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
OccuSeg+Semantic0.764 10.758 170.796 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
BPNet0.749 20.909 10.818 30.811 60.752 10.839 50.485 90.842 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
Virtual MVFusion0.746 30.771 150.819 20.848 10.702 60.865 30.397 250.899 10.699 10.664 20.948 140.588 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
MinkowskiNetpermissive0.736 40.859 40.818 30.832 40.709 50.840 40.521 40.853 30.660 40.643 40.951 70.544 40.286 120.731 50.893 10.675 120.772 80.683 40.874 160.852 50.727 2
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
SparseConvNet0.725 50.647 280.821 10.846 20.721 40.869 20.533 20.754 120.603 90.614 50.955 30.572 30.325 40.710 60.870 20.724 60.823 20.628 70.934 40.865 30.683 7
MatchingNet0.724 60.812 110.812 50.810 70.735 30.834 60.495 80.860 20.572 140.602 70.954 40.512 70.280 130.757 30.845 80.725 50.780 70.606 110.937 20.851 60.700 6
JSENet0.699 70.881 20.762 110.821 50.667 80.800 160.522 30.792 80.613 60.607 60.935 270.492 100.205 230.576 170.853 50.691 90.758 110.652 60.872 180.828 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
CU-Hybrid Net0.693 80.596 330.789 70.803 90.677 70.800 160.469 130.846 50.554 200.591 90.948 140.500 80.316 60.609 110.847 70.732 40.808 40.593 120.894 90.839 70.652 9
FusionNet0.688 90.704 230.741 160.754 160.656 90.829 80.501 60.741 130.609 70.548 120.950 110.522 60.371 10.633 90.756 120.715 70.771 90.623 80.861 220.814 100.658 8
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
KP-FCNN0.684 100.847 60.758 140.784 110.647 110.814 110.473 110.772 100.605 80.594 80.935 270.450 160.181 300.587 130.805 110.690 100.785 60.614 90.882 120.819 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
PointASNLpermissive0.666 110.703 240.781 80.751 180.655 100.830 70.471 120.769 110.474 300.537 130.951 70.475 110.279 140.635 80.698 170.675 120.751 130.553 210.816 280.806 130.703 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
PointConvpermissive0.666 110.781 130.759 130.699 200.644 120.822 100.475 100.779 90.564 170.504 210.953 50.428 240.203 250.586 140.754 130.661 150.753 120.588 130.902 60.813 120.642 11
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
DCM-Net0.658 130.778 140.702 220.806 80.619 140.813 120.468 140.693 220.494 270.524 170.941 210.449 170.298 80.510 230.821 90.675 120.727 150.568 160.826 250.803 150.637 12
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
MVPNetpermissive0.641 140.831 80.715 200.671 250.590 180.781 210.394 260.679 250.642 50.553 110.937 250.462 130.256 150.649 70.406 330.626 190.691 210.666 50.877 130.792 210.608 17
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 150.717 220.701 230.692 220.576 220.801 140.467 150.716 180.563 180.459 280.953 50.429 230.169 320.581 150.854 40.605 210.710 160.550 220.894 90.793 200.575 23
FPConvpermissive0.639 160.785 120.760 120.713 190.603 160.798 180.392 270.534 350.603 90.524 170.948 140.457 140.250 160.538 200.723 140.598 240.696 200.614 90.872 180.799 160.567 26
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
SConv0.636 170.830 90.697 260.752 170.572 240.780 220.445 180.716 180.529 210.530 140.951 70.446 180.170 310.507 250.666 190.636 180.682 230.541 260.886 110.799 160.594 21
joint point-basedpermissive0.634 180.614 310.778 90.667 270.633 130.825 90.420 200.804 70.467 320.561 100.951 70.494 90.291 90.566 180.458 280.579 280.764 100.559 200.838 240.814 100.598 20
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
MCCNNpermissive0.633 190.866 30.731 180.771 120.576 220.809 130.410 220.684 230.497 260.491 230.949 120.466 120.105 400.581 150.646 200.620 200.680 240.542 250.817 270.795 180.618 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
3DSM_DMMF0.631 200.626 300.745 150.801 100.607 150.751 270.506 50.729 160.565 160.491 230.866 420.434 200.197 270.595 120.630 210.709 80.705 170.560 190.875 150.740 320.491 35
FusionAwareConv0.630 210.604 320.741 160.766 140.590 180.747 280.501 60.734 140.503 250.527 150.919 350.454 150.323 50.550 190.420 320.678 110.688 220.544 240.896 80.795 180.627 14
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
PointMRNet-lite0.625 220.643 290.711 210.697 210.581 210.801 140.408 230.670 270.558 190.497 220.944 190.436 190.152 360.617 100.708 150.603 220.743 140.532 280.870 210.784 220.545 28
SIConv0.625 220.830 90.694 270.757 150.563 250.772 240.448 160.647 290.520 220.509 190.949 120.431 220.191 280.496 280.614 220.647 160.672 250.535 270.876 140.783 230.571 24
HPEIN0.618 240.729 190.668 300.647 280.597 170.766 250.414 210.680 240.520 220.525 160.946 170.432 210.215 210.493 290.599 230.638 170.617 330.570 150.897 70.806 130.605 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
SPH3D-GCNpermissive0.610 250.858 50.772 100.489 390.532 260.792 190.404 240.643 300.570 150.507 200.935 270.414 250.046 450.510 230.702 160.602 230.705 170.549 230.859 230.773 250.534 30
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
LAP-D0.594 260.720 200.692 280.637 300.456 330.773 230.391 290.730 150.587 110.445 300.940 230.381 280.288 100.434 310.453 290.591 260.649 270.581 140.777 320.749 310.610 16
DPC0.592 270.720 200.700 240.602 330.480 300.762 260.380 310.713 200.585 120.437 310.940 230.369 300.288 100.434 310.509 260.590 270.639 310.567 170.772 330.755 290.592 22
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 280.766 160.659 330.683 240.470 320.740 300.387 300.620 310.490 280.476 260.922 330.355 330.245 170.511 220.511 250.571 290.643 290.493 320.872 180.762 270.600 19
SegGCNpermissive0.589 280.833 70.731 180.539 370.514 270.789 200.448 160.467 360.573 130.484 250.936 260.396 260.061 440.501 260.507 270.594 250.700 190.563 180.874 160.771 260.493 34
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
TextureNetpermissive0.566 300.672 260.664 310.671 250.494 280.719 310.445 180.678 260.411 370.396 320.935 270.356 320.225 190.412 330.535 240.565 300.636 320.464 340.794 310.680 370.568 25
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
DVVNet0.562 310.648 270.700 240.770 130.586 200.687 350.333 330.650 280.514 240.475 270.906 390.359 310.223 200.340 360.442 310.422 390.668 260.501 300.708 370.779 240.534 30
Pointnet++ & Featurepermissive0.557 320.735 180.661 320.686 230.491 290.744 290.392 270.539 340.451 330.375 350.946 170.376 290.205 230.403 340.356 350.553 310.643 290.497 310.824 260.756 280.515 32
PanopticFusion-label0.529 330.491 400.688 290.604 320.386 360.632 400.225 440.705 210.434 350.293 390.815 430.348 340.241 180.499 270.669 180.507 320.649 270.442 380.796 300.602 430.561 27
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3DMV, FTSDF0.501 340.558 370.608 390.424 440.478 310.690 340.246 400.586 320.468 310.450 290.911 370.394 270.160 340.438 300.212 410.432 380.541 390.475 330.742 350.727 330.477 36
PCNN0.498 350.559 360.644 360.560 360.420 350.711 330.229 420.414 370.436 340.352 360.941 210.324 350.155 350.238 410.387 340.493 330.529 400.509 290.813 290.751 300.504 33
3DMV0.484 360.484 410.538 420.643 290.424 340.606 430.310 340.574 330.433 360.378 340.796 440.301 360.214 220.537 210.208 420.472 370.507 430.413 410.693 380.602 430.539 29
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 370.577 350.611 380.356 460.321 420.715 320.299 360.376 400.328 430.319 370.944 190.285 380.164 330.216 440.229 400.484 350.545 380.456 360.755 340.709 340.475 37
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 380.679 250.604 400.578 350.380 370.682 360.291 370.106 460.483 290.258 440.920 340.258 400.025 460.231 430.325 360.480 360.560 370.463 350.725 360.666 390.231 46
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
SurfaceConvPF0.442 390.505 390.622 370.380 450.342 410.654 380.227 430.397 390.367 410.276 410.924 320.240 420.198 260.359 350.262 380.366 410.581 350.435 390.640 400.668 380.398 39
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET20.442 390.548 380.548 410.597 340.363 390.628 410.300 350.292 410.374 400.307 380.881 410.268 390.186 290.238 410.204 430.407 400.506 440.449 370.667 390.620 410.462 38
Tangent Convolutionspermissive0.438 410.437 440.646 350.474 410.369 380.645 390.353 320.258 430.282 450.279 400.918 360.298 370.147 370.283 380.294 370.487 340.562 360.427 400.619 410.633 400.352 41
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
subcloud_weak0.411 420.479 420.650 340.475 400.285 450.519 460.087 470.725 170.396 390.386 330.621 470.250 410.117 380.338 370.443 300.188 470.594 340.369 440.377 470.616 420.306 42
SPLAT Netcopyleft0.393 430.472 430.511 430.606 310.311 430.656 370.245 410.405 380.328 430.197 450.927 310.227 440.000 480.001 480.249 390.271 460.510 410.383 430.593 420.699 350.267 44
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+FTSDF0.383 440.297 460.491 440.432 430.358 400.612 420.274 380.116 450.411 370.265 420.904 400.229 430.079 420.250 390.185 440.320 440.510 410.385 420.548 430.597 450.394 40
PointNet++permissive0.339 450.584 340.478 450.458 420.256 460.360 470.250 390.247 440.278 460.261 430.677 460.183 450.117 380.212 450.145 460.364 420.346 470.232 470.548 430.523 460.252 45
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 460.353 450.290 470.278 470.166 470.553 440.169 460.286 420.147 470.148 470.908 380.182 460.064 430.023 470.018 480.354 430.363 450.345 450.546 450.685 360.278 43
ScanNetpermissive0.306 470.203 470.366 460.501 380.311 430.524 450.211 450.002 480.342 420.189 460.786 450.145 470.102 410.245 400.152 450.318 450.348 460.300 460.460 460.437 470.182 47
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 480.000 480.041 480.172 480.030 480.062 480.001 480.035 470.004 480.051 480.143 480.019 480.003 470.041 460.050 470.003 480.054 480.018 480.005 480.264 480.082 48

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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
OccuSeg+instance0.672 11.000 10.758 70.682 30.576 10.842 10.477 10.504 110.524 20.567 10.585 10.451 20.557 61.000 10.751 10.797 20.563 51.000 10.467 4
GICN0.638 21.000 10.895 10.800 10.480 50.676 80.144 40.737 20.354 60.447 40.400 110.365 60.700 11.000 10.569 30.836 10.599 21.000 10.473 3
PointGroup0.636 31.000 10.765 50.624 40.505 40.797 30.116 70.696 30.384 50.441 50.559 20.476 10.596 41.000 10.666 20.756 50.556 80.997 60.513 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-MPA0.611 41.000 10.833 20.765 20.526 20.756 70.136 60.588 80.470 30.438 60.432 90.358 70.650 20.857 60.429 70.765 40.557 71.000 10.430 6
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
PCJC0.578 51.000 10.810 30.583 90.449 80.813 20.042 120.603 60.341 70.490 20.465 40.410 40.650 20.835 100.264 150.694 70.561 60.889 130.504 2
SSEN0.575 61.000 10.761 60.473 110.477 60.795 40.066 100.529 90.658 10.460 30.461 50.380 50.331 140.859 50.401 100.692 80.653 11.000 10.348 10
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
MTML0.549 71.000 10.807 40.588 80.327 120.647 90.004 180.815 10.180 120.418 70.364 130.182 100.445 91.000 10.442 60.688 90.571 41.000 10.396 7
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
Sparse R-CNN0.515 81.000 10.538 160.282 150.468 70.790 50.173 20.345 140.429 40.413 90.484 30.176 110.595 50.591 140.522 40.668 100.476 110.986 70.327 11
Occipital-SCS0.512 91.000 10.716 100.509 100.506 30.611 110.092 90.602 70.177 130.346 120.383 120.165 120.442 100.850 90.386 120.618 120.543 90.889 130.389 8
PE0.508 100.667 130.748 80.603 50.436 90.757 60.167 30.407 130.323 80.385 100.443 60.064 170.466 70.714 120.398 110.792 30.476 120.984 80.310 12
3D-BoNet0.488 111.000 10.672 130.590 70.301 130.484 170.098 80.620 40.306 90.341 130.259 150.125 140.434 110.796 110.402 90.499 170.513 100.909 120.439 5
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
PanopticFusion-inst0.478 120.667 130.712 120.595 60.259 150.550 150.000 210.613 50.175 140.250 160.434 70.437 30.411 130.857 60.485 50.591 150.267 190.944 100.359 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)
SALoss-ResNet0.459 131.000 10.737 90.159 200.259 140.587 130.138 50.475 120.217 110.416 80.408 100.128 130.315 150.714 120.411 80.536 160.590 30.873 160.304 13
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
MASCpermissive0.447 140.528 180.555 150.381 120.382 100.633 100.002 190.509 100.260 100.361 110.432 80.327 80.451 80.571 150.367 130.639 110.386 130.980 90.276 14
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
3D-SISpermissive0.382 151.000 10.432 180.245 160.190 160.577 140.013 160.263 160.033 200.320 140.240 160.075 160.422 120.857 60.117 180.699 60.271 180.883 150.235 16
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
UNet-backbone0.319 160.667 130.715 110.233 170.189 170.479 180.008 170.218 170.067 190.201 170.173 170.107 150.123 180.438 160.150 160.615 130.355 140.916 110.093 21
R-PointNet0.306 170.500 190.405 190.311 130.348 110.589 120.054 110.068 200.126 150.283 150.290 140.028 190.219 160.214 190.331 140.396 190.275 170.821 180.245 15
Region0.248 180.667 130.437 170.188 180.153 180.491 160.000 210.208 180.094 170.153 180.099 190.057 180.217 170.119 200.039 210.466 180.302 160.640 190.140 18
3D-BEVIS0.248 180.667 130.566 140.076 210.035 220.394 190.027 140.035 210.098 160.099 200.030 210.025 200.098 190.375 170.126 170.604 140.181 200.854 170.171 17
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Seg-Clusterpermissive0.215 200.370 200.337 210.285 140.105 190.325 200.025 150.282 150.085 180.105 190.107 180.007 220.079 200.317 180.114 190.309 210.304 150.587 200.123 20
Sgpn_scannet0.143 210.208 220.390 200.169 190.065 200.275 210.029 130.069 190.000 210.087 210.043 200.014 210.027 220.000 210.112 200.351 200.168 210.438 210.138 19
MaskRCNN 2d->3d Proj0.058 220.333 210.002 220.000 220.053 210.002 220.002 200.021 220.000 210.045 220.024 220.238 90.065 210.000 210.014 220.107 220.020 220.110 220.006 22

This table lists the benchmark results for the 2D 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
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 40.770 20.574 30.865 30.831 30.675 2
CU-Hybrid-2D Net0.636 30.825 20.820 20.179 150.648 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 70.851 20.634 3
DMMF_3d0.605 40.651 60.744 70.782 30.637 40.387 40.536 20.732 40.590 50.540 40.856 120.359 60.306 100.596 60.539 20.627 110.706 40.497 60.785 110.757 100.476 12
DMMF0.597 50.543 100.755 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 60.646 80.513 40.842 50.774 80.527 10
MCA-Net0.595 60.533 110.756 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 90.648 60.501 50.839 60.769 90.516 11
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 70.648 60.480 70.814 90.814 40.614 5
DCRedNet0.583 80.682 50.723 80.542 90.510 100.310 110.451 60.668 80.549 80.520 60.920 50.375 40.446 20.528 100.417 90.670 80.577 130.478 80.862 40.806 50.628 4
SSMAcopyleft0.577 90.695 40.716 100.439 110.563 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 6
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
FuseNetpermissive0.535 100.570 90.681 120.182 140.512 90.290 120.431 90.659 90.504 110.495 90.903 90.308 100.428 30.523 110.365 110.676 50.621 100.470 90.762 120.779 70.541 8
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 110.613 80.722 90.418 120.358 160.337 70.370 140.479 140.443 120.368 140.907 70.207 130.213 150.464 140.525 50.618 120.657 50.450 110.788 100.721 130.408 15
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 120.481 140.612 130.579 80.456 120.343 50.384 120.623 120.525 100.381 130.845 130.254 120.264 130.557 90.182 140.581 140.598 120.429 120.760 130.661 150.446 14
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 130.505 120.709 110.092 160.427 130.241 130.411 110.654 110.385 160.457 110.861 110.053 160.279 110.503 120.481 70.645 100.626 90.365 140.748 140.725 120.529 9
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 140.490 130.581 140.289 130.507 110.067 160.379 130.610 130.417 140.435 120.822 150.278 110.267 120.503 120.228 130.616 130.533 140.375 130.820 80.729 110.560 7
Enet (reimpl)0.376 150.264 160.452 160.452 100.365 140.181 140.143 160.456 150.409 150.346 150.769 160.164 140.218 140.359 150.123 160.403 160.381 160.313 160.571 150.685 140.472 13
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)permissive0.330 160.293 150.521 150.657 70.361 150.161 150.250 150.004 160.440 130.183 160.836 140.125 150.060 160.319 160.132 150.417 150.412 150.344 150.541 160.427 160.109 16
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17

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




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
MaskRCNN_ScanNetpermissive0.119 10.129 10.212 10.002 10.112 10.148 10.014 10.205 10.044 10.066 10.078 10.095 10.142 10.030 10.128 10.139 10.080 10.459 10.057 1
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-task learnerpermissive0.700 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.
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