The 3D semantic labeling task involves predicting a semantic labeling of a 3D scan mesh.

Evaluation and metrics

Our evaluation ranks all methods according to the PASCAL VOC intersection-over-union metric (IoU). IoU = TP/(TP+FP+FN), where TP, FP, and FN are the numbers of true positive, false positive, and false negative pixels, respectively. Predicted labels are evaluated per-vertex over the respective 3D scan mesh; for 3D approaches that operate on other representations like grids or points, the predicted labels should be mapped onto the mesh vertices (e.g., one such example for grid to mesh vertices is provided in the evaluation helpers).



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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mix3Dpermissive0.781 10.964 10.855 10.843 80.781 10.858 60.575 20.831 110.685 40.714 10.979 10.594 30.310 130.801 10.892 40.841 20.819 30.723 20.940 40.887 10.725 8
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 20.758 380.796 120.839 90.746 50.907 10.562 30.850 60.680 50.672 30.978 20.610 10.335 70.777 20.819 220.847 10.830 10.691 60.972 10.885 20.727 6
O-CNNpermissive0.762 30.924 20.823 40.844 70.770 20.852 70.577 10.847 70.711 10.640 100.958 60.592 40.217 450.762 50.888 50.758 50.813 50.726 10.932 100.868 50.744 2
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
BPNetcopyleft0.749 40.909 30.818 70.811 140.752 40.839 110.485 200.842 90.673 60.644 80.957 70.528 150.305 150.773 30.859 90.788 30.818 40.693 50.916 110.856 100.723 9
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
StratifiedFormerpermissive0.747 50.901 40.803 100.845 60.757 30.846 90.512 100.825 120.696 30.645 70.956 80.576 60.262 310.744 100.861 80.742 70.770 230.705 30.899 220.860 80.734 3
Xin Lai*, Jianhui Liu*, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
Virtual MVFusion0.746 60.771 320.819 60.848 40.702 150.865 50.397 580.899 10.699 20.664 40.948 290.588 50.330 80.746 90.851 150.764 40.796 110.704 40.935 70.866 60.728 4
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNetpermissive0.746 60.870 100.838 20.858 20.729 80.850 80.501 130.874 30.587 300.658 50.956 80.564 80.299 160.765 40.900 20.716 160.812 60.631 180.939 50.858 90.709 10
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)
EQ-Net0.743 80.620 670.799 110.849 30.730 70.822 220.493 180.897 20.664 70.681 20.955 110.562 90.378 10.760 60.903 10.738 80.801 90.673 80.907 140.877 30.745 1
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
MinkowskiNetpermissive0.736 90.859 120.818 70.832 100.709 120.840 100.521 90.853 50.660 90.643 90.951 190.544 100.286 220.731 110.893 30.675 280.772 210.683 70.874 420.852 120.727 6
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 100.890 50.837 30.864 10.726 90.873 20.530 70.824 130.489 610.647 60.978 20.609 20.336 60.624 250.733 340.758 50.776 190.570 410.949 20.877 30.728 4
SparseConvNet0.725 110.647 630.821 50.846 50.721 100.869 30.533 60.754 310.603 260.614 130.955 110.572 70.325 100.710 120.870 60.724 130.823 20.628 190.934 80.865 70.683 15
MatchingNet0.724 120.812 220.812 90.810 150.735 60.834 140.495 170.860 40.572 350.602 200.954 130.512 180.280 230.757 70.845 180.725 120.780 170.606 270.937 60.851 130.700 12
INS-Conv-semantic0.717 130.751 410.759 260.812 130.704 140.868 40.537 50.842 90.609 220.608 160.953 150.534 110.293 180.616 260.864 70.719 150.793 130.640 130.933 90.845 170.663 19
contrastBoundarypermissive0.705 140.769 350.775 200.809 160.687 170.820 250.439 430.812 180.661 80.591 230.945 380.515 170.171 630.633 220.856 100.720 140.796 110.668 90.889 300.847 150.689 14
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RFCR0.702 150.889 60.745 350.813 120.672 200.818 280.493 180.815 160.623 160.610 140.947 320.470 290.249 360.594 300.848 160.705 200.779 180.646 120.892 280.823 240.611 35
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
One Thing One Click0.701 160.825 190.796 120.723 370.716 110.832 150.433 450.816 140.634 140.609 150.969 50.418 550.344 40.559 440.833 190.715 170.808 70.560 450.902 190.847 150.680 16
JSENetpermissive0.699 170.881 90.762 240.821 110.667 210.800 420.522 80.792 230.613 180.607 170.935 570.492 220.205 500.576 360.853 120.691 230.758 290.652 110.872 450.828 210.649 24
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
PicassoNet-IIpermissive0.696 180.704 530.790 150.787 230.709 120.837 120.459 300.815 160.543 450.615 120.956 80.529 130.250 340.551 470.790 260.703 210.799 100.619 220.908 130.848 140.700 12
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One-Thing-One-Click0.693 190.743 420.794 140.655 610.684 180.822 220.497 160.719 410.622 170.617 110.977 40.447 430.339 50.750 80.664 490.703 210.790 150.596 300.946 30.855 110.647 25
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
CU-Hybrid Net0.693 190.596 710.789 160.803 180.677 190.800 420.469 240.846 80.554 430.591 230.948 290.500 200.316 120.609 270.847 170.732 90.808 70.593 330.894 260.839 180.652 22
Feature_GeometricNetpermissive0.690 210.884 70.754 300.795 210.647 260.818 280.422 470.802 210.612 190.604 180.945 380.462 320.189 570.563 420.853 120.726 100.765 240.632 160.904 160.821 260.606 39
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
Feature-Geometry Netpermissive0.690 210.884 70.754 300.795 210.647 260.818 280.422 470.802 210.612 190.604 180.945 380.462 320.189 570.563 420.853 120.726 100.765 240.632 160.904 160.821 260.606 39
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 230.704 530.741 390.754 340.656 220.829 170.501 130.741 360.609 220.548 310.950 230.522 160.371 20.633 220.756 290.715 170.771 220.623 200.861 510.814 290.658 20
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
KP-FCNN0.684 240.847 150.758 280.784 250.647 260.814 320.473 220.772 260.605 240.594 220.935 570.450 410.181 610.587 310.805 240.690 240.785 160.614 230.882 340.819 280.632 30
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 240.728 480.757 290.776 270.690 160.804 400.464 280.816 140.577 340.587 250.945 380.508 190.276 250.671 130.710 390.663 330.750 320.589 350.881 360.832 200.653 21
Superpoint Network0.683 260.851 140.728 440.800 200.653 240.806 380.468 250.804 190.572 350.602 200.946 350.453 390.239 390.519 530.822 200.689 260.762 270.595 320.895 250.827 220.630 31
PointContrast_LA_SEM0.683 260.757 390.784 170.786 240.639 300.824 210.408 520.775 250.604 250.541 330.934 610.532 120.269 280.552 450.777 270.645 440.793 130.640 130.913 120.824 230.671 17
VI-PointConv0.676 280.770 340.754 300.783 260.621 340.814 320.552 40.758 290.571 370.557 290.954 130.529 130.268 300.530 510.682 440.675 280.719 400.603 280.888 310.833 190.665 18
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 290.789 250.748 330.763 320.635 320.814 320.407 540.747 330.581 330.573 260.950 230.484 230.271 270.607 280.754 300.649 390.774 200.596 300.883 330.823 240.606 39
SALANet0.670 300.816 210.770 220.768 300.652 250.807 370.451 320.747 330.659 100.545 320.924 670.473 280.149 730.571 380.811 230.635 470.746 330.623 200.892 280.794 420.570 52
PointConvpermissive0.666 310.781 270.759 260.699 440.644 290.822 220.475 210.779 240.564 400.504 490.953 150.428 490.203 520.586 330.754 300.661 350.753 300.588 360.902 190.813 310.642 26
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 310.703 550.781 180.751 360.655 230.830 160.471 230.769 270.474 640.537 340.951 190.475 270.279 240.635 200.698 430.675 280.751 310.553 500.816 620.806 330.703 11
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
DCM-Net0.658 330.778 280.702 490.806 170.619 350.813 350.468 250.693 480.494 570.524 410.941 490.449 420.298 170.510 550.821 210.675 280.727 390.568 430.826 590.803 350.637 28
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 340.698 560.743 370.650 620.564 530.820 250.505 120.758 290.631 150.479 540.945 380.480 250.226 400.572 370.774 280.690 240.735 360.614 230.853 540.776 560.597 45
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 350.752 400.734 410.664 580.583 470.815 310.399 570.754 310.639 120.535 360.942 470.470 290.309 140.665 140.539 570.650 380.708 460.635 150.857 530.793 440.642 26
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 360.778 280.731 420.699 440.577 480.829 170.446 350.736 370.477 630.523 430.945 380.454 370.269 280.484 620.749 330.618 510.738 340.599 290.827 580.792 470.621 33
PointConv-SFPN0.641 370.776 300.703 480.721 380.557 560.826 190.451 320.672 530.563 410.483 530.943 460.425 520.162 680.644 180.726 350.659 360.709 450.572 400.875 400.786 510.559 57
MVPNetpermissive0.641 370.831 160.715 450.671 550.590 430.781 520.394 590.679 510.642 110.553 300.937 550.462 320.256 320.649 170.406 710.626 480.691 530.666 100.877 380.792 470.608 38
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 390.717 520.701 500.692 470.576 490.801 410.467 270.716 420.563 410.459 580.953 150.429 480.169 650.581 340.854 110.605 530.710 430.550 510.894 260.793 440.575 50
FPConvpermissive0.639 400.785 260.760 250.713 420.603 380.798 450.392 600.534 730.603 260.524 410.948 290.457 350.250 340.538 490.723 370.598 570.696 510.614 230.872 450.799 360.567 54
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 410.797 240.769 230.641 670.590 430.820 250.461 290.537 720.637 130.536 350.947 320.388 620.206 490.656 150.668 470.647 420.732 380.585 370.868 480.793 440.473 74
PointSPNet0.637 420.734 450.692 580.714 410.576 490.797 460.446 350.743 350.598 280.437 630.942 470.403 580.150 720.626 240.800 250.649 390.697 500.557 480.846 550.777 550.563 55
SConv0.636 430.830 170.697 530.752 350.572 520.780 540.445 370.716 420.529 480.530 380.951 190.446 440.170 640.507 570.666 480.636 460.682 550.541 570.886 320.799 360.594 46
PPCNN++permissive0.636 430.724 490.697 530.672 520.636 310.775 560.403 560.582 670.588 290.533 370.949 250.453 390.218 440.571 380.676 450.663 330.635 700.580 390.906 150.808 320.650 23
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
Supervoxel-CNN0.635 450.656 610.711 460.719 390.613 360.757 640.444 400.765 280.534 470.566 270.928 650.478 260.272 260.636 190.531 590.664 320.645 650.508 640.864 500.792 470.611 35
joint point-basedpermissive0.634 460.614 680.778 190.667 570.633 330.825 200.420 490.804 190.467 660.561 280.951 190.494 210.291 190.566 400.458 650.579 620.764 260.559 470.838 560.814 290.598 44
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
MCCNNpermissive0.633 470.866 110.731 420.771 280.576 490.809 360.410 510.684 490.497 560.491 510.949 250.466 310.105 770.581 340.646 510.620 490.680 560.542 560.817 610.795 400.618 34
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
PointMTL0.632 480.731 460.688 610.675 510.591 420.784 510.444 400.565 690.610 210.492 500.949 250.456 360.254 330.587 310.706 400.599 560.665 610.612 260.868 480.791 500.579 49
3DSM_DMMF0.631 490.626 660.745 350.801 190.607 370.751 650.506 110.729 400.565 390.491 510.866 800.434 450.197 550.595 290.630 520.709 190.705 480.560 450.875 400.740 660.491 69
APCF-Net0.631 490.742 430.687 630.672 520.557 560.792 490.408 520.665 540.545 440.508 460.952 180.428 490.186 590.634 210.702 410.620 490.706 470.555 490.873 430.798 380.581 48
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN0.631 490.771 320.692 580.672 520.524 600.837 120.440 420.706 460.538 460.446 600.944 440.421 540.219 430.552 450.751 320.591 590.737 350.543 550.901 210.768 580.557 58
FusionAwareConv0.630 520.604 700.741 390.766 310.590 430.747 660.501 130.734 380.503 550.527 390.919 710.454 370.323 110.550 480.420 700.678 270.688 540.544 530.896 240.795 400.627 32
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 530.800 230.625 740.719 390.545 580.806 380.445 370.597 620.448 700.519 440.938 540.481 240.328 90.489 610.499 640.657 370.759 280.592 340.881 360.797 390.634 29
SegGroup_sempermissive0.627 540.818 200.747 340.701 430.602 390.764 610.385 650.629 590.490 590.508 460.931 640.409 570.201 530.564 410.725 360.618 510.692 520.539 580.873 430.794 420.548 61
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation.
SIConv0.625 550.830 170.694 560.757 330.563 540.772 590.448 340.647 570.520 500.509 450.949 250.431 470.191 560.496 590.614 530.647 420.672 590.535 600.876 390.783 520.571 51
HPEIN0.618 560.729 470.668 640.647 640.597 410.766 600.414 500.680 500.520 500.525 400.946 350.432 460.215 460.493 600.599 540.638 450.617 710.570 410.897 230.806 330.605 42
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia: Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. ICCV 2019
SPH3D-GCNpermissive0.610 570.858 130.772 210.489 790.532 590.792 490.404 550.643 580.570 380.507 480.935 570.414 560.046 830.510 550.702 410.602 550.705 480.549 520.859 520.773 570.534 63
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 580.760 370.667 650.649 630.521 610.793 470.457 310.648 560.528 490.434 650.947 320.401 590.153 710.454 640.721 380.648 410.717 410.536 590.904 160.765 590.485 70
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 590.634 640.743 370.697 460.601 400.781 520.437 440.585 660.493 580.446 600.933 620.394 600.011 850.654 160.661 500.603 540.733 370.526 610.832 570.761 610.480 71
LAP-D0.594 600.720 500.692 580.637 680.456 690.773 580.391 620.730 390.587 300.445 620.940 510.381 630.288 200.434 670.453 670.591 590.649 630.581 380.777 660.749 650.610 37
DPC0.592 610.720 500.700 510.602 720.480 650.762 630.380 660.713 440.585 320.437 630.940 510.369 650.288 200.434 670.509 630.590 610.639 680.567 440.772 670.755 630.592 47
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 620.766 360.659 680.683 490.470 680.740 680.387 640.620 610.490 590.476 550.922 690.355 690.245 370.511 540.511 620.571 630.643 660.493 680.872 450.762 600.600 43
ROSMRF0.580 630.772 310.707 470.681 500.563 540.764 610.362 670.515 740.465 670.465 570.936 560.427 510.207 480.438 650.577 550.536 670.675 580.486 690.723 720.779 530.524 65
SQN_0.1%0.569 640.676 580.696 550.657 600.497 620.779 550.424 460.548 700.515 520.376 700.902 780.422 530.357 30.379 710.456 660.596 580.659 620.544 530.685 750.665 780.556 59
TextureNetpermissive0.566 650.672 600.664 660.671 550.494 630.719 690.445 370.678 520.411 760.396 680.935 570.356 680.225 410.412 690.535 580.565 640.636 690.464 720.794 650.680 750.568 53
Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkerhouser, Matthias Niessner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. CVPR
DVVNet0.562 660.648 620.700 510.770 290.586 460.687 730.333 710.650 550.514 530.475 560.906 750.359 670.223 420.340 740.442 690.422 780.668 600.501 650.708 730.779 530.534 63
Pointnet++ & Featurepermissive0.557 670.735 440.661 670.686 480.491 640.744 670.392 600.539 710.451 690.375 710.946 350.376 640.205 500.403 700.356 740.553 660.643 660.497 660.824 600.756 620.515 66
PointMRNet-lite0.553 680.633 650.648 690.659 590.430 720.800 420.390 630.592 640.454 680.371 720.939 530.368 660.136 750.368 720.448 680.560 650.715 420.486 690.882 340.720 700.462 75
GMLPs0.538 690.495 790.693 570.647 640.471 670.793 470.300 730.477 750.505 540.358 730.903 770.327 720.081 800.472 630.529 600.448 760.710 430.509 620.746 690.737 670.554 60
PanopticFusion-label0.529 700.491 800.688 610.604 710.386 750.632 780.225 830.705 470.434 730.293 780.815 810.348 700.241 380.499 580.669 460.507 690.649 630.442 770.796 640.602 810.561 56
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
subcloud_weak0.516 710.676 580.591 790.609 690.442 700.774 570.335 700.597 620.422 750.357 740.932 630.341 710.094 790.298 760.528 610.473 740.676 570.495 670.602 800.721 690.349 81
Online SegFusion0.515 720.607 690.644 720.579 740.434 710.630 790.353 680.628 600.440 710.410 660.762 840.307 740.167 660.520 520.403 720.516 680.565 730.447 760.678 760.701 720.514 67
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
3DMV, FTSDF0.501 730.558 750.608 770.424 830.478 660.690 720.246 790.586 650.468 650.450 590.911 730.394 600.160 690.438 650.212 800.432 770.541 780.475 710.742 700.727 680.477 72
PCNN0.498 740.559 740.644 720.560 760.420 740.711 710.229 810.414 760.436 720.352 750.941 490.324 730.155 700.238 800.387 730.493 700.529 790.509 620.813 630.751 640.504 68
3DMV0.484 750.484 810.538 810.643 660.424 730.606 820.310 720.574 680.433 740.378 690.796 820.301 750.214 470.537 500.208 810.472 750.507 820.413 800.693 740.602 810.539 62
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 760.577 730.611 760.356 850.321 820.715 700.299 750.376 790.328 820.319 760.944 440.285 770.164 670.216 830.229 790.484 720.545 770.456 740.755 680.709 710.475 73
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 770.679 570.604 780.578 750.380 760.682 740.291 760.106 850.483 620.258 830.920 700.258 800.025 840.231 820.325 750.480 730.560 750.463 730.725 710.666 770.231 85
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
SurfaceConvPF0.442 780.505 780.622 750.380 840.342 800.654 760.227 820.397 780.367 790.276 800.924 670.240 810.198 540.359 730.262 770.366 800.581 720.435 780.640 780.668 760.398 77
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET20.442 780.548 760.548 800.597 730.363 780.628 800.300 730.292 800.374 780.307 770.881 790.268 790.186 590.238 800.204 820.407 790.506 830.449 750.667 770.620 800.462 75
Tangent Convolutionspermissive0.438 800.437 830.646 710.474 800.369 770.645 770.353 680.258 820.282 840.279 790.918 720.298 760.147 740.283 770.294 760.487 710.562 740.427 790.619 790.633 790.352 80
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 810.525 770.647 700.522 770.324 810.488 850.077 860.712 450.353 800.401 670.636 860.281 780.176 620.340 740.565 560.175 860.551 760.398 810.370 860.602 810.361 79
SPLAT Netcopyleft0.393 820.472 820.511 820.606 700.311 830.656 750.245 800.405 770.328 820.197 840.927 660.227 830.000 870.001 870.249 780.271 850.510 800.383 830.593 810.699 730.267 83
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
ScanNet+FTSDF0.383 830.297 850.491 830.432 820.358 790.612 810.274 770.116 840.411 760.265 810.904 760.229 820.079 810.250 780.185 830.320 830.510 800.385 820.548 820.597 840.394 78
PointNet++permissive0.339 840.584 720.478 840.458 810.256 850.360 860.250 780.247 830.278 850.261 820.677 850.183 840.117 760.212 840.145 850.364 810.346 860.232 860.548 820.523 850.252 84
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 850.353 840.290 860.278 860.166 860.553 830.169 850.286 810.147 860.148 860.908 740.182 850.064 820.023 860.018 870.354 820.363 840.345 840.546 840.685 740.278 82
ScanNetpermissive0.306 860.203 860.366 850.501 780.311 830.524 840.211 840.002 870.342 810.189 850.786 830.145 860.102 780.245 790.152 840.318 840.348 850.300 850.460 850.437 860.182 86
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 870.000 870.041 870.172 870.030 870.062 870.001 870.035 860.004 870.051 870.143 870.019 870.003 860.041 850.050 860.003 870.054 870.018 870.005 870.264 870.082 87