0.853 6	0.691 13	0.758 18	0.652 6	0.872 33	0.828 12	0.649 15
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
FusionNet	0.688 13	0.704 42	0.741 26	0.754 25	0.656 13	0.829 11	0.501 8	0.741 27	0.609 14	0.548 21	0.950 15	0.522 9	0.371 1	0.633 15	0.756 21	0.715 9	0.771 14	0.623 13	0.861 38	0.814 19	0.658 12
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PointASNL	0.666 21	0.703 43	0.781 11	0.751 27	0.655 14	0.830 10	0.471 16	0.769 18	0.474 49	0.537 24	0.951 11	0.475 18	0.279 17	0.635 13	0.698 33	0.675 18	0.751 20	0.553 38	0.816 48	0.806 22	0.703 6
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
Superpoint Network	0.683 16	0.851 9	0.728 32	0.800 13	0.653 15	0.806 27	0.468 18	0.804 11	0.572 26	0.602 11	0.946 25	0.453 29	0.239 30	0.519 38	0.822 13	0.689 16	0.762 17	0.595 23	0.895 15	0.827 13	0.630 20

SALANet	0.670 20	0.816 16	0.770 14	0.768 21	0.652 16	0.807 26	0.451 23	0.747 24	0.659 5	0.545 22	0.924 52	0.473 19	0.149 56	0.571 28	0.811 16	0.635 34	0.746 22	0.623 13	0.892 18	0.794 30	0.570 40

KP-FCNN	0.684 14	0.847 10	0.758 18	0.784 16	0.647 17	0.814 21	0.473 15	0.772 17	0.605 15	0.594 13	0.935 45	0.450 30	0.181 47	0.587 21	0.805 17	0.690 14	0.785 9	0.614 15	0.882 23	0.819 18	0.632 19
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
Feature_GeometricNet	0.690 12	0.884 3	0.754 20	0.795 14	0.647 17	0.818 18	0.422 35	0.802 13	0.612 12	0.604 10	0.945 28	0.462 23	0.189 44	0.563 30	0.853 6	0.726 5	0.765 15	0.632 10	0.904 8	0.821 17	0.606 28
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
PointConv	0.666 21	0.781 20	0.759 17	0.699 33	0.644 19	0.822 16	0.475 14	0.779 15	0.564 31	0.504 35	0.953 8	0.428 37	0.203 40	0.586 23	0.754 22	0.661 24	0.753 19	0.588 26	0.902 10	0.813 21	0.642 16
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointContrast_LA_SEM	0.683 16	0.757 31	0.784 10	0.786 15	0.639 20	0.824 15	0.408 39	0.775 16	0.604 16	0.541 23	0.934 49	0.532 6	0.269 21	0.552 32	0.777 19	0.645 31	0.793 8	0.640 8	0.913 7	0.824 14	0.671 10

ROSMRF3D	0.673 19	0.789 18	0.748 22	0.763 23	0.635 21	0.814 21	0.407 41	0.747 24	0.581 23	0.573 16	0.950 15	0.484 15	0.271 20	0.607 18	0.754 22	0.649 27	0.774 12	0.596 22	0.883 22	0.823 15	0.606 28

joint point-based	0.634 34	0.614 52	0.778 12	0.667 44	0.633 22	0.825 14	0.420 36	0.804 11	0.467 51	0.561 18	0.951 11	0.494 13	0.291 12	0.566 29	0.458 48	0.579 47	0.764 16	0.559 35	0.838 43	0.814 19	0.598 32
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
VI-PointConv	0.676 18	0.770 27	0.754 20	0.783 17	0.621 23	0.814 21	0.552 2	0.758 20	0.571 28	0.557 19	0.954 6	0.529 7	0.268 23	0.530 37	0.682 34	0.675 18	0.719 27	0.603 20	0.888 20	0.833 10	0.665 11
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
DCM-Net	0.658 23	0.778 21	0.702 37	0.806 10	0.619 24	0.813 24	0.468 18	0.693 38	0.494 45	0.524 29	0.941 37	0.449 31	0.298 11	0.510 40	0.821 14	0.675 18	0.727 26	0.568 30	0.826 45	0.803 24	0.637 18
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
Supervoxel-CNN	0.635 33	0.656 47	0.711 34	0.719 30	0.613 25	0.757 47	0.444 31	0.765 19	0.534 37	0.566 17	0.928 50	0.478 17	0.272 19	0.636 12	0.531 44	0.664 22	0.645 49	0.508 48	0.864 37	0.792 33	0.611 24

3DSM_DMMF	0.631 37	0.626 51	0.745 23	0.801 12	0.607 26	0.751 48	0.506 6	0.729 31	0.565 30	0.491 37	0.866 63	0.434 33	0.197 42	0.595 19	0.630 38	0.709 11	0.705 34	0.560 33	0.875 28	0.740 52	0.491 54

FPConv	0.639 30	0.785 19	0.760 16	0.713 32	0.603 27	0.798 33	0.392 46	0.534 55	0.603 17	0.524 29	0.948 20	0.457 25	0.250 26	0.538 35	0.723 27	0.598 42	0.696 38	0.614 15	0.872 33	0.799 25	0.567 42
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
HPEIN	0.618 42	0.729 37	0.668 49	0.647 49	0.597 28	0.766 44	0.414 37	0.680 40	0.520 40	0.525 28	0.946 25	0.432 34	0.215 35	0.493 46	0.599 40	0.638 32	0.617 54	0.570 29	0.897 13	0.806 22	0.605 30
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
PointMTL	0.632 36	0.731 36	0.688 46	0.675 39	0.591 29	0.784 39	0.444 31	0.565 53	0.610 13	0.492 36	0.949 17	0.456 26	0.254 25	0.587 21	0.706 30	0.599 41	0.665 46	0.612 18	0.868 36	0.791 36	0.579 37

FusionAwareConv	0.630 40	0.604 53	0.741 26	0.766 22	0.590 30	0.747 49	0.501 8	0.734 29	0.503 43	0.527 27	0.919 56	0.454 27	0.323 6	0.550 34	0.420 53	0.678 17	0.688 40	0.544 41	0.896 14	0.795 28	0.627 21
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
MVPNet	0.641 27	0.831 12	0.715 33	0.671 42	0.590 30	0.781 40	0.394 45	0.679 41	0.642 6	0.553 20	0.937 42	0.462 23	0.256 24	0.649 10	0.406 54	0.626 35	0.691 39	0.666 5	0.877 26	0.792 33	0.608 27
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
DVVNet	0.562 51	0.648 48	0.700 39	0.770 20	0.586 32	0.687 56	0.333 54	0.650 45	0.514 42	0.475 43	0.906 60	0.359 52	0.223 33	0.340 57	0.442 52	0.422 60	0.668 45	0.501 49	0.708 58	0.779 39	0.534 48

SAFNet-seg	0.654 25	0.752 32	0.734 28	0.664 45	0.583 33	0.815 20	0.399 43	0.754 22	0.639 7	0.535 25	0.942 35	0.470 20	0.309 8	0.665 9	0.539 42	0.650 26	0.708 32	0.635 9	0.857 40	0.793 31	0.642 16

RandLA-Net	0.645 26	0.778 21	0.731 29	0.699 33	0.577 34	0.829 11	0.446 27	0.736 28	0.477 48	0.523 31	0.945 28	0.454 27	0.269 21	0.484 47	0.749 25	0.618 38	0.738 23	0.599 21	0.827 44	0.792 33	0.621 22

PointSPNet	0.637 31	0.734 35	0.692 43	0.714 31	0.576 35	0.797 34	0.446 27	0.743 26	0.598 19	0.437 49	0.942 35	0.403 44	0.150 55	0.626 16	0.800 18	0.649 27	0.697 37	0.557 36	0.846 42	0.777 41	0.563 43

MCCNN	0.633 35	0.866 6	0.731 29	0.771 19	0.576 35	0.809 25	0.410 38	0.684 39	0.497 44	0.491 37	0.949 17	0.466 22	0.105 61	0.581 24	0.646 37	0.620 36	0.680 42	0.542 43	0.817 47	0.795 28	0.618 23
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
PointMRNet	0.640 29	0.717 41	0.701 38	0.692 35	0.576 35	0.801 29	0.467 20	0.716 33	0.563 32	0.459 45	0.953 8	0.429 36	0.169 49	0.581 24	0.854 5	0.605 39	0.710 30	0.550 39	0.894 16	0.793 31	0.575 38

SConv	0.636 32	0.830 13	0.697 41	0.752 26	0.572 38	0.780 41	0.445 29	0.716 33	0.529 38	0.530 26	0.951 11	0.446 32	0.170 48	0.507 42	0.666 36	0.636 33	0.682 41	0.541 44	0.886 21	0.799 25	0.594 34

HPGCNN	0.656 24	0.698 44	0.743 25	0.650 47	0.564 39	0.820 17	0.505 7	0.758 20	0.631 9	0.479 41	0.945 28	0.480 16	0.226 31	0.572 27	0.774 20	0.690 14	0.735 25	0.614 15	0.853 41	0.776 42	0.597 33
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
ROSMRF	0.580 49	0.772 24	0.707 35	0.681 38	0.563 40	0.764 45	0.362 52	0.515 56	0.465 52	0.465 44	0.936 43	0.427 39	0.207 37	0.438 49	0.577 41	0.536 52	0.675 43	0.486 52	0.723 57	0.779 39	0.524 50

SIConv	0.625 41	0.830 13	0.694 42	0.757 24	0.563 40	0.772 43	0.448 25	0.647 47	0.520 40	0.509 32	0.949 17	0.431 35	0.191 43	0.496 45	0.614 39	0.647 30	0.672 44	0.535 46	0.876 27	0.783 38	0.571 39

PointConv-SFPN	0.641 27	0.776 23	0.703 36	0.721 29	0.557 42	0.826 13	0.451 23	0.672 43	0.563 32	0.483 40	0.943 34	0.425 40	0.162 51	0.644 11	0.726 26	0.659 25	0.709 31	0.572 28	0.875 28	0.786 37	0.559 45

APCF-Net	0.631 37	0.742 33	0.687 48	0.672 40	0.557 42	0.792 36	0.408 39	0.665 44	0.545 35	0.508 33	0.952 10	0.428 37	0.186 45	0.634 14	0.702 31	0.620 36	0.706 33	0.555 37	0.873 32	0.798 27	0.581 36
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
SPH3D-GCN	0.610 43	0.858 8	0.772 13	0.489 60	0.532 44	0.792 36	0.404 42	0.643 48	0.570 29	0.507 34	0.935 45	0.414 43	0.046 66	0.510 40	0.702 31	0.602 40	0.705 34	0.549 40	0.859 39	0.773 43	0.534 48
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
PointNet2-SFPN	0.631 37	0.771 25	0.692 43	0.672 40	0.524 45	0.837 7	0.440 33	0.706 36	0.538 36	0.446 47	0.944 32	0.421 41	0.219 34	0.552 32	0.751 24	0.591 44	0.737 24	0.543 42	0.901 12	0.768 45	0.557 46

AttAN	0.609 44	0.760 29	0.667 50	0.649 48	0.521 46	0.793 35	0.457 22	0.648 46	0.528 39	0.434 51	0.947 23	0.401 45	0.153 54	0.454 48	0.721 28	0.648 29	0.717 28	0.536 45	0.904 8	0.765 46	0.485 55
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
SegGCN	0.589 47	0.833 11	0.731 29	0.539 58	0.514 47	0.789 38	0.448 25	0.467 57	0.573 25	0.484 39	0.936 43	0.396 46	0.061 65	0.501 43	0.507 47	0.594 43	0.700 36	0.563 32	0.874 30	0.771 44	0.493 53
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
TextureNet	0.566 50	0.672 46	0.664 51	0.671 42	0.494 48	0.719 52	0.445 29	0.678 42	0.411 58	0.396 52	0.935 45	0.356 53	0.225 32	0.412 53	0.535 43	0.565 49	0.636 53	0.464 55	0.794 51	0.680 58	0.568 41
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
Pointnet++ & Feature	0.557 52	0.735 34	0.661 52	0.686 36	0.491 49	0.744 50	0.392 46	0.539 54	0.451 54	0.375 55	0.946 25	0.376 49	0.205 38	0.403 54	0.356 56	0.553 51	0.643 50	0.497 50	0.824 46	0.756 48	0.515 51

DPC	0.592 46	0.720 39	0.700 39	0.602 54	0.480 50	0.762 46	0.380 51	0.713 35	0.585 22	0.437 49	0.940 39	0.369 50	0.288 13	0.434 51	0.509 46	0.590 46	0.639 52	0.567 31	0.772 53	0.755 49	0.592 35
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
3DMV, FTSDF	0.501 55	0.558 58	0.608 60	0.424 65	0.478 51	0.690 55	0.246 61	0.586 51	0.468 50	0.450 46	0.911 58	0.394 47	0.160 52	0.438 49	0.212 62	0.432 59	0.541 60	0.475 54	0.742 55	0.727 53	0.477 56

CCRFNet	0.589 47	0.766 28	0.659 53	0.683 37	0.470 52	0.740 51	0.387 50	0.620 49	0.490 46	0.476 42	0.922 54	0.355 54	0.245 28	0.511 39	0.511 45	0.571 48	0.643 50	0.493 51	0.872 33	0.762 47	0.600 31

LAP-D	0.594 45	0.720 39	0.692 43	0.637 51	0.456 53	0.773 42	0.391 48	0.730 30	0.587 20	0.445 48	0.940 39	0.381 48	0.288 13	0.434 51	0.453 49	0.591 44	0.649 47	0.581 27	0.777 52	0.749 51	0.610 26

PointMRNet-lite	0.553 53	0.633 50	0.648 55	0.659 46	0.430 54	0.800 30	0.390 49	0.592 50	0.454 53	0.371 56	0.939 41	0.368 51	0.136 58	0.368 55	0.448 50	0.560 50	0.715 29	0.486 52	0.882 23	0.720 54	0.462 58

3DMV	0.484 57	0.484 62	0.538 63	0.643 50	0.424 55	0.606 64	0.310 55	0.574 52	0.433 57	0.378 54	0.796 65	0.301 57	0.214 36	0.537 36	0.208 63	0.472 58	0.507 64	0.413 62	0.693 59	0.602 64	0.539 47
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PCNN	0.498 56	0.559 57	0.644 57	0.560 57	0.420 56	0.711 54	0.229 63	0.414 58	0.436 55	0.352 57	0.941 37	0.324 56	0.155 53	0.238 62	0.387 55	0.493 54	0.529 61	0.509 47	0.813 49	0.751 50	0.504 52

PanopticFusion-label	0.529 54	0.491 61	0.688 46	0.604 53	0.386 57	0.632 61	0.225 65	0.705 37	0.434 56	0.293 60	0.815 64	0.348 55	0.241 29	0.499 44	0.669 35	0.507 53	0.649 47	0.442 59	0.796 50	0.602 64	0.561 44
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
FCPN	0.447 59	0.679 45	0.604 61	0.578 56	0.380 58	0.682 57	0.291 58	0.106 67	0.483 47	0.258 65	0.920 55	0.258 61	0.025 67	0.231 64	0.325 57	0.480 57	0.560 58	0.463 56	0.725 56	0.666 60	0.231 67
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
Tangent Convolutions	0.438 62	0.437 65	0.646 56	0.474 62	0.369 59	0.645 60	0.353 53	0.258 64	0.282 66	0.279 61	0.918 57	0.298 58	0.147 57	0.283 59	0.294 58	0.487 55	0.562 57	0.427 61	0.619 62	0.633 61	0.352 62
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
PNET2	0.442 60	0.548 59	0.548 62	0.597 55	0.363 60	0.628 62	0.300 56	0.292 62	0.374 61	0.307 59	0.881 62	0.268 60	0.186 45	0.238 62	0.204 64	0.407 61	0.506 65	0.449 58	0.667 60	0.620 62	0.462 58

ScanNet+FTSDF	0.383 65	0.297 67	0.491 65	0.432 64	0.358 61	0.612 63	0.274 59	0.116 66	0.411 58	0.265 63	0.904 61	0.229 64	0.079 63	0.250 60	0.185 65	0.320 65	0.510 62	0.385 63	0.548 64	0.597 66	0.394 61

SurfaceConvPF	0.442 60	0.505 60	0.622 58	0.380 66	0.342 62	0.654 59	0.227 64	0.397 60	0.367 62	0.276 62	0.924 52	0.240 63	0.198 41	0.359 56	0.262 59	0.366 62	0.581 56	0.435 60	0.640 61	0.668 59	0.398 60
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PointCNN with RGB	0.458 58	0.577 56	0.611 59	0.356 67	0.321 63	0.715 53	0.299 57	0.376 61	0.328 64	0.319 58	0.944 32	0.285 59	0.164 50	0.216 65	0.229 61	0.484 56	0.545 59	0.456 57	0.755 54	0.709 55	0.475 57
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
SPLAT Net	0.393 64	0.472 64	0.511 64	0.606 52	0.311 64	0.656 58	0.245 62	0.405 59	0.328 64	0.197 66	0.927 51	0.227 65	0.000 69	0.001 69	0.249 60	0.271 67	0.510 62	0.383 64	0.593 63	0.699 56	0.267 65
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
ScanNet	0.306 68	0.203 68	0.366 67	0.501 59	0.311 64	0.524 66	0.211 66	0.002 69	0.342 63	0.189 67	0.786 66	0.145 68	0.102 62	0.245 61	0.152 66	0.318 66	0.348 67	0.300 67	0.460 67	0.437 68	0.182 68
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
subcloud_weak	0.411 63	0.479 63	0.650 54	0.475 61	0.285 66	0.519 67	0.087 68	0.725 32	0.396 60	0.386 53	0.621 68	0.250 62	0.117 59	0.338 58	0.443 51	0.188 68	0.594 55	0.369 65	0.377 68	0.616 63	0.306 63

PointNet++	0.339 66	0.584 55	0.478 66	0.458 63	0.256 67	0.360 68	0.250 60	0.247 65	0.278 67	0.261 64	0.677 67	0.183 66	0.117 59	0.212 66	0.145 67	0.364 63	0.346 68	0.232 68	0.548 64	0.523 67	0.252 66
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNet	0.308 67	0.353 66	0.290 68	0.278 68	0.166 68	0.553 65	0.169 67	0.286 63	0.147 68	0.148 68	0.908 59	0.182 67	0.064 64	0.023 68	0.018 69	0.354 64	0.363 66	0.345 66	0.546 66	0.685 57	0.278 64

ERROR	0.054 69	0.000 69	0.041 69	0.172 69	0.030 69	0.062 69	0.001 69	0.035 68	0.004 69	0.051 69	0.143 69	0.019 69	0.003 68	0.041 67	0.050 68	0.003 69	0.054 69	0.018 69	0.005 69	0.264 69	0.082 69

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

HAIS	0.699 1	1.000 1	0.849 2	0.820 3	0.675 1	0.808 7	0.279 3	0.757 5	0.465 6	0.517 3	0.596 1	0.559 3	0.600 7	1.000 1	0.654 5	0.767 4	0.676 2	0.994 13	0.560 3

Mask-Group	0.664 4	1.000 1	0.822 5	0.764 8	0.616 2	0.815 4	0.139 7	0.694 8	0.597 2	0.459 6	0.566 5	0.599 2	0.600 7	0.516 23	0.715 3	0.819 2	0.635 6	1.000 1	0.603 1

OccuSeg+instance	0.672 3	1.000 1	0.758 14	0.682 10	0.576 3	0.842 1	0.477 1	0.504 19	0.524 3	0.567 1	0.585 4	0.451 7	0.557 13	1.000 1	0.751 2	0.797 3	0.563 12	1.000 1	0.467 10

SSTNet	0.698 2	1.000 1	0.697 19	0.888 2	0.556 4	0.803 8	0.387 2	0.626 9	0.417 9	0.556 2	0.585 3	0.702 1	0.600 7	1.000 1	0.824 1	0.720 11	0.692 1	1.000 1	0.509 5

RPGN	0.643 7	1.000 1	0.758 13	0.582 16	0.539 5	0.826 3	0.046 17	0.765 4	0.372 12	0.436 11	0.588 2	0.539 5	0.650 2	1.000 1	0.577 7	0.750 9	0.653 5	0.997 10	0.495 8

PE	0.645 6	1.000 1	0.773 10	0.798 5	0.538 6	0.786 13	0.088 14	0.799 3	0.350 14	0.435 12	0.547 7	0.545 4	0.646 6	0.933 10	0.562 9	0.761 7	0.556 16	0.997 10	0.501 7
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
Dyco3D	0.641 8	1.000 1	0.841 3	0.893 1	0.531 7	0.802 9	0.115 11	0.588 14	0.448 7	0.438 9	0.537 8	0.430 10	0.550 14	0.857 12	0.534 10	0.764 6	0.657 3	0.987 14	0.568 2

3D-MPA	0.611 11	1.000 1	0.833 4	0.765 7	0.526 8	0.756 14	0.136 9	0.588 14	0.470 5	0.438 10	0.432 16	0.358 14	0.650 2	0.857 12	0.429 14	0.765 5	0.557 14	1.000 1	0.430 13
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
CSC-Pretrained	0.648 5	1.000 1	0.810 6	0.768 6	0.523 9	0.813 5	0.143 6	0.819 1	0.389 10	0.422 13	0.511 10	0.443 8	0.650 2	1.000 1	0.624 6	0.732 10	0.634 7	1.000 1	0.375 16

Occipital-SCS	0.512 17	1.000 1	0.716 16	0.509 17	0.506 10	0.611 18	0.092 13	0.602 13	0.177 20	0.346 18	0.383 19	0.165 20	0.442 18	0.850 16	0.386 19	0.618 20	0.543 17	0.889 20	0.389 15

PointGroup	0.636 10	1.000 1	0.765 11	0.624 11	0.505 11	0.797 10	0.116 10	0.696 7	0.384 11	0.441 8	0.559 6	0.476 6	0.596 10	1.000 1	0.666 4	0.756 8	0.556 15	0.997 10	0.513 4
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]
GICN	0.638 9	1.000 1	0.895 1	0.800 4	0.480 12	0.676 15	0.144 5	0.737 6	0.354 13	0.447 7	0.400 18	0.365 13	0.700 1	1.000 1	0.569 8	0.836 1	0.599 9	1.000 1	0.473 9

SSEN	0.575 14	1.000 1	0.761 12	0.473 18	0.477 13	0.795 11	0.066 15	0.529 17	0.658 1	0.460 5	0.461 13	0.380 12	0.331 22	0.859 11	0.401 17	0.692 16	0.653 4	1.000 1	0.348 18
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
Sparse R-CNN	0.515 16	1.000 1	0.538 25	0.282 21	0.468 14	0.790 12	0.173 4	0.345 21	0.429 8	0.413 16	0.484 11	0.176 19	0.595 11	0.591 21	0.522 11	0.668 18	0.476 19	0.986 15	0.327 19

PCJC	0.578 13	1.000 1	0.810 7	0.583 15	0.449 15	0.813 6	0.042 18	0.603 12	0.341 15	0.490 4	0.465 12	0.410 11	0.650 2	0.835 17	0.264 22	0.694 15	0.561 13	0.889 20	0.504 6

SphereNet	0.606 12	1.000 1	0.776 9	0.745 9	0.436 16	0.834 2	0.035 19	0.587 16	0.518 4	0.338 20	0.534 9	0.352 15	0.594 12	1.000 1	0.391 18	0.696 14	0.624 8	1.000 1	0.451 11

MASC	0.447 21	0.528 26	0.555 23	0.381 19	0.382 17	0.633 17	0.002 25	0.509 18	0.260 17	0.361 17	0.432 15	0.327 16	0.451 16	0.571 22	0.367 20	0.639 19	0.386 20	0.980 16	0.276 21
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
R-PointNet	0.306 25	0.500 27	0.405 28	0.311 20	0.348 18	0.589 19	0.054 16	0.068 28	0.126 22	0.283 22	0.290 21	0.028 28	0.219 25	0.214 26	0.331 21	0.396 28	0.275 25	0.821 25	0.245 22

MTML	0.549 15	1.000 1	0.807 8	0.588 14	0.327 19	0.647 16	0.004 24	0.815 2	0.180 19	0.418 14	0.364 20	0.182 18	0.445 17	1.000 1	0.442 13	0.688 17	0.571 11	1.000 1	0.396 14
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
3D-BoNet	0.488 18	1.000 1	0.672 20	0.590 13	0.301 20	0.484 26	0.098 12	0.620 10	0.306 16	0.341 19	0.259 22	0.125 22	0.434 19	0.796 18	0.402 16	0.499 25	0.513 18	0.909 19	0.439 12
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
SALoss-ResNet	0.459 20	1.000 1	0.737 15	0.159 28	0.259 21	0.587 20	0.138 8	0.475 20	0.217 18	0.416 15	0.408 17	0.128 21	0.315 23	0.714 19	0.411 15	0.536 24	0.590 10	0.873 23	0.304 20
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
PanopticFusion-inst	0.478 19	0.667 21	0.712 18	0.595 12	0.259 22	0.550 23	0.000 27	0.613 11	0.175 21	0.250 24	0.434 14	0.437 9	0.411 21	0.857 12	0.485 12	0.591 23	0.267 27	0.944 17	0.359 17
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3D-SIS	0.382 22	1.000 1	0.432 27	0.245 23	0.190 23	0.577 21	0.013 22	0.263 23	0.033 27	0.320 21	0.240 23	0.075 24	0.422 20	0.857 12	0.117 25	0.699 12	0.271 26	0.883 22	0.235 23
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
UNet-backbone	0.319 24	0.667 21	0.715 17	0.233 24	0.189 24	0.479 27	0.008 23	0.218 24	0.067 26	0.201 25	0.173 25	0.107 23	0.123 27	0.438 24	0.150 23	0.615 21	0.355 21	0.916 18	0.093 29

RandSA	0.250 26	0.333 28	0.613 21	0.229 25	0.163 25	0.493 24	0.000 27	0.304 22	0.107 23	0.147 27	0.100 26	0.052 27	0.231 24	0.119 27	0.039 27	0.445 27	0.325 22	0.654 26	0.141 26

Hier3D	0.323 23	0.667 21	0.542 24	0.264 22	0.157 26	0.550 22	0.000 27	0.205 26	0.009 28	0.270 23	0.218 24	0.075 24	0.500 15	0.688 20	0.007 30	0.698 13	0.301 24	0.459 28	0.200 24
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region	0.248 27	0.667 21	0.437 26	0.188 26	0.153 27	0.491 25	0.000 27	0.208 25	0.094 25	0.153 26	0.099 27	0.057 26	0.217 26	0.119 27	0.039 27	0.466 26	0.302 23	0.640 27	0.140 27

Sgpn_scannet	0.143 29	0.208 30	0.390 29	0.169 27	0.065 28	0.275 29	0.029 20	0.069 27	0.000 29	0.087 29	0.043 28	0.014 30	0.027 30	0.000 29	0.112 26	0.351 29	0.168 29	0.438 29	0.138 28

MaskRCNN 2d->3d Proj	0.058 30	0.333 28	0.002 30	0.000 30	0.053 29	0.002 30	0.002 26	0.021 30	0.000 29	0.045 30	0.024 30	0.238 17	0.065 29	0.000 29	0.014 29	0.107 30	0.020 30	0.110 30	0.006 30

3D-BEVIS	0.248 27	0.667 21	0.566 22	0.076 29	0.035 30	0.394 28	0.027 21	0.035 29	0.098 24	0.099 28	0.030 29	0.025 29	0.098 28	0.375 25	0.126 24	0.604 22	0.181 28	0.854 24	0.171 25
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.

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 10	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 6	0.769 2	0.656 3	0.567 3	0.931 3	0.395 3	0.390 4	0.700 2	0.534 3	0.689 5	0.770 2	0.574 3	0.865 3	0.831 3	0.675 2
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
CU-Hybrid-2D Net	0.636 3	0.825 2	0.820 2	0.179 16	0.648 3	0.463 3	0.549 1	0.742 3	0.676 2	0.628 2	0.961 1	0.420 2	0.379 5	0.684 3	0.381 10	0.732 2	0.723 3	0.599 2	0.827 8	0.851 2	0.634 3

DMMF_3d	0.605 4	0.651 6	0.744 7	0.782 3	0.637 4	0.387 4	0.536 2	0.732 4	0.590 5	0.540 4	0.856 13	0.359 6	0.306 10	0.596 6	0.539 2	0.627 12	0.706 4	0.497 6	0.785 12	0.757 11	0.476 13

MCA-Net	0.595 6	0.533 12	0.756 5	0.746 5	0.590 5	0.334 8	0.506 3	0.670 7	0.587 6	0.500 8	0.905 8	0.366 5	0.352 6	0.601 5	0.506 6	0.669 10	0.648 6	0.501 5	0.839 7	0.769 9	0.516 12

DMMF	0.597 5	0.543 11	0.755 6	0.749 4	0.585 6	0.338 6	0.494 4	0.704 6	0.598 4	0.494 10	0.911 6	0.347 8	0.327 9	0.593 7	0.527 4	0.675 7	0.646 8	0.513 4	0.842 6	0.774 8	0.527 11

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

SSMA	0.577 9	0.695 4	0.716 10	0.439 12	0.563 8	0.314 10	0.444 8	0.719 5	0.551 7	0.503 7	0.887 10	0.346 9	0.348 7	0.603 4	0.353 12	0.709 3	0.600 11	0.457 10	0.901 2	0.786 6	0.599 7
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
SN_RN152pyrx8_RVC	0.546 10	0.572 9	0.663 13	0.638 8	0.518 9	0.298 12	0.366 15	0.633 12	0.510 11	0.446 12	0.864 11	0.296 11	0.267 12	0.542 10	0.346 13	0.704 4	0.575 14	0.431 12	0.853 5	0.766 10	0.630 4

FuseNet	0.535 11	0.570 10	0.681 12	0.182 15	0.512 10	0.290 13	0.431 9	0.659 9	0.504 12	0.495 9	0.903 9	0.308 10	0.428 3	0.523 12	0.365 11	0.676 6	0.621 10	0.470 9	0.762 13	0.779 7	0.541 9
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
DCRedNet	0.583 8	0.682 5	0.723 8	0.542 10	0.510 11	0.310 11	0.451 6	0.668 8	0.549 8	0.520 6	0.920 5	0.375 4	0.446 2	0.528 11	0.417 9	0.670 9	0.577 13	0.478 8	0.862 4	0.806 5	0.628 5

ILC-PSPNet	0.475 15	0.490 14	0.581 15	0.289 14	0.507 12	0.067 17	0.379 13	0.610 14	0.417 15	0.435 13	0.822 16	0.278 12	0.267 12	0.503 13	0.228 14	0.616 14	0.533 15	0.375 14	0.820 9	0.729 12	0.560 8

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

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

SE-ResNeXt-SSMA	0.498 2	0.000 3	0.812 2	0.941 1	0.500 1	0.500 2	0.500 2	0.500 1	0.429 3	0.500 2	0.667 2	0.500 1	0.625 2	0.000 1
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
multi-task	0.700 1	0.500 1	1.000 1	0.882 2	0.500 1	1.000 1	1.000 1	0.500 1	1.000 1	1.000 1	0.778 1	0.000 2	0.938 1	0.000 1
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
resnet50_scannet	0.353 3	0.250 2	0.812 2	0.529 3	0.500 1	0.500 2	0.000 3	0.500 1	0.571 2	0.000 3	0.556 3	0.000 2	0.375 3	0.000 1

3D Semantic label benchmark

3D Semantic instance benchmark

2D Semantic label benchmark

2D Semantic instance benchmark

Scene type classification benchmark