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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort by
FusionNet0.688 90.704 260.741 170.754 160.656 90.829 80.501 60.741 130.609 90.548 120.950 120.522 60.371 10.633 100.756 130.715 70.771 90.623 90.861 250.814 100.658 8
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
OccuSeg+Semantic0.764 10.758 180.796 60.839 30.746 20.907 10.562 10.850 40.680 20.672 10.978 10.610 10.335 20.777 10.819 100.847 10.830 10.691 30.972 10.885 10.727 2
Virtual MVFusion0.746 30.771 150.819 20.848 10.702 60.865 30.397 290.899 10.699 10.664 20.948 160.588 20.330 30.746 40.851 60.764 30.796 50.704 10.935 30.866 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
SparseConvNet0.725 50.647 320.821 10.846 20.721 40.869 20.533 20.754 120.603 110.614 50.955 30.572 30.325 40.710 60.870 20.724 60.823 20.628 80.934 40.865 30.683 7
FusionAwareConv0.630 240.604 360.741 170.766 140.590 200.747 320.501 60.734 140.503 290.527 150.919 390.454 170.323 50.550 210.420 360.678 120.688 250.544 270.896 90.795 190.627 14
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
CU-Hybrid Net0.693 80.596 370.789 70.803 90.677 70.800 170.469 140.846 50.554 220.591 90.948 160.500 90.316 60.609 120.847 70.732 40.808 40.593 140.894 100.839 70.652 9
BPNet0.749 20.909 10.818 30.811 60.752 10.839 50.485 100.842 60.673 30.644 30.957 20.528 50.305 70.773 20.859 30.788 20.818 30.693 20.916 50.856 40.723 4
DCM-Net0.658 140.778 140.702 230.806 80.619 140.813 130.468 150.693 230.494 310.524 170.941 250.449 190.298 80.510 260.821 90.675 130.727 160.568 180.826 290.803 150.637 12
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
joint point-basedpermissive0.634 190.614 350.778 90.667 300.633 130.825 100.420 230.804 70.467 360.561 100.951 80.494 100.291 90.566 200.458 320.579 320.764 100.559 220.838 280.814 100.598 20
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
DPC0.592 310.720 230.700 250.602 370.480 340.762 300.380 350.713 200.585 140.437 340.940 270.369 340.288 100.434 350.509 300.590 310.639 350.567 190.772 370.755 330.592 22
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
LAP-D0.594 300.720 230.692 290.637 340.456 370.773 270.391 330.730 150.587 130.445 330.940 270.381 320.288 100.434 350.453 330.591 300.649 310.581 160.777 360.749 350.610 16
MinkowskiNetpermissive0.736 40.859 40.818 30.832 40.709 50.840 40.521 40.853 30.660 40.643 40.951 80.544 40.286 120.731 50.893 10.675 130.772 80.683 40.874 170.852 50.727 2
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
MatchingNet0.724 60.812 110.812 50.810 70.735 30.834 60.495 80.860 20.572 160.602 70.954 40.512 70.280 130.757 30.845 80.725 50.780 70.606 130.937 20.851 60.700 6
PointASNLpermissive0.666 110.703 270.781 80.751 180.655 100.830 70.471 130.769 110.474 340.537 130.951 80.475 120.279 140.635 80.698 210.675 130.751 140.553 240.816 320.806 130.703 5
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
MVPNetpermissive0.641 150.831 80.715 210.671 280.590 200.781 250.394 300.679 260.642 60.553 110.937 290.462 140.256 150.649 70.406 370.626 210.691 240.666 50.877 140.792 220.608 17
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMTL0.632 210.731 210.688 300.675 260.591 190.784 240.444 220.565 370.610 80.492 250.949 130.456 160.254 160.587 140.706 180.599 270.665 300.612 120.868 240.791 230.579 24
FPConvpermissive0.639 170.785 120.760 120.713 190.603 160.798 190.392 310.534 390.603 110.524 170.948 160.457 150.250 170.538 220.723 150.598 280.696 230.614 100.872 200.799 160.567 29
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
HPGCNN0.661 130.689 280.749 150.689 230.595 180.828 90.490 90.695 220.659 50.498 230.946 200.503 80.247 180.531 240.769 120.691 90.758 110.653 60.860 260.787 240.578 25
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
CCRFNet0.589 320.766 160.659 370.683 250.470 360.740 340.387 340.620 340.490 320.476 290.922 370.355 370.245 190.511 250.511 290.571 330.643 330.493 360.872 200.762 310.600 19
PanopticFusion-label0.529 370.491 440.688 300.604 360.386 400.632 440.225 480.705 210.434 390.293 430.815 470.348 380.241 200.499 300.669 220.507 360.649 310.442 420.796 340.602 470.561 30
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
TextureNetpermissive0.566 340.672 300.664 350.671 280.494 320.719 350.445 200.678 270.411 410.396 360.935 310.356 360.225 210.412 370.535 280.565 340.636 360.464 380.794 350.680 410.568 28
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
DVVNet0.562 350.648 310.700 250.770 130.586 220.687 390.333 370.650 300.514 280.475 300.906 430.359 350.223 220.340 400.442 350.422 430.668 290.501 340.708 410.779 270.534 33
HPEIN0.618 270.729 220.668 330.647 320.597 170.766 290.414 240.680 250.520 260.525 160.946 200.432 230.215 230.493 320.599 270.638 190.617 370.570 170.897 80.806 130.605 18
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
3DMV0.484 400.484 450.538 460.643 330.424 380.606 470.310 380.574 360.433 400.378 380.796 480.301 400.214 240.537 230.208 460.472 410.507 470.413 450.693 420.602 470.539 32
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
Pointnet++ & Featurepermissive0.557 360.735 200.661 360.686 240.491 330.744 330.392 310.539 380.451 370.375 390.946 200.376 330.205 250.403 380.356 390.553 350.643 330.497 350.824 300.756 320.515 35
JSENet0.699 70.881 20.762 110.821 50.667 80.800 170.522 30.792 80.613 70.607 60.935 310.492 110.205 250.576 190.853 50.691 90.758 110.652 70.872 200.828 80.649 10
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
PointConvpermissive0.666 110.781 130.759 130.699 200.644 120.822 110.475 110.779 90.564 190.504 220.953 50.428 260.203 270.586 160.754 140.661 160.753 130.588 150.902 70.813 120.642 11
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
SurfaceConvPF0.442 430.505 430.622 410.380 490.342 450.654 420.227 470.397 430.367 450.276 450.924 360.240 460.198 280.359 390.262 420.366 450.581 390.435 430.640 440.668 420.398 43
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
3DSM_DMMF0.631 220.626 340.745 160.801 100.607 150.751 310.506 50.729 160.565 180.491 260.866 460.434 220.197 290.595 130.630 250.709 80.705 200.560 210.875 160.740 360.491 38
SIConv0.625 250.830 90.694 280.757 150.563 270.772 280.448 180.647 320.520 260.509 190.949 130.431 240.191 300.496 310.614 260.647 180.672 280.535 310.876 150.783 260.571 27
APCF-Net0.631 220.742 190.687 320.672 270.557 280.792 210.408 260.665 290.545 230.508 200.952 70.428 260.186 310.634 90.702 190.620 220.706 190.555 230.873 190.798 180.581 23
PNET20.442 430.548 420.548 450.597 380.363 430.628 450.300 390.292 450.374 440.307 420.881 450.268 430.186 310.238 450.204 470.407 440.506 480.449 410.667 430.620 450.462 42
KP-FCNN0.684 100.847 60.758 140.784 110.647 110.814 120.473 120.772 100.605 100.594 80.935 310.450 180.181 330.587 140.805 110.690 110.785 60.614 100.882 130.819 90.632 13
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
SConv0.636 180.830 90.697 270.752 170.572 260.780 260.445 200.716 180.529 240.530 140.951 80.446 200.170 340.507 280.666 230.636 200.682 260.541 290.886 120.799 160.594 21
PointMRNet0.640 160.717 250.701 240.692 220.576 240.801 150.467 160.716 180.563 200.459 310.953 50.429 250.169 350.581 170.854 40.605 240.710 180.550 250.894 100.793 210.575 26
PointCNN with RGBpermissive0.458 410.577 390.611 420.356 500.321 460.715 360.299 400.376 440.328 470.319 410.944 230.285 420.164 360.216 480.229 440.484 390.545 420.456 400.755 380.709 380.475 41
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
3DMV, FTSDF0.501 380.558 410.608 430.424 480.478 350.690 380.246 440.586 350.468 350.450 320.911 410.394 310.160 370.438 340.212 450.432 420.541 430.475 370.742 390.727 370.477 40
PCNN0.498 390.559 400.644 400.560 400.420 390.711 370.229 460.414 410.436 380.352 400.941 250.324 390.155 380.238 450.387 380.493 370.529 440.509 330.813 330.751 340.504 36
AttAN0.609 290.760 170.667 340.649 310.521 300.793 200.457 170.648 310.528 250.434 350.947 190.401 290.153 390.454 330.721 160.648 170.717 170.536 300.904 60.765 300.485 39
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
PointMRNet-lite0.625 250.643 330.711 220.697 210.581 230.801 150.408 260.670 280.558 210.497 240.944 230.436 210.152 400.617 110.708 170.603 250.743 150.532 320.870 230.784 250.545 31
Tangent Convolutionspermissive0.438 450.437 480.646 390.474 450.369 420.645 430.353 360.258 470.282 490.279 440.918 400.298 410.147 410.283 420.294 410.487 380.562 400.427 440.619 450.633 440.352 45
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
subcloud_weak0.411 460.479 460.650 380.475 440.285 490.519 500.087 510.725 170.396 430.386 370.621 510.250 450.117 420.338 410.443 340.188 510.594 380.369 480.377 510.616 460.306 46
PointNet++permissive0.339 490.584 380.478 490.458 460.256 500.360 510.250 430.247 480.278 500.261 470.677 500.183 490.117 420.212 490.145 500.364 460.346 510.232 510.548 470.523 500.252 49
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
MCCNNpermissive0.633 200.866 30.731 190.771 120.576 240.809 140.410 250.684 240.497 300.491 260.949 130.466 130.105 440.581 170.646 240.620 220.680 270.542 280.817 310.795 190.618 15
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
ScanNetpermissive0.306 510.203 510.366 500.501 420.311 470.524 490.211 490.002 520.342 460.189 500.786 490.145 510.102 450.245 440.152 490.318 490.348 500.300 500.460 500.437 510.182 51
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ScanNet+FTSDF0.383 480.297 500.491 480.432 470.358 440.612 460.274 420.116 490.411 410.265 460.904 440.229 470.079 460.250 430.185 480.320 480.510 450.385 460.548 470.597 490.394 44
SSC-UNetpermissive0.308 500.353 490.290 510.278 510.166 510.553 480.169 500.286 460.147 510.148 510.908 420.182 500.064 470.023 510.018 520.354 470.363 490.345 490.546 490.685 400.278 47
SegGCNpermissive0.589 320.833 70.731 190.539 410.514 310.789 230.448 180.467 400.573 150.484 280.936 300.396 300.061 480.501 290.507 310.594 290.700 220.563 200.874 170.771 290.493 37
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
SPH3D-GCNpermissive0.610 280.858 50.772 100.489 430.532 290.792 210.404 280.643 330.570 170.507 210.935 310.414 280.046 490.510 260.702 190.602 260.705 200.549 260.859 270.773 280.534 33
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
FCPNpermissive0.447 420.679 290.604 440.578 390.380 410.682 400.291 410.106 500.483 330.258 480.920 380.258 440.025 500.231 470.325 400.480 400.560 410.463 390.725 400.666 430.231 50
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
ERROR0.054 520.000 520.041 520.172 520.030 520.062 520.001 520.035 510.004 520.051 520.143 520.019 520.003 510.041 500.050 510.003 520.054 520.018 520.005 520.264 520.082 52
SPLAT Netcopyleft0.393 470.472 470.511 470.606 350.311 470.656 410.245 450.405 420.328 470.197 490.927 350.227 480.000 520.001 520.249 430.271 500.510 450.383 470.593 460.699 390.267 48
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

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




Method Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort by
PanopticFusion-inst0.693 101.000 10.852 130.655 140.616 120.788 90.334 130.763 40.771 50.457 170.555 100.652 10.518 110.857 100.765 90.732 170.631 110.944 120.577 9
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
PointGroup0.778 21.000 10.900 90.798 30.715 70.863 40.493 70.706 60.895 20.569 100.701 10.576 20.639 51.000 10.880 10.851 70.719 50.997 60.709 1
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]
3D-MPA0.737 51.000 10.933 30.785 40.794 20.831 80.279 160.588 90.695 90.616 70.559 90.556 30.650 31.000 10.809 60.875 40.696 81.000 10.608 7
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
GICN0.788 11.000 10.978 20.867 10.781 30.833 70.527 60.824 30.806 40.549 110.596 50.551 40.700 11.000 10.853 20.935 10.733 31.000 10.651 2
MTML0.731 61.000 10.992 10.779 70.609 130.746 120.308 140.867 10.601 140.607 80.539 120.519 50.550 91.000 10.824 40.869 60.729 41.000 10.616 5
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
PCJC0.684 131.000 10.895 100.757 90.659 110.862 50.189 190.739 50.606 130.712 30.581 70.515 60.650 30.857 100.357 200.785 140.631 120.889 160.635 3
OccuSeg+instance0.742 41.000 10.923 60.785 40.745 50.867 30.557 40.578 110.729 70.670 40.644 20.488 70.577 81.000 10.794 80.830 90.620 131.000 10.550 10
MaskRCNN 2d->3d Proj0.261 220.903 170.081 220.008 220.233 210.175 220.280 150.106 220.150 220.203 220.175 210.480 80.218 220.143 210.542 160.404 220.153 220.393 220.049 22
SSEN0.724 71.000 10.926 40.781 60.661 100.845 60.596 30.529 130.764 60.653 50.489 150.461 90.500 140.859 90.765 90.872 50.761 11.000 10.577 8
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
MASCpermissive0.615 140.711 180.802 150.540 170.757 40.777 100.029 210.577 120.588 150.521 150.600 40.436 100.534 100.697 150.616 140.838 80.526 150.980 90.534 13
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
Sparse R-CNN0.714 81.000 10.926 50.694 120.699 80.890 10.636 10.516 140.693 100.743 20.588 60.369 110.601 60.594 160.800 70.886 30.676 90.986 80.546 11
SALoss-ResNet0.695 91.000 10.855 120.579 160.589 150.735 140.484 80.588 90.856 30.634 60.571 80.298 120.500 141.000 10.824 40.818 100.702 70.935 140.545 12
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)
UNet-backbone0.605 151.000 10.909 80.764 80.603 140.704 150.415 110.301 180.548 160.461 160.394 160.267 130.386 160.857 100.649 130.817 110.504 160.959 100.356 18
Occipital-SCS0.688 111.000 10.913 70.730 110.737 60.743 130.442 90.855 20.655 110.546 120.546 110.263 140.508 130.889 80.568 150.771 150.705 60.889 160.625 4
3D-BoNet0.687 121.000 10.887 110.836 20.587 160.643 180.550 50.620 70.724 80.522 140.501 130.243 150.512 121.000 10.751 110.807 120.661 100.909 150.612 6
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
PE0.752 31.000 10.849 140.743 100.815 10.886 20.616 20.614 80.917 10.768 10.644 30.221 160.655 20.793 140.845 30.890 20.759 20.997 60.529 14
R-PointNet0.544 170.500 220.655 190.661 130.663 90.765 110.432 100.214 200.612 120.584 90.499 140.204 170.286 190.429 180.655 120.650 200.539 140.950 110.499 15
Sgpn_scannet0.390 200.556 210.636 200.493 180.353 190.539 200.271 170.160 210.450 190.359 190.178 200.146 180.250 210.143 210.347 210.698 190.436 190.667 200.331 20
Region0.474 181.000 10.727 170.433 200.481 180.673 170.022 220.380 170.517 170.436 180.338 170.128 190.343 170.429 180.291 220.728 180.473 170.833 190.300 21
3D-SISpermissive0.558 161.000 10.773 160.614 150.503 170.691 160.200 180.412 160.498 180.546 130.311 180.103 200.600 70.857 100.382 180.799 130.445 180.938 130.371 16
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
3D-BEVIS0.401 190.667 190.687 180.419 210.137 220.587 190.188 200.235 190.359 200.211 210.093 220.080 210.311 180.571 170.382 180.754 160.300 210.874 180.357 17
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Seg-Clusterpermissive0.380 210.625 200.420 210.456 190.296 200.473 210.390 120.433 150.293 210.322 200.247 190.066 220.264 200.325 200.388 170.486 210.401 200.614 210.341 19

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 bysorted 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
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
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
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
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
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
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
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
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
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
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
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
Marin Oršić, Ivan Krešo, Petra Bevandić, Siniša Šegvić: In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images. CVPR 2019
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
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.
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
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
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort by
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
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

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