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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
OccuSeg+Semantic0.764 10.758 150.796 40.839 20.746 10.907 10.562 10.850 30.680 10.672 10.978 10.610 10.335 10.777 10.819 70.847 10.830 10.691 10.972 10.885 10.727 1
MinkowskiNetpermissive0.736 20.859 30.818 20.832 30.709 40.840 30.521 40.853 20.660 20.643 20.951 50.544 30.286 90.731 30.893 10.675 90.772 60.683 20.874 130.852 30.727 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
MVPNetpermissive0.641 110.831 70.715 170.671 200.590 150.781 160.394 210.679 210.642 30.553 90.937 200.462 100.256 120.649 50.406 280.626 160.691 160.666 30.877 100.792 170.608 14
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
JSENet0.699 50.881 10.762 90.821 40.667 60.800 110.522 30.792 60.613 40.607 40.935 220.492 70.205 200.576 120.853 30.691 60.758 80.652 40.872 150.828 60.649 7
KP-FCNN0.684 70.847 50.758 120.784 90.647 80.814 80.473 90.772 80.605 50.594 60.935 220.450 130.181 270.587 90.805 80.690 70.785 40.614 60.882 90.819 70.632 10
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
FPConvpermissive0.639 120.785 110.760 100.713 160.603 130.798 130.392 220.534 300.603 60.524 140.948 110.457 110.250 130.538 150.723 100.598 190.696 150.614 60.872 150.799 130.567 22
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
SparseConvNet0.725 30.647 240.821 10.846 10.721 30.869 20.533 20.754 100.603 60.614 30.955 20.572 20.325 20.710 40.870 20.724 40.823 20.628 50.934 30.865 20.683 5
LAP-D0.594 210.720 180.692 230.637 250.456 280.773 180.391 240.730 120.587 80.445 250.940 180.381 230.288 70.434 260.453 240.591 210.649 220.581 110.777 270.749 260.610 13
DPC0.592 220.720 180.700 190.602 280.480 250.762 210.380 260.713 160.585 90.437 260.940 180.369 250.288 70.434 260.509 210.590 220.639 260.567 140.772 280.755 240.592 19
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
SegGCNpermissive0.589 230.833 60.731 150.539 320.514 220.789 150.448 130.467 310.573 100.484 210.936 210.396 210.061 390.501 210.507 220.594 200.700 140.563 150.874 130.771 210.493 29
Huan Lei, Naveed Akhtar, and Ajmal Mian: SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel. CVPR 2020
MatchingNet0.724 40.812 100.812 30.810 50.735 20.834 40.495 70.860 10.572 110.602 50.954 30.512 40.280 100.757 20.845 50.725 30.780 50.606 80.937 20.851 40.700 4
SPH3D-GCNpermissive0.610 200.858 40.772 80.489 340.532 210.792 140.404 200.643 250.570 120.507 170.935 220.414 200.046 400.510 180.702 110.602 180.705 120.549 190.859 180.773 200.534 25
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
3DSM_DMMF0.631 160.626 250.745 130.801 80.607 120.751 220.506 50.729 130.565 130.491 190.866 370.434 160.197 240.595 80.630 160.709 50.705 120.560 160.875 120.740 270.491 30
PointConvpermissive0.666 80.781 120.759 110.699 170.644 90.822 70.475 80.779 70.564 140.504 180.953 40.428 190.203 220.586 100.754 90.661 120.753 90.588 100.902 40.813 90.642 8
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
CU-Hybrid Net0.693 60.596 280.789 50.803 70.677 50.800 110.469 110.846 40.554 150.591 70.948 110.500 50.316 40.609 70.847 40.732 20.808 30.593 90.894 70.839 50.652 6
SConv0.636 130.830 80.697 210.752 140.572 190.780 170.445 150.716 150.529 160.530 110.951 50.446 150.170 280.507 200.666 140.636 150.682 180.541 220.886 80.799 130.594 18
SIConv0.625 180.830 80.694 220.757 130.563 200.772 190.448 130.647 240.520 170.509 160.949 90.431 180.191 250.496 230.614 170.647 130.672 200.535 230.876 110.783 180.571 20
HPEIN0.618 190.729 170.668 250.647 230.597 140.766 200.414 180.680 200.520 170.525 130.946 130.432 170.215 180.493 240.599 180.638 140.617 280.570 120.897 50.806 100.605 15
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
DVVNet0.562 260.648 230.700 190.770 110.586 170.687 300.333 280.650 230.514 190.475 230.906 340.359 260.223 170.340 310.442 260.422 340.668 210.501 250.708 320.779 190.534 25
FusionAwareConv0.630 170.604 270.741 140.766 120.590 150.747 230.501 60.734 110.503 200.527 120.919 300.454 120.323 30.550 140.420 270.678 80.688 170.544 200.896 60.795 150.627 11
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
MCCNNpermissive0.633 150.866 20.731 150.771 100.576 180.809 100.410 190.684 190.497 210.491 190.949 90.466 90.105 350.581 110.646 150.620 170.680 190.542 210.817 220.795 150.618 12
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
DCM-Net0.658 100.778 130.702 180.806 60.619 110.813 90.468 120.693 180.494 220.524 140.941 160.449 140.298 50.510 180.821 60.675 90.727 110.568 130.826 200.803 120.637 9
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
CCRFNet0.589 230.766 140.659 280.683 190.470 270.740 250.387 250.620 260.490 230.476 220.922 280.355 280.245 140.511 170.511 200.571 240.643 240.493 270.872 150.762 220.600 16
FCPNpermissive0.447 330.679 210.604 350.578 300.380 320.682 310.291 320.106 410.483 240.258 390.920 290.258 350.025 410.231 380.325 310.480 310.560 320.463 300.725 310.666 340.231 41
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
PointASNLpermissive0.666 80.703 200.781 60.751 150.655 70.830 50.471 100.769 90.474 250.537 100.951 50.475 80.279 110.635 60.698 120.675 90.751 100.553 180.816 230.806 100.703 3
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
3DMV, FTSDF0.501 290.558 320.608 340.424 390.478 260.690 290.246 350.586 270.468 260.450 240.911 320.394 220.160 300.438 250.212 360.432 330.541 340.475 280.742 300.727 280.477 31
joint point-basedpermissive0.634 140.614 260.778 70.667 220.633 100.825 60.420 170.804 50.467 270.561 80.951 50.494 60.291 60.566 130.458 230.579 230.764 70.559 170.838 190.814 80.598 17
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
Pointnet++ & Featurepermissive0.557 270.735 160.661 270.686 180.491 240.744 240.392 220.539 290.451 280.375 300.946 130.376 240.205 200.403 290.356 300.553 260.643 240.497 260.824 210.756 230.515 27
PCNN0.498 300.559 310.644 310.560 310.420 300.711 280.229 370.414 320.436 290.352 310.941 160.324 300.155 310.238 360.387 290.493 280.529 350.509 240.813 240.751 250.504 28
PanopticFusion-label0.529 280.491 350.688 240.604 270.386 310.632 350.225 390.705 170.434 300.293 340.815 380.348 290.241 150.499 220.669 130.507 270.649 220.442 330.796 250.602 380.561 23
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
3DMV0.484 310.484 360.538 370.643 240.424 290.606 380.310 290.574 280.433 310.378 290.796 390.301 310.214 190.537 160.208 370.472 320.507 380.413 360.693 330.602 380.539 24
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
ScanNet+FTSDF0.383 390.297 410.491 390.432 380.358 350.612 370.274 330.116 400.411 320.265 370.904 350.229 380.079 370.250 340.185 390.320 390.510 360.385 370.548 380.597 400.394 35
TextureNetpermissive0.566 250.672 220.664 260.671 200.494 230.719 260.445 150.678 220.411 320.396 270.935 220.356 270.225 160.412 280.535 190.565 250.636 270.464 290.794 260.680 320.568 21
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
subcloud_weak0.411 370.479 370.650 290.475 350.285 400.519 410.087 420.725 140.396 340.386 280.621 420.250 360.117 330.338 320.443 250.188 420.594 290.369 390.377 420.616 370.306 37
PNET20.442 340.548 330.548 360.597 290.363 340.628 360.300 300.292 360.374 350.307 330.881 360.268 340.186 260.238 360.204 380.407 350.506 390.449 320.667 340.620 360.462 33
SurfaceConvPF0.442 340.505 340.622 320.380 400.342 360.654 330.227 380.397 340.367 360.276 360.924 270.240 370.198 230.359 300.262 330.366 360.581 300.435 340.640 350.668 330.398 34
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
ScanNetpermissive0.306 420.203 420.366 410.501 330.311 380.524 400.211 400.002 430.342 370.189 410.786 400.145 420.102 360.245 350.152 400.318 400.348 410.300 410.460 410.437 420.182 42
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
SPLAT Netcopyleft0.393 380.472 380.511 380.606 260.311 380.656 320.245 360.405 330.328 380.197 400.927 260.227 390.000 430.001 430.249 340.271 410.510 360.383 380.593 370.699 300.267 39
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
PointCNN with RGBpermissive0.458 320.577 300.611 330.356 410.321 370.715 270.299 310.376 350.328 380.319 320.944 150.285 330.164 290.216 390.229 350.484 300.545 330.456 310.755 290.709 290.475 32
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
Tangent Convolutionspermissive0.438 360.437 390.646 300.474 360.369 330.645 340.353 270.258 380.282 400.279 350.918 310.298 320.147 320.283 330.294 320.487 290.562 310.427 350.619 360.633 350.352 36
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
PointNet++permissive0.339 400.584 290.478 400.458 370.256 410.360 420.250 340.247 390.278 410.261 380.677 410.183 400.117 330.212 400.145 410.364 370.346 420.232 420.548 380.523 410.252 40
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 410.353 400.290 420.278 420.166 420.553 390.169 410.286 370.147 420.148 420.908 330.182 410.064 380.023 420.018 430.354 380.363 400.345 400.546 400.685 310.278 38
ERROR0.054 430.000 430.041 430.172 430.030 430.062 430.001 430.035 420.004 430.051 430.143 430.019 430.003 420.041 410.050 420.003 430.054 430.018 430.005 430.264 430.082 43

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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
SSEN0.575 51.000 10.761 50.473 90.477 60.795 30.066 90.529 80.658 10.460 20.461 40.380 40.331 120.859 50.401 100.692 60.653 11.000 10.348 9
OccuSeg+instance0.672 11.000 10.758 60.682 30.576 10.842 10.477 10.504 100.524 20.567 10.585 10.451 20.557 51.000 10.751 10.797 20.563 51.000 10.467 3
3D-MPA0.611 41.000 10.833 20.765 20.526 20.756 50.136 50.588 70.470 30.438 50.432 70.358 60.650 20.857 60.429 70.765 30.557 61.000 10.430 5
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
Sparse R-CNN0.515 71.000 10.538 140.282 130.468 70.790 40.173 20.345 120.429 40.413 80.484 30.176 100.595 40.591 120.522 40.668 80.476 100.986 70.327 10
PointGroup0.636 31.000 10.765 40.624 40.505 40.797 20.116 60.696 30.384 50.441 40.559 20.476 10.596 31.000 10.666 20.756 40.556 70.997 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]
GICN0.638 21.000 10.895 10.800 10.480 50.676 60.144 30.737 20.354 60.447 30.400 90.365 50.700 11.000 10.569 30.836 10.599 21.000 10.473 2
3D-BoNet0.488 91.000 10.672 110.590 60.301 110.484 160.098 70.620 40.306 70.341 110.259 130.125 130.434 90.796 100.402 90.499 150.513 90.909 120.439 4
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
MASCpermissive0.447 120.528 160.555 130.381 100.382 80.633 80.002 170.509 90.260 80.361 90.432 60.327 70.451 60.571 130.367 120.639 90.386 110.980 80.276 12
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
ResNet-backbone0.459 111.000 10.737 70.159 180.259 120.587 120.138 40.475 110.217 90.416 70.408 80.128 120.315 130.714 110.411 80.536 140.590 30.873 150.304 11
MTML0.549 61.000 10.807 30.588 70.327 100.647 70.004 160.815 10.180 100.418 60.364 110.182 90.445 71.000 10.442 60.688 70.571 41.000 10.396 6
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
Occipital-SCS0.512 81.000 10.716 80.509 80.506 30.611 90.092 80.602 60.177 110.346 100.383 100.165 110.442 80.850 90.386 110.618 100.543 80.889 130.389 7
PanopticFusion-inst0.478 100.667 120.712 100.595 50.259 130.550 140.000 190.613 50.175 120.250 140.434 50.437 30.411 110.857 60.485 50.591 130.267 170.944 90.359 8
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
R-PointNet0.306 150.500 180.405 170.311 110.348 90.589 110.054 100.068 180.126 130.283 130.290 120.028 170.219 140.214 180.331 130.396 170.275 150.821 170.245 13
3D-BEVIS0.248 160.667 120.566 120.076 190.035 210.394 180.027 120.035 190.098 140.099 190.030 200.025 180.098 170.375 160.126 150.604 120.181 190.854 160.171 15
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Region0.248 160.667 120.437 150.188 160.153 160.491 150.000 190.208 160.094 150.153 170.099 170.057 160.217 150.119 190.039 200.466 160.302 140.640 180.140 16
Seg-Clusterpermissive0.215 180.370 190.337 190.285 120.105 170.325 190.025 130.282 130.085 160.105 180.107 160.007 210.079 180.317 170.114 170.309 190.304 130.587 190.123 18
UNet-backbone0.319 140.667 120.715 90.233 150.189 150.479 170.008 150.218 150.067 170.201 150.173 150.107 140.123 160.438 150.150 140.615 110.355 120.916 110.093 19
3D-SISpermissive0.382 131.000 10.432 160.245 140.190 140.577 130.013 140.263 140.033 180.320 120.240 140.075 150.422 100.857 60.117 160.699 50.271 160.883 140.235 14
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
PE0.188 190.528 160.046 200.017 200.062 190.600 100.000 190.003 210.030 190.177 160.032 190.013 200.000 210.487 140.090 190.093 210.261 180.916 100.029 20
Sgpn_scannet0.143 200.208 210.390 180.169 170.065 180.275 200.029 110.069 170.000 200.087 200.043 180.014 190.027 200.000 200.112 180.351 180.168 200.438 200.138 17
MaskRCNN 2d->3d Proj0.058 210.333 200.002 210.000 210.053 200.002 210.002 180.021 200.000 200.045 210.024 210.238 80.065 190.000 200.014 210.107 200.020 210.110 210.006 21

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
CU-Hybrid-2D Net0.636 10.825 10.820 10.179 130.648 10.463 10.549 10.742 10.676 10.628 10.961 10.420 10.379 30.684 10.381 70.732 10.723 10.599 10.827 50.851 10.634 1
DMMF0.597 30.543 80.755 40.749 20.585 40.338 40.494 40.704 40.598 20.494 80.911 40.347 60.327 70.593 50.527 20.675 40.646 60.513 20.842 30.774 60.527 7
DMMF_3d0.605 20.651 40.744 50.782 10.637 20.387 20.536 20.732 20.590 30.540 20.856 90.359 40.306 80.596 40.539 10.627 80.706 20.497 40.785 90.757 80.476 9
MCA-Net0.595 40.533 90.756 30.746 30.590 30.334 60.506 30.670 50.587 40.500 60.905 60.366 30.352 40.601 30.506 40.669 70.648 40.501 30.839 40.769 70.516 8
SSMAcopyleft0.577 70.695 20.716 80.439 90.563 60.314 80.444 70.719 30.551 50.503 50.887 80.346 70.348 50.603 20.353 90.709 20.600 80.457 80.901 10.786 40.599 4
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DCRedNet0.583 60.682 30.723 60.542 70.510 80.310 90.451 60.668 60.549 60.520 40.920 30.375 20.446 10.528 80.417 60.670 60.577 100.478 60.862 20.806 30.628 2
RFBNet0.592 50.616 50.758 20.659 40.581 50.330 70.469 50.655 80.543 70.524 30.924 20.355 50.336 60.572 60.479 50.671 50.648 40.480 50.814 70.814 20.614 3
3DMV (2d proj)0.498 100.481 110.612 100.579 60.456 100.343 30.384 90.623 90.525 80.381 100.845 100.254 100.264 100.557 70.182 110.581 110.598 90.429 100.760 110.661 120.446 11
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
FuseNetpermissive0.535 80.570 70.681 90.182 120.512 70.290 100.431 80.659 70.504 90.495 70.903 70.308 80.428 20.523 90.365 80.676 30.621 70.470 70.762 100.779 50.541 6
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 90.613 60.722 70.418 100.358 130.337 50.370 110.479 110.443 100.368 110.907 50.207 110.213 120.464 110.525 30.618 90.657 30.450 90.788 80.721 100.408 12
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
ScanNet (2d proj)permissive0.330 130.293 120.521 120.657 50.361 120.161 120.250 120.004 130.440 110.183 130.836 110.125 130.060 130.319 130.132 120.417 120.412 120.344 120.541 130.427 130.109 13
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ILC-PSPNet0.475 110.490 100.581 110.289 110.507 90.067 130.379 100.610 100.417 120.435 90.822 120.278 90.267 90.503 100.228 100.616 100.533 110.375 110.820 60.729 90.560 5
Enet (reimpl)0.376 120.264 130.452 130.452 80.365 110.181 110.143 130.456 120.409 130.346 120.769 130.164 120.218 110.359 120.123 130.403 130.381 130.313 130.571 120.685 110.472 10
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.

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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
MaskRCNN_ScanNetpermissive0.227 10.228 10.381 10.013 10.237 10.339 10.089 10.339 10.150 10.134 10.143 10.179 10.255 10.053 10.331 10.244 10.154 10.687 10.127 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
sort bysort bysort bysort bysort bysort bysort bysort bysorted 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.
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
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