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
sort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mix3Dpermissive0.781 10.964 10.855 10.843 100.781 10.858 70.575 30.831 180.685 70.714 10.979 10.594 30.310 160.801 10.892 80.841 20.819 30.723 30.940 70.887 10.725 12
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
O-CNNpermissive0.762 40.924 20.823 40.844 90.770 20.852 100.577 20.847 140.711 10.640 140.958 90.592 40.217 560.762 100.888 90.758 90.813 60.726 10.932 130.868 80.744 4
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
SAT0.742 150.860 130.765 330.819 160.769 30.848 120.533 110.829 190.663 130.631 160.955 170.586 80.274 320.753 140.896 60.729 150.760 350.666 150.921 160.855 190.733 7
PointTransformer++0.725 190.727 580.811 110.819 160.765 40.841 150.502 210.814 260.621 240.623 180.955 170.556 150.284 280.620 360.866 140.781 50.757 380.648 180.932 130.862 120.709 18
PointTransformerV20.752 50.742 510.809 120.872 10.758 50.860 60.552 70.891 50.610 280.687 20.960 70.559 140.304 190.766 80.926 20.767 60.797 130.644 200.942 50.876 70.722 14
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
CU-Hybrid Net0.764 20.924 20.819 60.840 110.757 60.853 90.580 10.848 130.709 20.643 110.958 90.587 70.295 220.753 140.884 120.758 90.815 50.725 20.927 150.867 90.743 5
StratifiedFormerpermissive0.747 100.901 60.803 150.845 80.757 60.846 130.512 180.825 200.696 50.645 90.956 130.576 90.262 420.744 180.861 160.742 130.770 300.705 50.899 300.860 140.734 6
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
LRPNet0.742 150.816 250.806 130.807 240.752 80.828 270.575 30.839 170.699 30.637 150.954 210.520 250.320 130.755 130.834 270.760 80.772 270.676 100.915 200.862 120.717 15
BPNetcopyleft0.749 70.909 40.818 80.811 210.752 80.839 170.485 300.842 150.673 100.644 100.957 120.528 230.305 180.773 60.859 170.788 40.818 40.693 70.916 190.856 170.723 13
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer0.749 70.793 300.790 220.807 240.750 100.856 80.524 150.881 60.588 380.642 130.977 40.591 50.274 320.781 20.929 10.804 30.796 140.642 210.947 30.885 20.715 17
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
OccuSeg+Semantic0.764 20.758 440.796 180.839 120.746 110.907 10.562 50.850 120.680 90.672 50.978 20.610 10.335 80.777 40.819 310.847 10.830 10.691 80.972 10.885 20.727 10
MSP0.748 90.623 750.804 140.859 30.745 120.824 310.501 220.912 20.690 60.685 30.956 130.567 110.320 130.768 70.918 30.720 200.802 90.676 100.921 160.881 40.779 1
Retro-FPN0.744 130.842 180.800 160.767 390.740 130.836 210.541 90.914 10.672 110.626 170.958 90.552 170.272 340.777 40.886 110.696 300.801 100.674 120.941 60.858 150.717 15
MatchingNet0.724 210.812 270.812 100.810 220.735 140.834 220.495 270.860 100.572 450.602 280.954 210.512 270.280 290.757 120.845 250.725 170.780 230.606 370.937 90.851 220.700 21
EQ-Net0.743 140.620 760.799 170.849 50.730 150.822 330.493 280.897 40.664 120.681 40.955 170.562 130.378 10.760 110.903 40.738 140.801 100.673 130.907 230.877 50.745 3
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
VMNetpermissive0.746 110.870 110.838 20.858 40.729 160.850 110.501 220.874 70.587 390.658 70.956 130.564 120.299 200.765 90.900 50.716 230.812 70.631 260.939 80.858 150.709 18
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)
IPCA0.731 180.890 70.837 30.864 20.726 170.873 20.530 140.824 210.489 690.647 80.978 20.609 20.336 70.624 350.733 440.758 90.776 250.570 510.949 20.877 50.728 8
SimConv0.410 910.000 960.782 260.772 360.722 180.838 180.407 630.000 970.000 970.595 320.947 400.000 970.270 370.000 970.000 970.000 970.786 210.621 310.000 970.841 280.621 42
SparseConvNet0.725 190.647 720.821 50.846 70.721 190.869 30.533 110.754 400.603 340.614 210.955 170.572 100.325 110.710 200.870 130.724 180.823 20.628 270.934 110.865 110.683 24
One Thing One Click0.701 260.825 230.796 180.723 460.716 200.832 230.433 560.816 220.634 200.609 230.969 60.418 640.344 50.559 510.833 280.715 240.808 80.560 550.902 270.847 240.680 25
MinkowskiNetpermissive0.736 170.859 140.818 80.832 130.709 210.840 160.521 170.853 110.660 150.643 110.951 290.544 180.286 270.731 190.893 70.675 370.772 270.683 90.874 480.852 210.727 10
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
PicassoNet-IIpermissive0.696 280.704 620.790 220.787 310.709 210.837 190.459 390.815 240.543 540.615 200.956 130.529 210.250 450.551 560.790 360.703 280.799 120.619 320.908 220.848 230.700 21
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
INS-Conv-semantic0.717 220.751 470.759 360.812 200.704 230.868 40.537 100.842 150.609 300.608 240.953 240.534 190.293 230.616 370.864 150.719 220.793 180.640 220.933 120.845 260.663 29
Virtual MVFusion0.746 110.771 380.819 60.848 60.702 240.865 50.397 670.899 30.699 30.664 60.948 380.588 60.330 90.746 170.851 230.764 70.796 140.704 60.935 100.866 100.728 8
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++0.684 330.728 570.757 390.776 350.690 250.804 500.464 370.816 220.577 440.587 350.945 470.508 290.276 310.671 220.710 490.663 420.750 410.589 460.881 420.832 300.653 32
DMF-Net0.752 50.906 50.793 210.802 270.689 260.825 290.556 60.867 80.681 80.602 280.960 70.555 160.365 30.779 30.859 170.747 120.795 170.717 40.917 180.856 170.764 2
contrastBoundarypermissive0.705 240.769 410.775 290.809 230.687 270.820 360.439 540.812 270.661 140.591 340.945 470.515 260.171 740.633 320.856 190.720 200.796 140.668 140.889 370.847 240.689 23
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
PointMetaBase0.714 230.835 190.785 240.821 140.684 280.846 130.531 130.865 90.614 250.596 310.953 240.500 300.246 480.674 210.888 90.692 310.764 320.624 280.849 620.844 270.675 26
One-Thing-One-Click0.693 290.743 500.794 200.655 690.684 280.822 330.497 260.719 500.622 230.617 190.977 40.447 510.339 60.750 160.664 590.703 280.790 200.596 410.946 40.855 190.647 34
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
RFCR0.702 250.889 80.745 450.813 190.672 300.818 400.493 280.815 240.623 220.610 220.947 400.470 390.249 470.594 400.848 240.705 270.779 240.646 190.892 350.823 340.611 44
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
JSENetpermissive0.699 270.881 100.762 340.821 140.667 310.800 520.522 160.792 320.613 260.607 250.935 660.492 320.205 610.576 450.853 210.691 320.758 370.652 170.872 510.828 310.649 33
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
FusionNet0.688 310.704 620.741 490.754 430.656 320.829 250.501 220.741 450.609 300.548 410.950 330.522 240.371 20.633 320.756 390.715 240.771 290.623 290.861 580.814 390.658 30
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PointASNLpermissive0.666 400.703 640.781 270.751 450.655 330.830 240.471 330.769 360.474 720.537 450.951 290.475 370.279 300.635 300.698 530.675 370.751 400.553 600.816 690.806 430.703 20
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 Network0.683 350.851 160.728 530.800 290.653 340.806 480.468 340.804 280.572 450.602 280.946 440.453 480.239 510.519 620.822 290.689 350.762 340.595 430.895 330.827 320.630 40
SALANet0.670 390.816 250.770 310.768 380.652 350.807 470.451 410.747 420.659 160.545 420.924 760.473 380.149 840.571 470.811 330.635 550.746 420.623 290.892 350.794 510.570 61
KP-FCNN0.684 330.847 170.758 380.784 330.647 360.814 430.473 320.772 350.605 320.594 330.935 660.450 490.181 720.587 410.805 340.690 330.785 220.614 330.882 410.819 380.632 39
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
Feature_GeometricNetpermissive0.690 300.884 90.754 400.795 300.647 360.818 400.422 580.802 300.612 270.604 260.945 470.462 420.189 690.563 500.853 210.726 160.765 310.632 250.904 250.821 370.606 48
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
Feature-Geometry Netpermissive0.685 320.866 120.748 420.819 160.645 380.794 550.450 440.802 300.587 390.604 260.945 470.464 410.201 640.554 530.840 260.723 190.732 470.602 390.907 230.822 360.603 51
PointConvpermissive0.666 400.781 330.759 360.699 540.644 390.822 330.475 310.779 330.564 500.504 590.953 240.428 580.203 630.586 430.754 400.661 430.753 390.588 470.902 270.813 410.642 35
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointContrast_LA_SEM0.683 350.757 450.784 250.786 320.639 400.824 310.408 610.775 340.604 330.541 430.934 700.532 200.269 380.552 540.777 370.645 520.793 180.640 220.913 210.824 330.671 27
PPCNN++permissive0.663 420.746 480.708 560.722 470.638 410.820 360.451 410.566 760.599 360.541 430.950 330.510 280.313 150.648 270.819 310.616 600.682 650.590 450.869 540.810 420.656 31
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
ROSMRF3D0.673 380.789 310.748 420.763 410.635 420.814 430.407 630.747 420.581 430.573 360.950 330.484 330.271 360.607 380.754 400.649 470.774 260.596 410.883 400.823 340.606 48
joint point-basedpermissive0.634 550.614 770.778 280.667 660.633 430.825 290.420 590.804 280.467 740.561 380.951 290.494 310.291 240.566 480.458 740.579 710.764 320.559 570.838 640.814 390.598 53
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
VI-PointConv0.676 370.770 400.754 400.783 340.621 440.814 430.552 70.758 380.571 470.557 390.954 210.529 210.268 400.530 600.682 540.675 370.719 500.603 380.888 380.833 290.665 28
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
DCM-Net0.658 430.778 340.702 590.806 260.619 450.813 460.468 340.693 580.494 650.524 510.941 580.449 500.298 210.510 640.821 300.675 370.727 490.568 530.826 670.803 450.637 37
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
Supervoxel-CNN0.635 540.656 700.711 550.719 490.613 460.757 720.444 510.765 370.534 560.566 370.928 740.478 360.272 340.636 290.531 680.664 410.645 750.508 730.864 570.792 560.611 44
3DSM_DMMF0.631 570.626 740.745 450.801 280.607 470.751 730.506 190.729 490.565 490.491 610.866 900.434 530.197 670.595 390.630 610.709 260.705 570.560 550.875 460.740 750.491 79
FPConvpermissive0.639 500.785 320.760 350.713 520.603 480.798 530.392 690.534 810.603 340.524 510.948 380.457 440.250 450.538 580.723 470.598 650.696 600.614 330.872 510.799 460.567 63
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
SegGroup_sempermissive0.627 620.818 240.747 440.701 530.602 490.764 690.385 730.629 680.490 670.508 560.931 730.409 660.201 640.564 490.725 460.618 580.692 610.539 670.873 490.794 510.548 70
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
wsss-transformer0.600 670.634 730.743 470.697 560.601 500.781 610.437 550.585 740.493 660.446 700.933 710.394 690.011 950.654 250.661 600.603 620.733 460.526 700.832 650.761 700.480 81
HPEIN0.618 640.729 560.668 730.647 720.597 510.766 680.414 600.680 590.520 590.525 500.946 440.432 540.215 570.493 690.599 630.638 530.617 800.570 510.897 310.806 430.605 50
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
PointMTL0.632 560.731 550.688 700.675 610.591 520.784 600.444 510.565 770.610 280.492 600.949 360.456 450.254 440.587 410.706 500.599 640.665 710.612 360.868 550.791 590.579 58
FusionAwareConv0.630 600.604 790.741 490.766 400.590 530.747 740.501 220.734 470.503 640.527 490.919 800.454 460.323 120.550 570.420 780.678 360.688 630.544 630.896 320.795 500.627 41
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
PD-Net0.638 510.797 290.769 320.641 750.590 530.820 360.461 380.537 800.637 190.536 460.947 400.388 710.206 600.656 240.668 570.647 500.732 470.585 480.868 550.793 530.473 84
MVPNetpermissive0.641 470.831 200.715 540.671 640.590 530.781 610.394 680.679 600.642 170.553 400.937 630.462 420.256 430.649 260.406 790.626 560.691 620.666 150.877 440.792 560.608 47
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
DVVNet0.562 750.648 710.700 610.770 370.586 560.687 810.333 800.650 640.514 620.475 650.906 840.359 750.223 540.340 820.442 770.422 860.668 700.501 740.708 810.779 620.534 73
SAFNet-segpermissive0.654 450.752 460.734 510.664 670.583 570.815 420.399 660.754 400.639 180.535 470.942 560.470 390.309 170.665 230.539 660.650 460.708 550.635 240.857 600.793 530.642 35
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 460.778 340.731 520.699 540.577 580.829 250.446 460.736 460.477 710.523 530.945 470.454 460.269 380.484 710.749 430.618 580.738 430.599 400.827 660.792 560.621 42
PointSPNet0.637 520.734 540.692 670.714 510.576 590.797 540.446 460.743 440.598 370.437 730.942 560.403 670.150 830.626 340.800 350.649 470.697 590.557 580.846 630.777 640.563 64
PointMRNet0.640 490.717 610.701 600.692 570.576 590.801 510.467 360.716 510.563 510.459 680.953 240.429 570.169 760.581 440.854 200.605 610.710 520.550 610.894 340.793 530.575 59
SConv0.636 530.830 210.697 630.752 440.572 610.780 630.445 480.716 510.529 570.530 480.951 290.446 520.170 750.507 660.666 580.636 540.682 650.541 660.886 390.799 460.594 55
HPGCNN0.656 440.698 650.743 470.650 700.564 620.820 360.505 200.758 380.631 210.479 630.945 470.480 350.226 520.572 460.774 380.690 330.735 450.614 330.853 610.776 650.597 54
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SIConv0.625 630.830 210.694 650.757 420.563 630.772 670.448 450.647 660.520 590.509 550.949 360.431 560.191 680.496 680.614 620.647 500.672 690.535 690.876 450.783 610.571 60
ROSMRF0.580 710.772 370.707 570.681 600.563 630.764 690.362 760.515 820.465 750.465 670.936 650.427 600.207 590.438 740.577 640.536 750.675 680.486 780.723 800.779 620.524 75
PointConv-SFPN0.641 470.776 360.703 580.721 480.557 650.826 280.451 410.672 620.563 510.483 620.943 550.425 610.162 790.644 280.726 450.659 440.709 540.572 500.875 460.786 600.559 66
APCF-Net0.631 570.742 510.687 720.672 620.557 650.792 580.408 610.665 630.545 530.508 560.952 280.428 580.186 700.634 310.702 510.620 570.706 560.555 590.873 490.798 480.581 57
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
DenSeR0.628 610.800 280.625 820.719 490.545 670.806 480.445 480.597 710.448 780.519 540.938 620.481 340.328 100.489 700.499 730.657 450.759 360.592 440.881 420.797 490.634 38
SPH3D-GCNpermissive0.610 650.858 150.772 300.489 870.532 680.792 580.404 650.643 670.570 480.507 580.935 660.414 650.046 930.510 640.702 510.602 630.705 570.549 620.859 590.773 660.534 73
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
PointNet2-SFPN0.631 570.771 380.692 670.672 620.524 690.837 190.440 530.706 560.538 550.446 700.944 530.421 630.219 550.552 540.751 420.591 670.737 440.543 650.901 290.768 670.557 67
AttAN0.609 660.760 430.667 740.649 710.521 700.793 560.457 400.648 650.528 580.434 750.947 400.401 680.153 820.454 730.721 480.648 490.717 510.536 680.904 250.765 680.485 80
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
SD-DETR0.576 720.746 480.609 860.445 910.517 710.643 870.366 750.714 530.456 760.468 660.870 890.432 540.264 410.558 520.674 550.586 700.688 630.482 790.739 780.733 770.537 72
SQN_0.1%0.569 730.676 670.696 640.657 680.497 720.779 640.424 570.548 780.515 610.376 800.902 870.422 620.357 40.379 800.456 750.596 660.659 720.544 630.685 830.665 880.556 68
TextureNetpermissive0.566 740.672 690.664 750.671 640.494 730.719 770.445 480.678 610.411 840.396 780.935 660.356 760.225 530.412 780.535 670.565 730.636 790.464 810.794 720.680 850.568 62
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++ & Featurepermissive0.557 760.735 530.661 760.686 580.491 740.744 750.392 690.539 790.451 770.375 810.946 440.376 730.205 610.403 790.356 820.553 740.643 760.497 750.824 680.756 710.515 76
DPC0.592 690.720 590.700 610.602 800.480 750.762 710.380 740.713 540.585 420.437 730.940 600.369 740.288 250.434 760.509 720.590 690.639 780.567 540.772 740.755 720.592 56
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
3DMV, FTSDF0.501 810.558 830.608 870.424 930.478 760.690 800.246 890.586 730.468 730.450 690.911 820.394 690.160 800.438 740.212 890.432 850.541 880.475 800.742 770.727 780.477 82
GMLPs0.538 770.495 870.693 660.647 720.471 770.793 560.300 830.477 830.505 630.358 820.903 860.327 800.081 900.472 720.529 690.448 840.710 520.509 710.746 760.737 760.554 69
CCRFNet0.589 700.766 420.659 770.683 590.470 780.740 760.387 720.620 700.490 670.476 640.922 780.355 770.245 490.511 630.511 710.571 720.643 760.493 770.872 510.762 690.600 52
LAP-D0.594 680.720 590.692 670.637 760.456 790.773 660.391 710.730 480.587 390.445 720.940 600.381 720.288 250.434 760.453 760.591 670.649 730.581 490.777 730.749 740.610 46
subcloud_weak0.516 790.676 670.591 890.609 770.442 800.774 650.335 790.597 710.422 830.357 830.932 720.341 790.094 890.298 840.528 700.473 820.676 670.495 760.602 890.721 800.349 91
Online SegFusion0.515 800.607 780.644 800.579 820.434 810.630 890.353 770.628 690.440 790.410 760.762 940.307 820.167 770.520 610.403 800.516 760.565 830.447 850.678 840.701 820.514 77
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
3DMV0.484 830.484 890.538 910.643 740.424 820.606 920.310 810.574 750.433 820.378 790.796 920.301 830.214 580.537 590.208 900.472 830.507 920.413 900.693 820.602 910.539 71
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PCNN0.498 820.559 820.644 800.560 840.420 830.711 790.229 910.414 840.436 800.352 840.941 580.324 810.155 810.238 890.387 810.493 780.529 890.509 710.813 700.751 730.504 78
PanopticFusion-label0.529 780.491 880.688 700.604 790.386 840.632 880.225 930.705 570.434 810.293 880.815 910.348 780.241 500.499 670.669 560.507 770.649 730.442 870.796 710.602 910.561 65
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
FCPNpermissive0.447 850.679 660.604 880.578 830.380 850.682 820.291 860.106 940.483 700.258 930.920 790.258 890.025 940.231 910.325 830.480 810.560 850.463 820.725 790.666 870.231 95
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
Tangent Convolutionspermissive0.438 890.437 920.646 790.474 880.369 860.645 860.353 770.258 910.282 930.279 890.918 810.298 840.147 850.283 860.294 840.487 790.562 840.427 890.619 880.633 890.352 90
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
DGCNN_reproducecopyleft0.446 860.474 900.623 830.463 890.366 870.651 850.310 810.389 870.349 890.330 850.937 630.271 870.126 860.285 850.224 880.350 910.577 820.445 860.625 870.723 790.394 87
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
PNET20.442 870.548 840.548 900.597 810.363 880.628 900.300 830.292 890.374 860.307 870.881 880.268 880.186 700.238 890.204 910.407 870.506 930.449 840.667 850.620 900.462 85
ScanNet+FTSDF0.383 930.297 940.491 930.432 920.358 890.612 910.274 870.116 930.411 840.265 910.904 850.229 910.079 910.250 870.185 920.320 920.510 900.385 920.548 910.597 940.394 87
SurfaceConvPF0.442 870.505 860.622 840.380 940.342 900.654 840.227 920.397 860.367 870.276 900.924 760.240 900.198 660.359 810.262 850.366 880.581 810.435 880.640 860.668 860.398 86
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
3DWSSS0.425 900.525 850.647 780.522 850.324 910.488 950.077 960.712 550.353 880.401 770.636 960.281 860.176 730.340 820.565 650.175 950.551 860.398 910.370 950.602 910.361 89
PointCNN with RGBpermissive0.458 840.577 810.611 850.356 950.321 920.715 780.299 850.376 880.328 910.319 860.944 530.285 850.164 780.216 920.229 870.484 800.545 870.456 830.755 750.709 810.475 83
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
SPLAT Netcopyleft0.393 920.472 910.511 920.606 780.311 930.656 830.245 900.405 850.328 910.197 940.927 750.227 920.000 970.001 960.249 860.271 940.510 900.383 930.593 900.699 830.267 93
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
ScanNetpermissive0.306 960.203 950.366 950.501 860.311 930.524 940.211 940.002 960.342 900.189 950.786 930.145 950.102 880.245 880.152 930.318 930.348 950.300 950.460 940.437 960.182 96
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
PointNet++permissive0.339 940.584 800.478 940.458 900.256 950.360 960.250 880.247 920.278 940.261 920.677 950.183 930.117 870.212 930.145 940.364 890.346 960.232 960.548 910.523 950.252 94
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 950.353 930.290 960.278 960.166 960.553 930.169 950.286 900.147 950.148 960.908 830.182 940.064 920.023 950.018 960.354 900.363 940.345 940.546 930.685 840.278 92
ERROR0.054 970.000 960.041 970.172 970.030 970.062 970.001 970.035 950.004 960.051 970.143 970.019 960.003 960.041 940.050 950.003 960.054 970.018 970.005 960.264 970.082 97