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 10.758 260.796 70.839 40.746 20.907 10.562 10.850 50.680 20.672 10.978 10.610 10.335 20.777 10.819 120.847 10.830 10.691 30.972 10.885 10.727 2
SparseConvNet0.725 60.647 430.821 20.846 30.721 50.869 20.533 20.754 160.603 140.614 60.955 40.572 30.325 40.710 70.870 30.724 60.823 20.628 100.934 50.865 30.683 8
Virtual MVFusion0.746 30.771 220.819 30.848 20.702 70.865 30.397 390.899 10.699 10.664 20.948 180.588 20.330 30.746 50.851 70.764 30.796 60.704 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 40.838 10.858 10.729 40.850 40.501 70.874 20.587 170.658 30.956 30.564 40.299 90.765 30.900 10.716 70.812 40.631 90.939 20.858 40.709 5
MinkowskiNetpermissive0.736 50.859 60.818 40.832 50.709 60.840 50.521 40.853 40.660 40.643 50.951 90.544 50.286 140.731 60.893 20.675 150.772 100.683 40.874 220.852 60.727 2
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
BPNet0.749 20.909 10.818 40.811 80.752 10.839 60.485 120.842 70.673 30.644 40.957 20.528 60.305 80.773 20.859 40.788 20.818 30.693 20.916 60.856 50.723 4
PointNet2-SFPN0.631 310.771 220.692 380.672 350.524 400.837 70.440 300.706 290.538 310.446 420.944 270.421 370.219 290.552 290.751 190.591 390.737 190.543 360.901 90.768 400.557 40
MatchingNet0.724 70.812 150.812 60.810 90.735 30.834 80.495 100.860 30.572 210.602 90.954 50.512 80.280 150.757 40.845 100.725 50.780 80.606 170.937 30.851 70.700 7
PointASNLpermissive0.666 140.703 370.781 90.751 210.655 120.830 90.471 150.769 130.474 440.537 170.951 90.475 140.279 160.635 120.698 290.675 150.751 150.553 320.816 410.806 150.703 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-Netpermissive0.645 190.778 180.731 230.699 260.577 290.829 100.446 240.736 210.477 430.523 250.945 250.454 230.269 180.484 420.749 200.618 310.738 180.599 180.827 370.792 270.621 18
FusionNet0.688 110.704 360.741 200.754 190.656 110.829 100.501 70.741 200.609 120.548 150.950 130.522 70.371 10.633 140.756 170.715 80.771 110.623 110.861 310.814 120.658 10
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
PointConv-SFPN0.641 200.776 200.703 300.721 220.557 370.826 120.451 200.672 360.563 260.483 350.943 300.425 360.162 450.644 100.726 210.659 200.709 240.572 220.875 200.786 310.559 39
joint point-basedpermissive0.634 280.614 460.778 100.667 390.633 160.825 130.420 320.804 90.467 460.561 130.951 90.494 100.291 110.566 280.458 430.579 420.764 120.559 290.838 360.814 120.598 26
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointConvpermissive0.666 140.781 170.759 150.699 260.644 150.822 140.475 130.779 110.564 250.504 290.953 60.428 330.203 350.586 220.754 180.661 190.753 140.588 200.902 80.813 140.642 13
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
HPGCNN0.656 170.698 380.743 190.650 410.564 340.820 150.505 60.758 150.631 80.479 360.945 250.480 120.226 260.572 260.774 160.690 120.735 200.614 130.853 340.776 370.597 27
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
RFCR0.702 80.889 20.745 170.813 70.672 90.818 160.493 110.815 80.623 90.610 70.947 210.470 160.249 230.594 190.848 80.705 100.779 90.646 70.892 140.823 100.611 20
SAFNet-segcopyleft0.654 180.752 270.734 220.664 400.583 270.815 170.399 380.754 160.639 70.535 180.942 310.470 160.309 70.665 80.539 370.650 210.708 250.635 80.857 330.793 250.642 13
KP-FCNN0.684 120.847 80.758 160.784 130.647 140.814 180.473 140.772 120.605 130.594 100.935 400.450 250.181 410.587 200.805 140.690 120.785 70.614 130.882 170.819 110.632 16
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DCM-Net0.658 160.778 180.702 310.806 100.619 170.813 190.468 170.693 310.494 400.524 230.941 330.449 260.298 100.510 350.821 110.675 150.727 210.568 250.826 380.803 170.637 15
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
MCCNNpermissive0.633 290.866 50.731 230.771 140.576 300.809 200.410 340.684 320.497 390.491 320.949 150.466 190.105 550.581 230.646 320.620 290.680 360.542 370.817 400.795 220.618 19
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
SALANet0.670 130.816 140.770 120.768 160.652 130.807 210.451 200.747 180.659 50.545 160.924 460.473 150.149 510.571 270.811 130.635 270.746 160.623 110.892 140.794 240.570 34
PointMRNet0.640 220.717 350.701 320.692 290.576 300.801 220.467 180.716 260.563 260.459 400.953 60.429 320.169 430.581 230.854 50.605 330.710 230.550 330.894 120.793 250.575 32
PointMRNet-lite0.625 350.643 440.711 270.697 280.581 280.801 220.408 350.670 370.558 280.497 300.944 270.436 280.152 490.617 160.708 250.603 340.743 170.532 410.870 280.784 320.545 41
CU-Hybrid Net0.693 100.596 480.789 80.803 110.677 80.800 240.469 160.846 60.554 290.591 110.948 180.500 90.316 60.609 170.847 90.732 40.808 50.593 190.894 120.839 80.652 11
JSENet0.699 90.881 30.762 130.821 60.667 100.800 240.522 30.792 100.613 100.607 80.935 400.492 110.205 330.576 250.853 60.691 110.758 130.652 60.872 250.828 90.649 12
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
FPConvpermissive0.639 230.785 160.760 140.713 250.603 200.798 260.392 410.534 490.603 140.524 230.948 180.457 210.250 220.538 310.723 220.598 370.696 310.614 130.872 250.799 190.567 36
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PointSPNet0.637 250.734 300.692 380.714 240.576 300.797 270.446 240.743 190.598 160.437 440.942 310.403 390.150 500.626 150.800 150.649 220.697 300.557 300.846 350.777 360.563 37
AttAN0.609 390.760 250.667 450.649 420.521 410.793 280.457 190.648 400.528 340.434 460.947 210.401 400.153 480.454 430.721 240.648 230.717 220.536 390.904 70.765 410.485 50
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
APCF-Net0.631 310.742 280.687 430.672 350.557 370.792 290.408 350.665 380.545 300.508 270.952 80.428 330.186 390.634 130.702 270.620 290.706 260.555 310.873 240.798 210.581 30
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
SPH3D-GCNpermissive0.610 380.858 70.772 110.489 540.532 390.792 290.404 370.643 420.570 220.507 280.935 400.414 380.046 600.510 350.702 270.602 350.705 270.549 340.859 320.773 380.534 43
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
VACNN++0.638 240.820 130.701 320.687 300.594 220.791 310.430 310.587 440.569 230.529 200.950 130.467 180.253 210.524 330.722 230.618 310.694 320.570 230.793 450.802 180.659 9
SegGCNpermissive0.589 420.833 90.731 230.539 520.514 420.789 320.448 220.467 510.573 200.484 340.936 380.396 410.061 590.501 380.507 420.594 380.700 290.563 270.874 220.771 390.493 48
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
PointMTL0.632 300.731 310.688 410.675 340.591 230.784 330.444 280.565 470.610 110.492 310.949 150.456 220.254 200.587 200.706 260.599 360.665 400.612 160.868 290.791 300.579 31
MVPNetpermissive0.641 200.831 100.715 260.671 370.590 240.781 340.394 400.679 340.642 60.553 140.937 370.462 200.256 190.649 90.406 480.626 280.691 330.666 50.877 180.792 270.608 23
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
SConv0.636 260.830 110.697 360.752 200.572 330.780 350.445 260.716 260.529 330.530 190.951 90.446 270.170 420.507 370.666 310.636 260.682 350.541 380.886 160.799 190.594 28
LAP-D0.594 400.720 330.692 380.637 450.456 480.773 360.391 430.730 230.587 170.445 430.940 350.381 430.288 120.434 460.453 440.591 390.649 410.581 210.777 460.749 460.610 22
SIConv0.625 350.830 110.694 370.757 180.563 350.772 370.448 220.647 410.520 350.509 260.949 150.431 310.191 380.496 400.614 340.647 240.672 380.535 400.876 190.783 330.571 33
HPEIN0.618 370.729 320.668 440.647 430.597 210.766 380.414 330.680 330.520 350.525 220.946 230.432 300.215 300.493 410.599 350.638 250.617 480.570 230.897 100.806 150.605 24
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
ROSMRF0.580 440.772 210.707 290.681 330.563 350.764 390.362 460.515 500.465 470.465 390.936 380.427 350.207 320.438 440.577 360.536 460.675 370.486 470.723 510.779 340.524 45
DPC0.592 410.720 330.700 340.602 480.480 450.762 400.380 450.713 280.585 190.437 440.940 350.369 450.288 120.434 460.509 410.590 410.639 460.567 260.772 470.755 440.592 29
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
Supervoxel-CNN0.635 270.656 410.711 270.719 230.613 180.757 410.444 280.765 140.534 320.566 120.928 440.478 130.272 170.636 110.531 390.664 180.645 430.508 430.864 300.792 270.611 20
3DSM_DMMF0.631 310.626 450.745 170.801 120.607 190.751 420.506 50.729 240.565 240.491 320.866 570.434 290.197 370.595 180.630 330.709 90.705 270.560 280.875 200.740 470.491 49
FusionAwareConv0.630 340.604 470.741 200.766 170.590 240.747 430.501 70.734 220.503 380.527 210.919 500.454 230.323 50.550 300.420 470.678 140.688 340.544 350.896 110.795 220.627 17
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
Pointnet++ & Featurepermissive0.557 470.735 290.661 470.686 310.491 440.744 440.392 410.539 480.451 480.375 500.946 230.376 440.205 330.403 490.356 500.553 450.643 440.497 450.824 390.756 430.515 46
CCRFNet0.589 420.766 240.659 480.683 320.470 470.740 450.387 440.620 430.490 410.476 370.922 480.355 480.245 240.511 340.511 400.571 430.643 440.493 460.872 250.762 420.600 25
TextureNetpermissive0.566 450.672 400.664 460.671 370.494 430.719 460.445 260.678 350.411 520.396 470.935 400.356 470.225 270.412 480.535 380.565 440.636 470.464 490.794 440.680 520.568 35
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 RGBpermissive0.458 520.577 500.611 530.356 610.321 570.715 470.299 510.376 550.328 580.319 520.944 270.285 530.164 440.216 590.229 550.484 500.545 530.456 510.755 480.709 490.475 52
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
PCNN0.498 500.559 510.644 510.560 510.420 500.711 480.229 570.414 520.436 490.352 510.941 330.324 500.155 470.238 560.387 490.493 480.529 550.509 420.813 420.751 450.504 47
3DMV, FTSDF0.501 490.558 520.608 540.424 590.478 460.690 490.246 550.586 450.468 450.450 410.911 520.394 420.160 460.438 440.212 560.432 530.541 540.475 480.742 490.727 480.477 51
DVVNet0.562 460.648 420.700 340.770 150.586 260.687 500.333 480.650 390.514 370.475 380.906 540.359 460.223 280.340 510.442 460.422 540.668 390.501 440.708 520.779 340.534 43
FCPNpermissive0.447 530.679 390.604 550.578 500.380 520.682 510.291 520.106 610.483 420.258 590.920 490.258 550.025 610.231 580.325 510.480 510.560 520.463 500.725 500.666 540.231 61
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
SPLAT Netcopyleft0.393 580.472 580.511 580.606 460.311 580.656 520.245 560.405 530.328 580.197 600.927 450.227 590.000 630.001 630.249 540.271 610.510 560.383 580.593 570.699 500.267 59
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
SurfaceConvPF0.442 540.505 540.622 520.380 600.342 560.654 530.227 580.397 540.367 560.276 560.924 460.240 570.198 360.359 500.262 530.366 560.581 500.435 540.640 550.668 530.398 54
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 560.437 590.646 500.474 560.369 530.645 540.353 470.258 580.282 600.279 550.918 510.298 520.147 520.283 530.294 520.487 490.562 510.427 550.619 560.633 550.352 56
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
PanopticFusion-label0.529 480.491 550.688 410.604 470.386 510.632 550.225 590.705 300.434 500.293 540.815 580.348 490.241 250.499 390.669 300.507 470.649 410.442 530.796 430.602 580.561 38
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
PNET20.442 540.548 530.548 560.597 490.363 540.628 560.300 500.292 560.374 550.307 530.881 560.268 540.186 390.238 560.204 580.407 550.506 590.449 520.667 540.620 560.462 53
ScanNet+FTSDF0.383 590.297 610.491 590.432 580.358 550.612 570.274 530.116 600.411 520.265 570.904 550.229 580.079 570.250 540.185 590.320 590.510 560.385 570.548 580.597 600.394 55
3DMV0.484 510.484 560.538 570.643 440.424 490.606 580.310 490.574 460.433 510.378 490.796 590.301 510.214 310.537 320.208 570.472 520.507 580.413 560.693 530.602 580.539 42
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
SSC-UNetpermissive0.308 610.353 600.290 620.278 620.166 620.553 590.169 610.286 570.147 620.148 620.908 530.182 610.064 580.023 620.018 630.354 580.363 600.345 600.546 600.685 510.278 58
ScanNetpermissive0.306 620.203 620.366 610.501 530.311 580.524 600.211 600.002 630.342 570.189 610.786 600.145 620.102 560.245 550.152 600.318 600.348 610.300 610.460 610.437 620.182 62
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
subcloud_weak0.411 570.479 570.650 490.475 550.285 600.519 610.087 620.725 250.396 540.386 480.621 620.250 560.117 530.338 520.443 450.188 620.594 490.369 590.377 620.616 570.306 57
PointNet++permissive0.339 600.584 490.478 600.458 570.256 610.360 620.250 540.247 590.278 610.261 580.677 610.183 600.117 530.212 600.145 610.364 570.346 620.232 620.548 580.523 610.252 60
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
ERROR0.054 630.000 630.041 630.172 630.030 630.062 630.001 630.035 620.004 630.051 630.143 630.019 630.003 620.041 610.050 620.003 630.054 630.018 630.005 630.264 630.082 63

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 21.000 10.758 110.682 70.576 30.842 10.477 10.504 150.524 30.567 10.585 20.451 50.557 101.000 10.751 10.797 30.563 81.000 10.467 7
Mask-Group0.664 31.000 10.822 30.764 60.616 20.815 20.139 60.694 70.597 20.459 50.566 30.599 10.600 60.516 190.715 20.819 20.635 31.000 10.603 1
CSC-Pretrained0.648 41.000 10.810 40.768 40.523 60.813 30.143 50.819 20.389 70.422 100.511 60.443 60.650 21.000 10.624 50.732 70.634 41.000 10.375 12
PCJC0.578 91.000 10.810 50.583 120.449 120.813 40.042 150.603 100.341 110.490 30.465 80.410 80.650 20.835 130.264 180.694 110.561 90.889 160.504 4
CRNet0.688 11.000 10.802 70.783 30.644 10.804 50.182 20.874 10.511 40.501 20.592 10.536 30.587 91.000 10.637 40.730 80.683 10.994 100.523 2
PointGroup0.636 71.000 10.765 90.624 80.505 80.797 60.116 90.696 60.384 80.441 70.559 40.476 40.596 71.000 10.666 30.756 60.556 110.997 80.513 3
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]
SSEN0.575 101.000 10.761 100.473 140.477 100.795 70.066 130.529 130.658 10.460 40.461 90.380 90.331 180.859 80.401 140.692 120.653 21.000 10.348 14
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-CNN0.515 121.000 10.538 200.282 170.468 110.790 80.173 30.345 170.429 60.413 130.484 70.176 150.595 80.591 170.522 80.668 140.476 150.986 110.327 15
PE0.645 51.000 10.773 80.798 20.538 40.786 90.088 120.799 40.350 100.435 90.547 50.545 20.646 50.933 70.562 70.761 50.556 120.997 80.501 5
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
3D-MPA0.611 81.000 10.833 20.765 50.526 50.756 100.136 80.588 120.470 50.438 80.432 120.358 110.650 20.857 90.429 110.765 40.557 101.000 10.430 9
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
GICN0.638 61.000 10.895 10.800 10.480 90.676 110.144 40.737 50.354 90.447 60.400 140.365 100.700 11.000 10.569 60.836 10.599 51.000 10.473 6
MTML0.549 111.000 10.807 60.588 110.327 150.647 120.004 200.815 30.180 150.418 110.364 160.182 140.445 131.000 10.442 100.688 130.571 71.000 10.396 10
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
MASCpermissive0.447 170.528 220.555 180.381 150.382 130.633 130.002 210.509 140.260 130.361 140.432 110.327 120.451 120.571 180.367 160.639 150.386 160.980 120.276 17
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
Occipital-SCS0.512 131.000 10.716 130.509 130.506 70.611 140.092 110.602 110.177 160.346 150.383 150.165 160.442 140.850 120.386 150.618 160.543 130.889 160.389 11
R-PointNet0.306 210.500 230.405 230.311 160.348 140.589 150.054 140.068 230.126 180.283 180.290 170.028 230.219 200.214 220.331 170.396 230.275 200.821 210.245 18
SALoss-ResNet0.459 161.000 10.737 120.159 230.259 170.587 160.138 70.475 160.217 140.416 120.408 130.128 170.315 190.714 150.411 120.536 200.590 60.873 190.304 16
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-SISpermissive0.382 181.000 10.432 220.245 190.190 190.577 170.013 180.263 180.033 220.320 170.240 190.075 200.422 160.857 90.117 210.699 90.271 210.883 180.235 19
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3Dcopyleft0.323 190.667 170.542 190.264 180.157 210.550 180.000 230.205 210.009 230.270 190.218 200.075 200.500 110.688 160.007 250.698 100.301 190.459 230.200 20
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
PanopticFusion-inst0.478 150.667 170.712 150.595 90.259 180.550 190.000 230.613 90.175 170.250 200.434 100.437 70.411 170.857 90.485 90.591 190.267 220.944 130.359 13
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Region0.248 220.667 170.437 210.188 210.153 220.491 200.000 230.208 200.094 200.153 220.099 220.057 220.217 210.119 230.039 230.466 220.302 180.640 220.140 22
3D-BoNet0.488 141.000 10.672 160.590 100.301 160.484 210.098 100.620 80.306 120.341 160.259 180.125 180.434 150.796 140.402 130.499 210.513 140.909 150.439 8
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-backbone0.319 200.667 170.715 140.233 200.189 200.479 220.008 190.218 190.067 210.201 210.173 210.107 190.123 220.438 200.150 190.615 170.355 170.916 140.093 24
3D-BEVIS0.248 220.667 170.566 170.076 240.035 250.394 230.027 170.035 240.098 190.099 230.030 240.025 240.098 230.375 210.126 200.604 180.181 230.854 200.171 21
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.143 240.208 250.390 240.169 220.065 230.275 240.029 160.069 220.000 240.087 240.043 230.014 250.027 250.000 240.112 220.351 240.168 240.438 240.138 23
MaskRCNN 2d->3d Proj0.058 250.333 240.002 250.000 250.053 240.002 250.002 220.021 250.000 240.045 250.024 250.238 130.065 240.000 240.014 240.107 250.020 250.110 250.006 25

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_2D0.670 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
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