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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
OccuSeg+Semantic0.764 10.758 300.796 70.839 40.746 20.907 10.562 10.850 50.680 20.672 10.978 10.610 10.335 30.777 10.819 150.847 10.830 10.691 30.972 10.885 10.727 2
SparseConvNet0.725 60.647 490.821 20.846 30.721 50.869 20.533 30.754 220.603 170.614 60.955 50.572 30.325 50.710 70.870 30.724 70.823 20.628 120.934 50.865 30.683 8
Virtual MVFusion0.746 30.771 250.819 30.848 20.702 80.865 30.397 440.899 10.699 10.664 20.948 200.588 20.330 40.746 50.851 80.764 30.796 70.704 10.935 40.866 20.728 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
VMNet0.746 30.870 50.838 10.858 10.729 40.850 40.501 80.874 20.587 200.658 30.956 40.564 40.299 100.765 30.900 10.716 80.812 40.631 110.939 20.858 40.709 5
MinkowskiNetpermissive0.736 50.859 70.818 40.832 50.709 70.840 50.521 50.853 40.660 40.643 50.951 110.544 50.286 150.731 60.893 20.675 180.772 130.683 40.874 300.852 60.727 2
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
BPNetcopyleft0.749 20.909 10.818 40.811 80.752 10.839 60.485 130.842 70.673 30.644 40.957 30.528 80.305 90.773 20.859 40.788 20.818 30.693 20.916 60.856 50.723 4
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointNet2-SFPN0.631 370.771 250.692 430.672 400.524 450.837 70.440 330.706 360.538 360.446 470.944 320.421 410.219 340.552 320.751 240.591 440.737 240.543 420.901 120.768 450.557 46
MatchingNet0.724 70.812 170.812 60.810 90.735 30.834 80.495 110.860 30.572 260.602 110.954 60.512 100.280 160.757 40.845 110.725 60.780 100.606 190.937 30.851 70.700 7
One Thing One Click0.701 90.825 150.796 70.723 280.716 60.832 90.433 340.816 80.634 80.609 80.969 20.418 420.344 20.559 310.833 120.715 90.808 50.560 330.902 100.847 80.680 9
PointASNLpermissive0.666 210.703 430.781 110.751 270.655 140.830 100.471 160.769 180.474 490.537 240.951 110.475 180.279 170.635 130.698 330.675 180.751 200.553 380.816 480.806 220.703 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
RandLA-Netpermissive0.645 260.778 210.731 290.699 330.577 340.829 110.446 270.736 280.477 480.523 310.945 280.454 270.269 210.484 470.749 250.618 380.738 230.599 210.827 440.792 330.621 22
FusionNet0.688 130.704 420.741 260.754 250.656 130.829 110.501 80.741 270.609 140.548 210.950 150.522 90.371 10.633 150.756 210.715 90.771 140.623 130.861 380.814 190.658 12
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PointConv-SFPN0.641 270.776 230.703 360.721 290.557 420.826 130.451 230.672 430.563 320.483 400.943 340.425 400.162 510.644 110.726 260.659 250.709 310.572 280.875 280.786 370.559 45
joint point-basedpermissive0.634 340.614 520.778 120.667 440.633 220.825 140.420 360.804 110.467 510.561 180.951 110.494 130.291 120.566 290.458 480.579 470.764 160.559 350.838 430.814 190.598 32
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointContrast_LA_SEM0.683 160.757 310.784 100.786 150.639 200.824 150.408 390.775 160.604 160.541 230.934 490.532 60.269 210.552 320.777 190.645 310.793 80.640 80.913 70.824 140.671 10
PointConvpermissive0.666 210.781 200.759 170.699 330.644 190.822 160.475 140.779 150.564 310.504 350.953 80.428 370.203 400.586 230.754 220.661 240.753 190.588 260.902 100.813 210.642 16
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
HPGCNN0.656 240.698 440.743 250.650 470.564 390.820 170.505 70.758 200.631 90.479 410.945 280.480 160.226 310.572 270.774 200.690 140.735 250.614 150.853 410.776 420.597 33
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
Feature_GeometricNetpermissive0.690 120.884 30.754 200.795 140.647 170.818 180.422 350.802 130.612 120.604 100.945 280.462 230.189 440.563 300.853 60.726 50.765 150.632 100.904 80.821 170.606 28
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
RFCR0.702 80.889 20.745 230.813 70.672 110.818 180.493 120.815 100.623 100.610 70.947 230.470 200.249 270.594 200.848 90.705 120.779 110.646 70.892 180.823 150.611 24
SAFNet-segcopyleft0.654 250.752 320.734 280.664 450.583 330.815 200.399 430.754 220.639 70.535 250.942 350.470 200.309 80.665 90.539 420.650 260.708 320.635 90.857 400.793 310.642 16
VI-PointConv0.676 180.770 270.754 200.783 170.621 230.814 210.552 20.758 200.571 280.557 190.954 60.529 70.268 230.530 370.682 340.675 180.719 270.603 200.888 200.833 100.665 11
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
KP-FCNN0.684 140.847 100.758 180.784 160.647 170.814 210.473 150.772 170.605 150.594 130.935 450.450 300.181 470.587 210.805 170.690 140.785 90.614 150.882 230.819 180.632 19
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
ROSMRF3D0.673 190.789 180.748 220.763 230.635 210.814 210.407 410.747 240.581 230.573 160.950 150.484 150.271 200.607 180.754 220.649 270.774 120.596 220.883 220.823 150.606 28
DCM-Net0.658 230.778 210.702 370.806 100.619 240.813 240.468 180.693 380.494 450.524 290.941 370.449 310.298 110.510 400.821 140.675 180.727 260.568 300.826 450.803 240.637 18
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
MCCNNpermissive0.633 350.866 60.731 290.771 190.576 350.809 250.410 380.684 390.497 440.491 370.949 170.466 220.105 610.581 240.646 370.620 360.680 420.542 430.817 470.795 280.618 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
SALANet0.670 200.816 160.770 140.768 210.652 160.807 260.451 230.747 240.659 50.545 220.924 520.473 190.149 560.571 280.811 160.635 340.746 220.623 130.892 180.794 300.570 40
Superpoint Network0.683 160.851 90.728 320.800 130.653 150.806 270.468 180.804 110.572 260.602 110.946 250.453 290.239 300.519 380.822 130.689 160.762 170.595 230.895 150.827 130.630 20
VACNN++0.684 140.728 380.757 190.776 180.690 90.804 280.464 210.816 80.577 240.587 150.945 280.508 110.276 180.671 80.710 290.663 230.750 210.589 250.881 250.832 110.653 13
PointMRNet0.640 290.717 410.701 380.692 350.576 350.801 290.467 200.716 330.563 320.459 450.953 80.429 360.169 490.581 240.854 50.605 390.710 300.550 390.894 160.793 310.575 38
JSENet0.699 100.881 40.762 150.821 60.667 120.800 300.522 40.792 140.613 110.607 90.935 450.492 140.205 380.576 260.853 60.691 130.758 180.652 60.872 330.828 120.649 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
CU-Hybrid Net0.693 110.596 540.789 90.803 110.677 100.800 300.469 170.846 60.554 340.591 140.948 200.500 120.316 70.609 170.847 100.732 40.808 50.593 240.894 160.839 90.652 14
PointMRNet-lite0.553 530.633 500.648 550.659 460.430 540.800 300.390 490.592 500.454 530.371 560.939 410.368 510.136 580.368 550.448 500.560 500.715 290.486 520.882 230.720 540.462 58
FPConvpermissive0.639 300.785 190.760 160.713 320.603 270.798 330.392 460.534 550.603 170.524 290.948 200.457 250.250 260.538 350.723 270.598 420.696 380.614 150.872 330.799 250.567 42
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PointSPNet0.637 310.734 350.692 430.714 310.576 350.797 340.446 270.743 260.598 190.437 490.942 350.403 440.150 550.626 160.800 180.649 270.697 370.557 360.846 420.777 410.563 43
AttAN0.609 440.760 290.667 500.649 480.521 460.793 350.457 220.648 460.528 390.434 510.947 230.401 450.153 540.454 480.721 280.648 290.717 280.536 450.904 80.765 460.485 55
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
APCF-Net0.631 370.742 330.687 480.672 400.557 420.792 360.408 390.665 440.545 350.508 330.952 100.428 370.186 450.634 140.702 310.620 360.706 330.555 370.873 320.798 270.581 36
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
SPH3D-GCNpermissive0.610 430.858 80.772 130.489 600.532 440.792 360.404 420.643 480.570 290.507 340.935 450.414 430.046 660.510 400.702 310.602 400.705 340.549 400.859 390.773 430.534 48
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
SegGCNpermissive0.589 470.833 110.731 290.539 580.514 470.789 380.448 250.467 570.573 250.484 390.936 430.396 460.061 650.501 430.507 470.594 430.700 360.563 320.874 300.771 440.493 53
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
PointMTL0.632 360.731 360.688 460.675 390.591 290.784 390.444 310.565 530.610 130.492 360.949 170.456 260.254 250.587 210.706 300.599 410.665 460.612 180.868 360.791 360.579 37
MVPNetpermissive0.641 270.831 120.715 330.671 420.590 300.781 400.394 450.679 410.642 60.553 200.937 420.462 230.256 240.649 100.406 540.626 350.691 390.666 50.877 260.792 330.608 27
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
SConv0.636 320.830 130.697 410.752 260.572 380.780 410.445 290.716 330.529 380.530 260.951 110.446 320.170 480.507 420.666 360.636 330.682 410.541 440.886 210.799 250.594 34
LAP-D0.594 450.720 390.692 430.637 510.456 530.773 420.391 480.730 300.587 200.445 480.940 390.381 480.288 130.434 510.453 490.591 440.649 470.581 270.777 520.749 510.610 26
SIConv0.625 410.830 130.694 420.757 240.563 400.772 430.448 250.647 470.520 400.509 320.949 170.431 350.191 430.496 450.614 390.647 300.672 440.535 460.876 270.783 380.571 39
HPEIN0.618 420.729 370.668 490.647 490.597 280.766 440.414 370.680 400.520 400.525 280.946 250.432 340.215 350.493 460.599 400.638 320.617 540.570 290.897 130.806 220.605 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
ROSMRF0.580 490.772 240.707 350.681 380.563 400.764 450.362 520.515 560.465 520.465 440.936 430.427 390.207 370.438 490.577 410.536 520.675 430.486 520.723 570.779 390.524 50
DPC0.592 460.720 390.700 390.602 540.480 500.762 460.380 510.713 350.585 220.437 490.940 390.369 500.288 130.434 510.509 460.590 460.639 520.567 310.772 530.755 490.592 35
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
Supervoxel-CNN0.635 330.656 470.711 340.719 300.613 250.757 470.444 310.765 190.534 370.566 170.928 500.478 170.272 190.636 120.531 440.664 220.645 490.508 480.864 370.792 330.611 24
3DSM_DMMF0.631 370.626 510.745 230.801 120.607 260.751 480.506 60.729 310.565 300.491 370.866 630.434 330.197 420.595 190.630 380.709 110.705 340.560 330.875 280.740 520.491 54
FusionAwareConv0.630 400.604 530.741 260.766 220.590 300.747 490.501 80.734 290.503 430.527 270.919 560.454 270.323 60.550 340.420 530.678 170.688 400.544 410.896 140.795 280.627 21
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
Pointnet++ & Featurepermissive0.557 520.735 340.661 520.686 360.491 490.744 500.392 460.539 540.451 540.375 550.946 250.376 490.205 380.403 540.356 560.553 510.643 500.497 500.824 460.756 480.515 51
CCRFNet0.589 470.766 280.659 530.683 370.470 520.740 510.387 500.620 490.490 460.476 420.922 540.355 540.245 280.511 390.511 450.571 480.643 500.493 510.872 330.762 470.600 31
TextureNetpermissive0.566 500.672 460.664 510.671 420.494 480.719 520.445 290.678 420.411 580.396 520.935 450.356 530.225 320.412 530.535 430.565 490.636 530.464 550.794 510.680 580.568 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
PointCNN with RGBpermissive0.458 580.577 560.611 590.356 670.321 630.715 530.299 570.376 610.328 640.319 580.944 320.285 590.164 500.216 650.229 610.484 560.545 590.456 570.755 540.709 550.475 57
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
PCNN0.498 560.559 570.644 570.560 570.420 560.711 540.229 630.414 580.436 550.352 570.941 370.324 560.155 530.238 620.387 550.493 540.529 610.509 470.813 490.751 500.504 52
3DMV, FTSDF0.501 550.558 580.608 600.424 650.478 510.690 550.246 610.586 510.468 500.450 460.911 580.394 470.160 520.438 490.212 620.432 590.541 600.475 540.742 550.727 530.477 56
DVVNet0.562 510.648 480.700 390.770 200.586 320.687 560.333 540.650 450.514 420.475 430.906 600.359 520.223 330.340 570.442 520.422 600.668 450.501 490.708 580.779 390.534 48
FCPNpermissive0.447 590.679 450.604 610.578 560.380 580.682 570.291 580.106 670.483 470.258 650.920 550.258 610.025 670.231 640.325 570.480 570.560 580.463 560.725 560.666 600.231 67
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
SPLAT Netcopyleft0.393 640.472 640.511 640.606 520.311 640.656 580.245 620.405 590.328 640.197 660.927 510.227 650.000 690.001 690.249 600.271 670.510 620.383 640.593 630.699 560.267 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
SurfaceConvPF0.442 600.505 600.622 580.380 660.342 620.654 590.227 640.397 600.367 620.276 620.924 520.240 630.198 410.359 560.262 590.366 620.581 560.435 600.640 610.668 590.398 60
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 620.437 650.646 560.474 620.369 590.645 600.353 530.258 640.282 660.279 610.918 570.298 580.147 570.283 590.294 580.487 550.562 570.427 610.619 620.633 610.352 62
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
PanopticFusion-label0.529 540.491 610.688 460.604 530.386 570.632 610.225 650.705 370.434 560.293 600.815 640.348 550.241 290.499 440.669 350.507 530.649 470.442 590.796 500.602 640.561 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)
PNET20.442 600.548 590.548 620.597 550.363 600.628 620.300 560.292 620.374 610.307 590.881 620.268 600.186 450.238 620.204 640.407 610.506 650.449 580.667 600.620 620.462 58
ScanNet+FTSDF0.383 650.297 670.491 650.432 640.358 610.612 630.274 590.116 660.411 580.265 630.904 610.229 640.079 630.250 600.185 650.320 650.510 620.385 630.548 640.597 660.394 61
3DMV0.484 570.484 620.538 630.643 500.424 550.606 640.310 550.574 520.433 570.378 540.796 650.301 570.214 360.537 360.208 630.472 580.507 640.413 620.693 590.602 640.539 47
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
SSC-UNetpermissive0.308 670.353 660.290 680.278 680.166 680.553 650.169 670.286 630.147 680.148 680.908 590.182 670.064 640.023 680.018 690.354 640.363 660.345 660.546 660.685 570.278 64
ScanNetpermissive0.306 680.203 680.366 670.501 590.311 640.524 660.211 660.002 690.342 630.189 670.786 660.145 680.102 620.245 610.152 660.318 660.348 670.300 670.460 670.437 680.182 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_weak0.411 630.479 630.650 540.475 610.285 660.519 670.087 680.725 320.396 600.386 530.621 680.250 620.117 590.338 580.443 510.188 680.594 550.369 650.377 680.616 630.306 63
PointNet++permissive0.339 660.584 550.478 660.458 630.256 670.360 680.250 600.247 650.278 670.261 640.677 670.183 660.117 590.212 660.145 670.364 630.346 680.232 680.548 640.523 670.252 66
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
ERROR0.054 690.000 690.041 690.172 690.030 690.062 690.001 690.035 680.004 690.051 690.143 690.019 690.003 680.041 670.050 680.003 690.054 690.018 690.005 690.264 690.082 69

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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
OccuSeg+instance0.672 31.000 10.758 140.682 100.576 30.842 10.477 10.504 190.524 30.567 10.585 40.451 70.557 131.000 10.751 20.797 30.563 121.000 10.467 10
SphereNet0.606 121.000 10.776 90.745 90.436 160.834 20.035 190.587 160.518 40.338 200.534 90.352 150.594 121.000 10.391 180.696 140.624 81.000 10.451 11
RPGN0.643 71.000 10.758 130.582 160.539 50.826 30.046 170.765 40.372 120.436 110.588 20.539 50.650 21.000 10.577 70.750 90.653 50.997 100.495 8
Mask-Group0.664 41.000 10.822 50.764 80.616 20.815 40.139 70.694 80.597 20.459 60.566 50.599 20.600 70.516 230.715 30.819 20.635 61.000 10.603 1
CSC-Pretrained0.648 51.000 10.810 60.768 60.523 90.813 50.143 60.819 10.389 100.422 130.511 100.443 80.650 21.000 10.624 60.732 100.634 71.000 10.375 16
PCJC0.578 131.000 10.810 70.583 150.449 150.813 60.042 180.603 120.341 150.490 40.465 120.410 110.650 20.835 170.264 220.694 150.561 130.889 200.504 6
HAIS0.699 11.000 10.849 20.820 30.675 10.808 70.279 30.757 50.465 60.517 30.596 10.559 30.600 71.000 10.654 50.767 40.676 20.994 130.560 3
SSTNet0.698 21.000 10.697 190.888 20.556 40.803 80.387 20.626 90.417 90.556 20.585 30.702 10.600 71.000 10.824 10.720 110.692 11.000 10.509 5
Dyco3Dcopyleft0.641 81.000 10.841 30.893 10.531 70.802 90.115 110.588 140.448 70.438 90.537 80.430 100.550 140.857 120.534 100.764 60.657 30.987 140.568 2
PointGroup0.636 101.000 10.765 110.624 110.505 110.797 100.116 100.696 70.384 110.441 80.559 60.476 60.596 101.000 10.666 40.756 80.556 150.997 100.513 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]
SSEN0.575 141.000 10.761 120.473 180.477 130.795 110.066 150.529 170.658 10.460 50.461 130.380 120.331 220.859 110.401 170.692 160.653 41.000 10.348 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-CNN0.515 161.000 10.538 250.282 210.468 140.790 120.173 40.345 210.429 80.413 160.484 110.176 190.595 110.591 210.522 110.668 180.476 190.986 150.327 19
PE0.645 61.000 10.773 100.798 50.538 60.786 130.088 140.799 30.350 140.435 120.547 70.545 40.646 60.933 100.562 90.761 70.556 160.997 100.501 7
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
3D-MPA0.611 111.000 10.833 40.765 70.526 80.756 140.136 90.588 140.470 50.438 100.432 160.358 140.650 20.857 120.429 140.765 50.557 141.000 10.430 13
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
GICN0.638 91.000 10.895 10.800 40.480 120.676 150.144 50.737 60.354 130.447 70.400 180.365 130.700 11.000 10.569 80.836 10.599 91.000 10.473 9
MTML0.549 151.000 10.807 80.588 140.327 190.647 160.004 240.815 20.180 190.418 140.364 200.182 180.445 171.000 10.442 130.688 170.571 111.000 10.396 14
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
MASCpermissive0.447 210.528 260.555 230.381 190.382 170.633 170.002 250.509 180.260 170.361 170.432 150.327 160.451 160.571 220.367 200.639 190.386 200.980 160.276 21
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
Occipital-SCS0.512 171.000 10.716 160.509 170.506 100.611 180.092 130.602 130.177 200.346 180.383 190.165 200.442 180.850 160.386 190.618 200.543 170.889 200.389 15
R-PointNet0.306 250.500 270.405 280.311 200.348 180.589 190.054 160.068 280.126 220.283 220.290 210.028 280.219 250.214 260.331 210.396 280.275 250.821 250.245 22
SALoss-ResNet0.459 201.000 10.737 150.159 280.259 210.587 200.138 80.475 200.217 180.416 150.408 170.128 210.315 230.714 190.411 150.536 240.590 100.873 230.304 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)
3D-SISpermissive0.382 221.000 10.432 270.245 230.190 230.577 210.013 220.263 230.033 270.320 210.240 230.075 240.422 200.857 120.117 250.699 120.271 260.883 220.235 23
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3Dcopyleft0.323 230.667 210.542 240.264 220.157 260.550 220.000 270.205 260.009 280.270 230.218 240.075 240.500 150.688 200.007 300.698 130.301 240.459 280.200 24
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
PanopticFusion-inst0.478 190.667 210.712 180.595 120.259 220.550 230.000 270.613 110.175 210.250 240.434 140.437 90.411 210.857 120.485 120.591 230.267 270.944 170.359 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)
RandSA0.250 260.333 280.613 210.229 250.163 250.493 240.000 270.304 220.107 230.147 270.100 260.052 270.231 240.119 270.039 270.445 270.325 220.654 260.141 26
Region0.248 270.667 210.437 260.188 260.153 270.491 250.000 270.208 250.094 250.153 260.099 270.057 260.217 260.119 270.039 270.466 260.302 230.640 270.140 27
3D-BoNet0.488 181.000 10.672 200.590 130.301 200.484 260.098 120.620 100.306 160.341 190.259 220.125 220.434 190.796 180.402 160.499 250.513 180.909 190.439 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
UNet-backbone0.319 240.667 210.715 170.233 240.189 240.479 270.008 230.218 240.067 260.201 250.173 250.107 230.123 270.438 240.150 230.615 210.355 210.916 180.093 29
3D-BEVIS0.248 270.667 210.566 220.076 290.035 300.394 280.027 210.035 290.098 240.099 280.030 290.025 290.098 280.375 250.126 240.604 220.181 280.854 240.171 25
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.143 290.208 300.390 290.169 270.065 280.275 290.029 200.069 270.000 290.087 290.043 280.014 300.027 300.000 290.112 260.351 290.168 290.438 290.138 28
MaskRCNN 2d->3d Proj0.058 300.333 280.002 300.000 300.053 290.002 300.002 260.021 300.000 290.045 300.024 300.238 170.065 290.000 290.014 290.107 300.020 300.110 300.006 30

This table lists the benchmark results for the 2D semantic label scenario.


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Virtual MVFusion (R)0.745 10.861 10.839 10.881 10.672 10.512 10.422 100.898 10.723 10.714 10.954 20.454 10.509 10.773 10.895 10.756 10.820 10.653 10.935 10.891 10.728 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_2Dcopyleft0.670 20.822 30.795 30.836 20.659 20.481 20.451 60.769 20.656 30.567 30.931 30.395 30.390 40.700 20.534 30.689 50.770 20.574 30.865 30.831 30.675 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 Net0.636 30.825 20.820 20.179 160.648 30.463 30.549 10.742 30.676 20.628 20.961 10.420 20.379 50.684 30.381 100.732 20.723 30.599 20.827 80.851 20.634 3
DMMF_3d0.605 40.651 60.744 70.782 30.637 40.387 40.536 20.732 40.590 50.540 40.856 130.359 60.306 100.596 60.539 20.627 120.706 40.497 60.785 120.757 110.476 13
3DMV (2d proj)0.498 130.481 150.612 140.579 90.456 130.343 50.384 120.623 130.525 100.381 140.845 140.254 130.264 140.557 90.182 150.581 150.598 120.429 130.760 140.661 160.446 15
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
DMMF0.597 50.543 110.755 60.749 40.585 60.338 60.494 40.704 60.598 40.494 100.911 60.347 80.327 90.593 70.527 40.675 70.646 80.513 40.842 60.774 80.527 11
AdapNet++copyleft0.503 120.613 80.722 90.418 130.358 170.337 70.370 140.479 150.443 130.368 150.907 70.207 140.213 160.464 150.525 50.618 130.657 50.450 110.788 110.721 140.408 16
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
MCA-Net0.595 60.533 120.756 50.746 50.590 50.334 80.506 30.670 70.587 60.500 80.905 80.366 50.352 60.601 50.506 60.669 100.648 60.501 50.839 70.769 90.516 12
RFBNet0.592 70.616 70.758 40.659 60.581 70.330 90.469 50.655 100.543 90.524 50.924 40.355 70.336 80.572 80.479 80.671 80.648 60.480 70.814 100.814 40.614 6
SSMAcopyleft0.577 90.695 40.716 100.439 120.563 80.314 100.444 80.719 50.551 70.503 70.887 100.346 90.348 70.603 40.353 120.709 30.600 110.457 100.901 20.786 60.599 7
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DCRedNet0.583 80.682 50.723 80.542 100.510 110.310 110.451 60.668 80.549 80.520 60.920 50.375 40.446 20.528 110.417 90.670 90.577 130.478 80.862 40.806 50.628 5
SN_RN152pyrx8_RVCcopyleft0.546 100.572 90.663 130.638 80.518 90.298 120.366 150.633 120.510 110.446 120.864 110.296 110.267 120.542 100.346 130.704 40.575 140.431 120.853 50.766 100.630 4
FuseNetpermissive0.535 110.570 100.681 120.182 150.512 100.290 130.431 90.659 90.504 120.495 90.903 90.308 100.428 30.523 120.365 110.676 60.621 100.470 90.762 130.779 70.541 9
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
MSeg1080_RVCpermissive0.485 140.505 130.709 110.092 170.427 140.241 140.411 110.654 110.385 170.457 110.861 120.053 170.279 110.503 130.481 70.645 110.626 90.365 150.748 150.725 130.529 10
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
Enet (reimpl)0.376 160.264 170.452 170.452 110.365 150.181 150.143 170.456 160.409 160.346 160.769 170.164 150.218 150.359 160.123 170.403 170.381 170.313 170.571 160.685 150.472 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)permissive0.330 170.293 160.521 160.657 70.361 160.161 160.250 160.004 170.440 140.183 170.836 150.125 160.060 170.319 170.132 160.417 160.412 160.344 160.541 170.427 170.109 17
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ILC-PSPNet0.475 150.490 140.581 150.289 140.507 120.067 170.379 130.610 140.417 150.435 130.822 160.278 120.267 120.503 130.228 140.616 140.533 150.375 140.820 90.729 120.560 8

This table lists the benchmark results for the 2D semantic instance scenario.




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
UniDet_RVC0.205 10.381 10.323 10.037 10.226 10.177 10.063 10.277 10.120 10.067 10.131 10.074 20.317 10.080 10.235 10.289 10.141 10.678 10.080 1
MaskRCNN_ScanNetpermissive0.119 20.129 20.212 20.002 20.112 20.148 20.014 20.205 20.044 20.066 20.078 20.095 10.142 20.030 20.128 20.139 20.080 20.459 20.057 2
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17

This table lists the benchmark results for the scene type classification scenario.




Method Infoavg recallapartmentbathroombedroom / hotelbookstore / libraryconference roomcopy/mail roomhallwaykitchenlaundry roomliving room / loungemiscofficestorage / basement / garage
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
multi-taskpermissive0.700 10.500 11.000 10.882 20.500 11.000 11.000 10.500 11.000 11.000 10.778 10.000 20.938 10.000 1
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
SE-ResNeXt-SSMA0.498 20.000 30.812 20.941 10.500 10.500 20.500 20.500 10.429 30.500 20.667 20.500 10.625 20.000 1
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
resnet50_scannet0.353 30.250 20.812 20.529 30.500 10.500 20.000 30.500 10.571 20.000 30.556 30.000 20.375 30.000 1