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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort by
Mix3Dpermissive0.781 10.964 10.855 10.843 50.781 10.858 40.575 20.831 90.685 30.714 10.979 10.594 20.310 100.801 10.892 30.841 20.819 30.723 20.940 30.887 10.725 5
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
OccuSeg+Semantic0.764 20.758 340.796 90.839 60.746 40.907 10.562 30.850 50.680 40.672 20.978 20.610 10.335 40.777 20.819 180.847 10.830 10.691 50.972 10.885 20.727 3
O-CNNpermissive0.762 30.924 20.823 30.844 40.770 20.852 50.577 10.847 60.711 10.640 70.958 50.592 30.217 380.762 50.888 40.758 50.813 50.726 10.932 80.868 30.744 1
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 MVFusion0.746 50.771 290.819 50.848 20.702 100.865 30.397 490.899 10.699 20.664 30.948 230.588 40.330 50.746 80.851 110.764 40.796 90.704 30.935 60.866 40.728 2
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
SparseConvNet0.725 80.647 540.821 40.846 30.721 70.869 20.533 50.754 250.603 210.614 90.955 80.572 50.325 70.710 100.870 50.724 100.823 20.628 150.934 70.865 50.683 10
VMNetpermissive0.746 50.870 80.838 20.858 10.729 60.850 60.501 100.874 20.587 240.658 40.956 70.564 60.299 130.765 40.900 10.716 110.812 60.631 140.939 40.858 60.709 7
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)
BPNetcopyleft0.749 40.909 30.818 60.811 100.752 30.839 80.485 160.842 80.673 50.644 50.957 60.528 100.305 120.773 30.859 60.788 30.818 40.693 40.916 90.856 70.723 6
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-Click0.693 130.743 370.794 110.655 510.684 120.822 180.497 130.719 360.622 130.617 80.977 30.447 360.339 30.750 70.664 400.703 160.790 110.596 250.946 20.855 80.647 18
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
MinkowskiNetpermissive0.736 70.859 100.818 60.832 70.709 90.840 70.521 70.853 40.660 60.643 60.951 140.544 70.286 180.731 90.893 20.675 220.772 160.683 60.874 350.852 90.727 3
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
MatchingNet0.724 90.812 200.812 80.810 110.735 50.834 100.495 140.860 30.572 300.602 150.954 90.512 120.280 190.757 60.845 140.725 90.780 130.606 220.937 50.851 100.700 9
One Thing One Click0.701 110.825 180.796 90.723 310.716 80.832 110.433 380.816 100.634 100.609 110.969 40.418 470.344 20.559 350.833 150.715 120.808 70.560 380.902 140.847 110.680 11
CU-Hybrid Net0.693 130.596 600.789 120.803 130.677 130.800 350.469 200.846 70.554 380.591 180.948 230.500 140.316 90.609 200.847 130.732 60.808 70.593 280.894 200.839 120.652 16
VI-PointConv0.676 220.770 310.754 230.783 200.621 270.814 250.552 40.758 230.571 320.557 230.954 90.529 90.268 260.530 410.682 370.675 220.719 320.603 230.888 240.833 130.665 13
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
VACNN++0.684 180.728 430.757 220.776 210.690 110.804 330.464 240.816 100.577 280.587 190.945 310.508 130.276 210.671 110.710 320.663 270.750 260.589 300.881 290.832 140.653 15
JSENetpermissive0.699 120.881 70.762 180.821 80.667 150.800 350.522 60.792 170.613 140.607 120.935 500.492 160.205 420.576 290.853 80.691 170.758 230.652 80.872 380.828 150.649 17
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 Network0.683 200.851 120.728 360.800 150.653 180.806 310.468 210.804 130.572 300.602 150.946 280.453 330.239 330.519 430.822 160.689 200.762 210.595 270.895 190.827 160.630 24
PointContrast_LA_SEM0.683 200.757 350.784 130.786 180.639 240.824 170.408 440.775 190.604 200.541 270.934 540.532 80.269 240.552 360.777 220.645 360.793 100.640 100.913 100.824 170.671 12
RFCR0.702 100.889 40.745 270.813 90.672 140.818 210.493 150.815 120.623 120.610 100.947 260.470 230.249 300.594 230.848 120.705 150.779 140.646 90.892 220.823 180.611 28
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
ROSMRF3D0.673 230.789 220.748 260.763 260.635 250.814 250.407 460.747 270.581 270.573 200.950 180.484 170.271 230.607 210.754 250.649 320.774 150.596 250.883 260.823 180.606 32
Feature_GeometricNetpermissive0.690 150.884 50.754 230.795 160.647 200.818 210.422 390.802 150.612 150.604 130.945 310.462 260.189 480.563 330.853 80.726 70.765 180.632 120.904 110.821 200.606 32
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
Feature-Geometry Netpermissive0.690 150.884 50.754 230.795 160.647 200.818 210.422 390.802 150.612 150.604 130.945 310.462 260.189 480.563 330.853 80.726 70.765 180.632 120.904 110.821 200.606 32
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
KP-FCNN0.684 180.847 130.758 210.784 190.647 200.814 250.473 180.772 200.605 190.594 170.935 500.450 340.181 520.587 240.805 200.690 180.785 120.614 180.882 270.819 220.632 23
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
joint point-basedpermissive0.634 380.614 570.778 150.667 480.633 260.825 160.420 410.804 130.467 550.561 220.951 140.494 150.291 150.566 320.458 540.579 520.764 200.559 400.838 480.814 230.598 37
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
FusionNet0.688 170.704 470.741 300.754 280.656 160.829 130.501 100.741 300.609 180.548 250.950 180.522 110.371 10.633 180.756 240.715 120.771 170.623 160.861 430.814 230.658 14
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PointConvpermissive0.666 250.781 240.759 200.699 370.644 230.822 180.475 170.779 180.564 350.504 400.953 110.428 420.203 440.586 260.754 250.661 280.753 240.588 310.902 140.813 250.642 19
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 250.703 480.781 140.751 300.655 170.830 120.471 190.769 210.474 530.537 280.951 140.475 210.279 200.635 160.698 360.675 220.751 250.553 430.816 530.806 260.703 8
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
HPEIN0.618 470.729 420.668 530.647 540.597 320.766 490.414 420.680 450.520 440.525 320.946 280.432 390.215 390.493 510.599 440.638 370.617 590.570 340.897 170.806 260.605 35
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-Net0.658 270.778 250.702 410.806 120.619 280.813 280.468 210.693 430.494 490.524 330.941 410.449 350.298 140.510 450.821 170.675 220.727 310.568 350.826 500.803 280.637 21
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
SConv0.636 360.830 160.697 450.752 290.572 420.780 460.445 320.716 370.529 420.530 300.951 140.446 370.170 540.507 470.666 390.636 380.682 460.541 490.886 250.799 290.594 39
FPConvpermissive0.639 340.785 230.760 190.713 360.603 310.798 380.392 510.534 620.603 210.524 330.948 230.457 290.250 290.538 390.723 300.598 470.696 430.614 180.872 380.799 290.567 47
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
APCF-Net0.631 410.742 380.687 520.672 440.557 460.792 410.408 440.665 490.545 390.508 380.952 130.428 420.186 500.634 170.702 340.620 410.706 380.555 420.873 370.798 310.581 41
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
DenSeR0.628 450.800 210.625 640.719 330.545 480.806 310.445 320.597 560.448 590.519 360.938 460.481 180.328 60.489 520.499 530.657 300.759 220.592 290.881 290.797 320.634 22
MCCNNpermissive0.633 390.866 90.731 330.771 220.576 390.809 290.410 430.684 440.497 480.491 420.949 200.466 250.105 680.581 270.646 410.620 410.680 470.542 480.817 520.795 330.618 27
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
FusionAwareConv0.630 440.604 590.741 300.766 250.590 340.747 540.501 100.734 320.503 470.527 310.919 610.454 310.323 80.550 380.420 590.678 210.688 450.544 460.896 180.795 330.627 25
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
SALANet0.670 240.816 190.770 170.768 240.652 190.807 300.451 260.747 270.659 70.545 260.924 570.473 220.149 630.571 310.811 190.635 390.746 270.623 160.892 220.794 350.570 45
SAFNet-segpermissive0.654 290.752 360.734 320.664 490.583 370.815 240.399 480.754 250.639 90.535 290.942 390.470 230.309 110.665 120.539 470.650 310.708 370.635 110.857 450.793 360.642 19
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
PointMRNet0.640 330.717 460.701 420.692 390.576 390.801 340.467 230.716 370.563 360.459 500.953 110.429 410.169 550.581 270.854 70.605 440.710 350.550 440.894 200.793 360.575 43
Supervoxel-CNN0.635 370.656 520.711 380.719 330.613 290.757 520.444 350.765 220.534 410.566 210.928 550.478 200.272 220.636 150.531 490.664 260.645 540.508 530.864 420.792 380.611 28
RandLA-Netpermissive0.645 300.778 250.731 330.699 370.577 380.829 130.446 300.736 310.477 520.523 350.945 310.454 310.269 240.484 530.749 280.618 430.738 280.599 240.827 490.792 380.621 26
MVPNetpermissive0.641 310.831 150.715 370.671 460.590 340.781 450.394 500.679 460.642 80.553 240.937 470.462 260.256 270.649 130.406 600.626 400.691 440.666 70.877 310.792 380.608 31
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMTL0.632 400.731 410.688 500.675 430.591 330.784 440.444 350.565 600.610 170.492 410.949 200.456 300.254 280.587 240.706 330.599 460.665 510.612 210.868 410.791 410.579 42
PointConv-SFPN0.641 310.776 270.703 400.721 320.557 460.826 150.451 260.672 480.563 360.483 450.943 380.425 450.162 580.644 140.726 290.659 290.709 360.572 330.875 330.786 420.559 50
SIConv0.625 460.830 160.694 460.757 270.563 440.772 480.448 280.647 520.520 440.509 370.949 200.431 400.191 470.496 500.614 430.647 350.672 490.535 510.876 320.783 430.571 44
DVVNet0.562 560.648 530.700 430.770 230.586 360.687 610.333 600.650 500.514 460.475 480.906 650.359 570.223 360.340 630.442 580.422 660.668 500.501 540.708 630.779 440.534 53
ROSMRF0.580 540.772 280.707 390.681 420.563 440.764 500.362 570.515 630.465 560.465 490.936 480.427 440.207 410.438 550.577 450.536 570.675 480.486 570.723 620.779 440.524 55
PointSPNet0.637 350.734 400.692 470.714 350.576 390.797 390.446 300.743 290.598 230.437 540.942 390.403 490.150 620.626 190.800 210.649 320.697 420.557 410.846 470.777 460.563 48
HPGCNN0.656 280.698 490.743 290.650 520.564 430.820 200.505 90.758 230.631 110.479 460.945 310.480 190.226 340.572 300.774 230.690 180.735 300.614 180.853 460.776 470.597 38
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SPH3D-GCNpermissive0.610 480.858 110.772 160.489 670.532 490.792 410.404 470.643 530.570 330.507 390.935 500.414 480.046 730.510 450.702 340.602 450.705 390.549 450.859 440.773 480.534 53
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
SegGCNpermissive0.589 520.833 140.731 330.539 640.514 520.789 430.448 280.467 640.573 290.484 440.936 480.396 510.061 720.501 480.507 520.594 480.700 410.563 370.874 350.771 490.493 59
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
PointNet2-SFPN0.631 410.771 290.692 470.672 440.524 500.837 90.440 370.706 410.538 400.446 520.944 360.421 460.219 370.552 360.751 270.591 490.737 290.543 470.901 160.768 500.557 51
AttAN0.609 490.760 330.667 540.649 530.521 510.793 400.457 250.648 510.528 430.434 560.947 260.401 500.153 610.454 540.721 310.648 340.717 330.536 500.904 110.765 510.485 61
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
CCRFNet0.589 520.766 320.659 570.683 410.470 570.740 560.387 550.620 550.490 500.476 470.922 590.355 590.245 310.511 440.511 500.571 530.643 550.493 560.872 380.762 520.600 36
Pointnet++ & Featurepermissive0.557 570.735 390.661 560.686 400.491 540.744 550.392 510.539 610.451 580.375 620.946 280.376 540.205 420.403 600.356 630.553 560.643 550.497 550.824 510.756 530.515 56
DPC0.592 510.720 440.700 430.602 590.480 550.762 510.380 560.713 390.585 260.437 540.940 430.369 550.288 160.434 570.509 510.590 510.639 570.567 360.772 580.755 540.592 40
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
PCNN0.498 620.559 630.644 620.560 630.420 620.711 590.229 690.414 650.436 610.352 640.941 410.324 610.155 600.238 690.387 620.493 600.529 680.509 520.813 540.751 550.504 58
LAP-D0.594 500.720 440.692 470.637 560.456 580.773 470.391 530.730 330.587 240.445 530.940 430.381 530.288 160.434 570.453 550.591 490.649 520.581 320.777 570.749 560.610 30
3DSM_DMMF0.631 410.626 560.745 270.801 140.607 300.751 530.506 80.729 340.565 340.491 420.866 680.434 380.197 460.595 220.630 420.709 140.705 390.560 380.875 330.740 570.491 60
3DMV, FTSDF0.501 610.558 640.608 670.424 720.478 560.690 600.246 670.586 580.468 540.450 510.911 630.394 520.160 590.438 550.212 690.432 650.541 670.475 590.742 600.727 580.477 62
PointMRNet-lite0.553 580.633 550.648 590.659 500.430 600.800 350.390 540.592 570.454 570.371 630.939 450.368 560.136 650.368 610.448 560.560 550.715 340.486 570.882 270.720 590.462 64
PointCNN with RGBpermissive0.458 640.577 620.611 660.356 740.321 700.715 580.299 630.376 680.328 710.319 650.944 360.285 650.164 570.216 720.229 680.484 620.545 660.456 620.755 590.709 600.475 63
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
Online SegFusion0.515 600.607 580.644 620.579 610.434 590.630 670.353 580.628 540.440 600.410 570.762 720.307 620.167 560.520 420.403 610.516 580.565 620.447 640.678 650.701 610.514 57
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 Netcopyleft0.393 710.472 710.511 710.606 570.311 710.656 630.245 680.405 660.328 710.197 730.927 560.227 720.000 760.001 760.249 670.271 730.510 690.383 710.593 690.699 620.267 72
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-UNetpermissive0.308 740.353 730.290 750.278 750.166 750.553 710.169 730.286 700.147 750.148 750.908 640.182 740.064 710.023 750.018 760.354 700.363 730.345 730.546 720.685 630.278 71
TextureNetpermissive0.566 550.672 510.664 550.671 460.494 530.719 570.445 320.678 470.411 640.396 590.935 500.356 580.225 350.412 590.535 480.565 540.636 580.464 600.794 560.680 640.568 46
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
SurfaceConvPF0.442 660.505 670.622 650.380 730.342 680.654 640.227 700.397 670.367 680.276 690.924 570.240 700.198 450.359 620.262 660.366 680.581 610.435 660.640 670.668 650.398 66
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
FCPNpermissive0.447 650.679 500.604 680.578 620.380 640.682 620.291 640.106 740.483 510.258 720.920 600.258 680.025 740.231 710.325 640.480 630.560 640.463 610.725 610.666 660.231 74
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
Tangent Convolutionspermissive0.438 680.437 720.646 610.474 690.369 650.645 650.353 580.258 710.282 730.279 680.918 620.298 640.147 640.283 660.294 650.487 610.562 630.427 670.619 680.633 670.352 69
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
PNET20.442 660.548 650.548 690.597 600.363 660.628 680.300 620.292 690.374 670.307 660.881 670.268 670.186 500.238 690.204 710.407 670.506 720.449 630.667 660.620 680.462 64
subcloud_weak0.411 700.479 700.650 580.475 680.285 730.519 730.087 740.725 350.396 660.386 600.621 750.250 690.117 660.338 650.443 570.188 740.594 600.369 720.377 740.616 690.306 70
PanopticFusion-label0.529 590.491 680.688 500.604 580.386 630.632 660.225 710.705 420.434 620.293 670.815 690.348 600.241 320.499 490.669 380.507 590.649 520.442 650.796 550.602 700.561 49
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3DWSSS0.425 690.525 660.647 600.522 650.324 690.488 740.077 750.712 400.353 690.401 580.636 740.281 660.176 530.340 630.565 460.175 750.551 650.398 690.370 750.602 700.361 68
3DMV0.484 630.484 690.538 700.643 550.424 610.606 700.310 610.574 590.433 630.378 610.796 700.301 630.214 400.537 400.208 700.472 640.507 710.413 680.693 640.602 700.539 52
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
ScanNet+FTSDF0.383 720.297 740.491 720.432 710.358 670.612 690.274 650.116 730.411 640.265 700.904 660.229 710.079 700.250 670.185 720.320 710.510 690.385 700.548 700.597 730.394 67
PointNet++permissive0.339 730.584 610.478 730.458 700.256 740.360 750.250 660.247 720.278 740.261 710.677 730.183 730.117 660.212 730.145 740.364 690.346 750.232 750.548 700.523 740.252 73
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
ScanNetpermissive0.306 750.203 750.366 740.501 660.311 710.524 720.211 720.002 760.342 700.189 740.786 710.145 750.102 690.245 680.152 730.318 720.348 740.300 740.460 730.437 750.182 75
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 760.000 760.041 760.172 760.030 760.062 760.001 760.035 750.004 760.051 760.143 760.019 760.003 750.041 740.050 750.003 760.054 760.018 760.005 760.264 760.082 76

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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
HAISpermissive0.699 11.000 10.849 20.820 30.675 10.808 70.279 30.757 70.465 60.517 30.596 10.559 30.600 91.000 10.654 60.767 40.676 30.994 150.560 4
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNetpermissive0.698 21.000 10.697 210.888 20.556 60.803 80.387 20.626 110.417 100.556 20.585 30.702 10.600 91.000 10.824 10.720 120.692 11.000 10.509 7
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
OccuSeg+instance0.672 31.000 10.758 160.682 110.576 40.842 10.477 10.504 210.524 30.567 10.585 40.451 70.557 151.000 10.751 20.797 30.563 141.000 10.467 12
Mask-Group0.664 41.000 10.822 50.764 80.616 20.815 40.139 90.694 100.597 20.459 70.566 50.599 20.600 90.516 250.715 30.819 20.635 71.000 10.603 1
CSC-Pretrained0.648 51.000 10.810 60.768 60.523 110.813 50.143 80.819 20.389 110.422 140.511 110.443 80.650 21.000 10.624 80.732 100.634 81.000 10.375 18
PE0.645 61.000 10.773 120.798 50.538 80.786 130.088 160.799 50.350 150.435 130.547 70.545 40.646 70.933 120.562 110.761 70.556 180.997 120.501 9
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN0.643 71.000 10.758 150.582 180.539 70.826 30.046 190.765 60.372 130.436 120.588 20.539 50.650 21.000 10.577 90.750 90.653 60.997 120.495 10
Dyco3Dcopyleft0.641 81.000 10.841 30.893 10.531 90.802 90.115 130.588 160.448 70.438 100.537 90.430 100.550 160.857 140.534 120.764 60.657 40.987 160.568 2
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN0.638 91.000 10.895 10.800 40.480 140.676 160.144 70.737 80.354 140.447 80.400 190.365 150.700 11.000 10.569 100.836 10.599 111.000 10.473 11
PointGroup0.636 101.000 10.765 130.624 120.505 130.797 100.116 120.696 90.384 120.441 90.559 60.476 60.596 121.000 10.666 40.756 80.556 170.997 120.513 6
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+Group0.635 110.667 220.797 100.714 100.562 50.774 140.146 60.810 40.429 90.476 50.546 80.399 120.633 81.000 10.632 70.722 110.609 101.000 10.514 5
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
DENet0.629 121.000 10.797 90.608 130.589 30.627 190.219 40.882 10.310 170.402 180.383 210.396 130.650 21.000 10.663 50.543 250.691 21.000 10.568 3
3D-MPA0.611 131.000 10.833 40.765 70.526 100.756 150.136 110.588 160.470 50.438 110.432 170.358 160.650 20.857 140.429 160.765 50.557 161.000 10.430 15
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
SphereNet0.606 141.000 10.776 110.745 90.436 180.834 20.035 210.587 180.518 40.338 220.534 100.352 170.594 141.000 10.391 200.696 150.624 91.000 10.451 13
PCJC0.578 151.000 10.810 70.583 170.449 170.813 60.042 200.603 140.341 160.490 40.465 130.410 110.650 20.835 190.264 240.694 160.561 150.889 220.504 8
SSEN0.575 161.000 10.761 140.473 200.477 150.795 110.066 170.529 190.658 10.460 60.461 140.380 140.331 240.859 130.401 190.692 170.653 51.000 10.348 20
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
MTML0.549 171.000 10.807 80.588 160.327 210.647 170.004 260.815 30.180 210.418 150.364 220.182 200.445 191.000 10.442 150.688 180.571 131.000 10.396 16
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
Sparse R-CNN0.515 181.000 10.538 270.282 230.468 160.790 120.173 50.345 230.429 80.413 170.484 120.176 210.595 130.591 230.522 130.668 190.476 210.986 170.327 21
Occipital-SCS0.512 191.000 10.716 180.509 190.506 120.611 200.092 150.602 150.177 220.346 200.383 200.165 220.442 200.850 180.386 210.618 210.543 190.889 220.389 17
3D-BoNet0.488 201.000 10.672 220.590 150.301 220.484 280.098 140.620 120.306 180.341 210.259 240.125 240.434 210.796 200.402 180.499 270.513 200.909 210.439 14
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-inst0.478 210.667 220.712 200.595 140.259 240.550 250.000 290.613 130.175 230.250 260.434 150.437 90.411 230.857 140.485 140.591 240.267 290.944 190.359 19
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
SALoss-ResNet0.459 221.000 10.737 170.159 300.259 230.587 220.138 100.475 220.217 200.416 160.408 180.128 230.315 250.714 210.411 170.536 260.590 120.873 250.304 22
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)
MASCpermissive0.447 230.528 280.555 250.381 210.382 190.633 180.002 270.509 200.260 190.361 190.432 160.327 180.451 180.571 240.367 220.639 200.386 220.980 180.276 23
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
3D-SISpermissive0.382 241.000 10.432 290.245 250.190 250.577 230.013 240.263 250.033 290.320 230.240 250.075 260.422 220.857 140.117 270.699 130.271 280.883 240.235 25
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3Dcopyleft0.323 250.667 220.542 260.264 240.157 280.550 240.000 290.205 280.009 300.270 250.218 260.075 260.500 170.688 220.007 320.698 140.301 260.459 300.200 26
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone0.319 260.667 220.715 190.233 260.189 260.479 290.008 250.218 260.067 280.201 270.173 270.107 250.123 290.438 260.150 250.615 220.355 230.916 200.093 31
R-PointNet0.306 270.500 290.405 300.311 220.348 200.589 210.054 180.068 300.126 240.283 240.290 230.028 300.219 270.214 280.331 230.396 300.275 270.821 270.245 24
RandSA0.250 280.333 300.613 230.229 270.163 270.493 260.000 290.304 240.107 250.147 290.100 280.052 290.231 260.119 290.039 290.445 290.325 240.654 280.141 28
Region0.248 290.667 220.437 280.188 280.153 290.491 270.000 290.208 270.094 270.153 280.099 290.057 280.217 280.119 290.039 290.466 280.302 250.640 290.140 29
3D-BEVIS0.248 290.667 220.566 240.076 310.035 320.394 300.027 230.035 310.098 260.099 300.030 310.025 310.098 300.375 270.126 260.604 230.181 300.854 260.171 27
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.143 310.208 320.390 310.169 290.065 300.275 310.029 220.069 290.000 310.087 310.043 300.014 320.027 320.000 310.112 280.351 310.168 310.438 310.138 30
MaskRCNN 2d->3d Proj0.058 320.333 300.002 320.000 320.053 310.002 320.002 280.021 320.000 310.045 320.024 320.238 190.065 310.000 310.014 310.107 320.020 320.110 320.006 32

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted 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
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
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)
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
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
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
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
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
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
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
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
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
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
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
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.
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
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

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




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort 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
sort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
3DASPP-SCE0.691 20.500 10.938 20.824 31.000 11.000 10.500 21.000 10.857 20.500 20.556 30.000 20.812 20.500 1
multi-taskpermissive0.700 10.500 11.000 10.882 20.500 21.000 11.000 10.500 21.000 11.000 10.778 10.000 20.938 10.000 2
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
resnet50_scannet0.353 40.250 30.812 30.529 40.500 20.500 30.000 40.500 20.571 30.000 40.556 30.000 20.375 40.000 2
SE-ResNeXt-SSMA0.498 30.000 40.812 30.941 10.500 20.500 30.500 20.500 20.429 40.500 20.667 20.500 10.625 30.000 2
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv