Presenting the ScanNet200 Benchmark

We present the ScanNet200 benchmark, which studies an order of magnitude more class categories than previous version of ScanNet. The scene geometry is shared within the two tasks, but the parsing of surface annotation allows for a larger vocabulary and more realistic setting for in the wild 3D understanding methods.

The ScanNet200 benchmark includes both finer-grained categories as well as a large number of previously unaddressed classes. This induces a much more challenging setting regarding the diversity of naturally observed semantic classes seen in the raw ScanNet RGB-D observations, where the data also reflects naturally encountered class imbalances. The difference in category frequencies between ScanNet and ScanNet200 can be seen in the Figure above.

ScanNet200 Benchmark

ScanNet200 3D Semantic Label Benchmark

This table lists the benchmark results for the ScanNet200 3D semantic label scenario.




Method Infoavg iouhead ioucommon ioutail ioualarm clockarmchairbackpackbagballbarbasketbathroom cabinetbathroom counterbathroom stallbathroom stall doorbathroom vanitybathtubbedbenchbicyclebinblackboardblanketblindsboardbookbookshelfbottlebowlboxbroombucketbulletin boardcabinetcalendarcandlecartcase of water bottlescd caseceilingceiling lightchairclockclosetcloset doorcloset rodcloset wallclothesclothes dryercoat rackcoffee kettlecoffee makercoffee tablecolumncomputer towercontainercopiercouchcountercratecupcurtaincushiondecorationdeskdining tabledish rackdishwasherdividerdoordoorframedresserdumbbelldustpanend tablefanfile cabinetfire alarmfire extinguisherfireplacefloorfolded chairfurnitureguitarguitar casehair dryerhandicap barhatheadphonesironing boardjacketkeyboardkeyboard pianokitchen cabinetkitchen counterladderlamplaptoplaundry basketlaundry detergentlaundry hamperledgelightlight switchluggagemachinemailboxmatmattressmicrowavemini fridgemirrormonitormousemusic standnightstandobjectoffice chairottomanovenpaperpaper bagpaper cutterpaper towel dispenserpaper towel rollpersonpianopicturepillarpillowpipeplantplateplungerposterpotted plantpower outletpower stripprinterprojectorprojector screenpurserackradiatorrailrange hoodrecycling binrefrigeratorscaleseatshelfshoeshowershower curtainshower curtain rodshower doorshower floorshower headshower wallsignsinksoap dishsoap dispensersofa chairspeakerstair railstairsstandstoolstorage binstorage containerstorage organizerstovestructurestuffed animalsuitcasetabletelephonetissue boxtoastertoaster oventoilettoilet papertoilet paper dispensertoilet paper holdertoilet seat cover dispensertoweltrash bintrash cantraytubetvtv standvacuum cleanerventwallwardrobewashing machinewater bottlewater coolerwater pitcherwhiteboardwindowwindowsill
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
BFANet ScanNet200permissive0.360 40.553 60.293 40.193 40.483 100.096 50.266 50.000 30.000 60.000 10.298 120.255 110.661 10.810 50.810 30.194 90.785 60.000 30.000 160.161 50.000 90.494 80.382 20.574 40.258 40.000 90.372 80.000 10.000 30.043 130.436 70.000 100.000 10.239 20.000 20.901 30.105 10.689 40.025 40.128 20.614 20.436 10.493 160.000 10.000 20.526 40.546 120.109 40.651 130.953 40.753 60.101 60.143 120.897 40.000 10.431 10.469 140.000 70.522 50.337 50.661 60.459 20.409 60.666 40.102 120.508 50.757 40.000 80.060 130.970 30.497 10.000 10.376 20.511 30.262 40.688 20.921 10.617 90.321 110.590 60.491 80.556 30.000 30.000 10.481 40.093 10.043 20.284 20.000 40.875 140.135 80.669 50.124 120.394 60.849 110.298 20.000 10.476 160.088 110.042 70.000 40.000 10.254 30.653 100.741 60.215 10.573 50.852 50.266 90.654 10.056 100.835 50.000 50.492 10.000 10.000 70.000 30.612 80.000 40.000 70.000 10.616 50.469 160.460 40.698 130.516 20.000 10.378 70.563 40.476 50.863 50.574 90.330 60.000 110.282 40.000 10.760 40.710 40.233 10.000 90.641 30.814 20.000 10.585 90.053 100.000 70.000 10.629 90.000 20.000 10.678 30.528 120.534 40.129 130.596 40.973 30.264 110.772 20.526 90.139 100.707 40.000 10.000 120.764 130.591 150.848 60.000 10.827 40.338 30.806 110.000 10.568 90.151 80.358 20.659 90.510 4
PPT-SpUNet-F.T.0.332 110.556 50.270 60.123 130.519 40.091 60.349 30.000 30.000 60.000 10.339 80.383 90.498 100.833 40.807 40.241 40.584 80.000 30.755 60.124 70.000 90.608 20.330 70.530 90.314 20.000 90.374 70.000 10.000 30.197 40.459 60.000 100.000 10.117 50.000 20.876 70.095 20.682 90.000 70.086 70.518 60.433 20.930 40.000 10.000 20.563 30.542 130.077 70.715 30.858 100.756 50.008 160.171 110.874 70.000 10.039 60.550 100.000 70.545 40.256 80.657 80.453 30.351 90.449 90.213 60.392 110.611 100.000 80.037 140.946 60.138 130.000 10.000 120.063 100.308 20.537 70.796 40.673 40.323 100.392 100.400 130.509 70.000 30.000 10.649 10.000 100.023 100.000 110.000 40.914 70.002 150.506 150.163 100.359 80.872 50.000 110.000 10.623 60.112 50.001 110.000 40.000 10.021 80.753 50.565 150.150 40.579 40.806 90.267 80.616 40.042 130.783 120.000 50.374 100.000 10.000 70.000 30.620 70.000 40.000 70.000 10.572 120.634 50.350 90.792 40.000 80.000 10.376 80.535 60.378 60.855 60.672 30.074 120.000 110.185 90.000 10.727 110.660 110.076 160.000 90.432 110.646 100.000 10.594 70.006 120.000 70.000 10.658 60.000 20.000 10.661 40.549 90.300 130.291 90.045 130.942 110.304 70.600 70.572 60.135 120.695 50.000 10.008 90.793 80.942 10.899 20.000 10.816 60.181 70.897 20.000 10.679 40.223 60.264 40.691 50.345 11
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormer ScanNet200permissive0.326 120.539 90.265 90.131 110.499 60.110 30.522 10.000 30.000 60.000 10.318 100.427 60.455 140.743 100.765 120.175 100.842 30.000 30.828 40.204 20.033 60.429 100.335 50.601 30.312 30.000 90.357 90.000 10.000 30.047 100.423 80.000 100.000 10.105 80.000 20.873 90.079 80.670 120.000 70.117 40.471 130.432 30.829 100.000 10.000 20.584 20.417 160.089 60.684 80.837 110.705 150.021 120.178 100.892 50.000 10.028 70.505 120.000 70.457 80.200 130.662 40.412 90.244 140.496 70.000 160.451 70.626 80.000 80.102 100.943 90.138 130.000 10.000 120.149 70.291 30.534 80.722 60.632 60.331 90.253 140.453 100.487 110.000 30.000 10.479 50.000 100.022 110.000 110.000 40.900 100.128 100.684 30.164 90.413 40.854 100.000 110.000 10.512 150.074 130.003 100.000 40.000 10.000 100.469 140.613 120.132 80.529 70.871 30.227 150.582 70.026 160.787 110.000 50.339 140.000 10.000 70.000 30.626 60.000 40.029 60.000 10.587 80.612 70.411 70.724 90.000 80.000 10.407 50.552 50.513 30.849 90.655 40.408 30.000 110.296 30.000 10.686 140.645 130.145 90.022 70.414 130.633 110.000 10.637 10.224 20.000 70.000 10.650 70.000 20.000 10.622 80.535 110.343 110.483 30.230 120.943 100.289 90.618 60.596 40.140 90.679 70.000 10.022 60.783 100.620 110.906 10.000 10.806 80.137 100.865 40.000 10.378 120.000 140.168 140.680 70.227 13
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
DITR0.409 20.616 10.351 10.215 30.651 10.238 10.400 20.000 30.340 10.000 10.534 20.476 40.585 20.687 150.853 10.143 120.854 20.000 30.865 20.167 40.000 90.175 160.573 10.617 20.372 10.362 10.591 10.000 10.000 30.330 10.494 20.247 90.000 10.385 10.000 20.878 60.037 130.791 10.053 20.118 30.479 110.429 40.940 30.000 10.000 20.461 70.562 100.093 50.628 140.991 10.762 20.135 30.270 30.917 30.000 10.140 40.597 20.000 70.361 110.375 10.730 20.431 50.459 30.410 120.008 150.656 10.814 10.036 60.554 30.947 50.139 100.000 10.263 50.896 10.191 80.615 40.839 30.757 10.399 50.877 10.504 50.524 60.000 30.000 10.587 30.000 100.022 110.077 90.921 10.928 20.132 90.670 40.759 10.652 10.862 70.091 100.000 10.662 30.072 150.000 120.000 40.000 10.496 10.852 20.752 40.152 30.743 10.953 10.301 30.625 30.053 110.913 10.399 10.452 40.000 10.000 70.000 30.742 20.000 40.000 70.000 10.694 20.643 40.444 60.784 70.000 80.000 10.571 10.614 30.491 40.938 10.559 100.357 50.107 70.404 10.000 10.796 20.688 60.148 80.186 10.629 40.827 10.000 10.558 110.198 40.000 70.000 10.723 20.000 20.000 10.833 10.619 10.609 20.478 40.617 10.959 40.370 30.597 80.737 20.191 50.752 20.000 10.118 10.853 10.925 20.670 130.000 10.831 30.000 160.873 30.000 10.699 10.005 110.360 10.723 30.235 12
L3DETR-ScanNet_2000.336 70.533 100.279 50.155 90.508 50.073 100.101 160.000 30.058 50.000 10.294 130.233 130.548 40.927 10.788 100.264 20.463 100.000 30.638 110.098 120.014 70.411 110.226 120.525 100.225 80.010 70.397 50.000 10.000 30.192 50.380 130.598 40.000 10.117 50.000 20.883 50.082 70.689 40.000 70.032 160.549 50.417 50.910 50.000 10.000 20.448 80.613 90.000 100.697 60.960 20.759 40.158 20.293 20.883 60.000 10.312 30.583 30.079 40.422 100.068 160.660 70.418 70.298 110.430 100.114 100.526 40.776 30.051 30.679 10.946 60.152 60.000 10.183 80.000 140.211 60.511 90.409 150.565 110.355 70.448 80.512 40.557 20.000 30.000 10.420 80.000 100.007 160.104 60.000 40.125 160.330 20.514 140.146 110.321 120.860 80.174 90.000 10.629 50.075 120.000 120.000 40.000 10.002 90.671 80.712 70.141 60.339 110.856 40.261 110.529 90.067 80.835 50.000 50.369 110.000 10.259 20.000 30.629 50.000 40.487 10.000 10.579 100.646 30.107 160.720 100.122 60.000 10.333 130.505 90.303 90.908 30.503 140.565 20.074 80.324 20.000 10.740 70.661 100.109 130.000 90.427 120.563 160.000 10.579 100.108 70.000 70.000 10.664 50.000 20.000 10.641 70.539 100.416 60.515 20.256 100.940 120.312 50.209 160.620 30.138 110.636 100.000 10.000 120.775 120.861 50.765 110.000 10.801 90.119 110.860 70.000 10.687 20.001 130.192 130.679 80.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
CeCo0.340 60.551 80.247 120.181 50.475 120.057 140.142 110.000 30.000 60.000 10.387 50.463 50.499 90.924 20.774 110.213 50.257 120.000 30.546 140.100 100.006 80.615 10.177 160.534 70.246 50.000 90.400 40.000 10.338 10.006 150.484 40.609 30.000 10.083 100.000 20.873 90.089 50.661 130.000 70.048 140.560 30.408 60.892 70.000 10.000 20.586 10.616 80.000 100.692 70.900 70.721 110.162 10.228 50.860 100.000 10.000 100.575 40.083 30.550 30.347 40.624 120.410 100.360 80.740 20.109 110.321 140.660 70.000 80.121 80.939 120.143 70.000 10.400 10.003 120.190 100.564 50.652 90.615 100.421 30.304 130.579 10.547 40.000 30.000 10.296 130.000 100.030 80.096 70.000 40.916 50.037 120.551 110.171 80.376 70.865 60.286 30.000 10.633 40.102 100.027 80.011 30.000 10.000 100.474 130.742 50.133 70.311 120.824 80.242 120.503 130.068 70.828 80.000 50.429 60.000 10.063 40.000 30.781 10.000 40.000 70.000 10.665 30.633 60.450 50.818 20.000 80.000 10.429 40.532 70.226 120.825 100.510 120.377 40.709 20.079 130.000 10.753 50.683 70.102 150.063 40.401 150.620 130.000 10.619 20.000 130.000 70.000 10.595 120.000 20.000 10.345 130.564 50.411 70.603 10.384 80.945 90.266 100.643 50.367 130.304 10.663 90.000 10.010 70.726 140.767 70.898 30.000 10.784 120.435 10.861 60.000 10.447 110.000 140.257 60.656 100.377 9
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
PTv3 ScanNet2000.393 30.592 30.330 20.216 20.520 30.109 40.108 150.000 30.337 20.000 10.310 110.394 80.494 110.753 80.848 20.256 30.717 70.000 30.842 30.192 30.065 30.449 90.346 30.546 60.190 120.000 90.384 60.000 10.000 30.218 30.505 10.791 20.000 10.136 30.000 20.903 20.073 100.687 60.000 70.168 10.551 40.387 70.941 20.000 10.000 20.397 120.654 30.000 100.714 40.759 140.752 70.118 50.264 40.926 20.000 10.048 50.575 40.000 70.597 10.366 20.755 10.469 10.474 20.798 10.140 90.617 20.692 60.000 80.592 20.971 20.188 30.000 10.133 90.593 20.349 10.650 30.717 70.699 30.455 20.790 20.523 30.636 10.301 10.000 10.622 20.000 100.017 140.259 30.000 40.921 40.337 10.733 20.210 30.514 30.860 80.407 10.000 10.688 20.109 70.000 120.000 40.000 10.151 40.671 80.782 10.115 120.641 20.903 20.349 10.616 40.088 50.832 70.000 50.480 20.000 10.428 10.000 30.497 90.000 40.000 70.000 10.662 40.690 20.612 10.828 10.575 10.000 10.404 60.644 10.325 70.887 40.728 10.009 150.134 60.026 160.000 10.761 30.731 30.172 60.077 30.528 70.727 70.000 10.603 40.220 30.022 30.000 10.740 10.000 20.000 10.661 40.586 20.566 30.436 50.531 50.978 20.457 10.708 30.583 50.141 80.748 30.000 10.026 50.822 30.871 40.879 50.000 10.851 20.405 20.914 10.000 10.682 30.000 140.281 30.738 20.463 6
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
ALS-MinkowskiNetcopyleft0.414 10.610 20.322 30.271 10.542 20.153 20.159 100.000 30.000 60.000 10.404 40.503 30.532 60.672 160.804 50.285 10.888 10.000 30.900 10.226 10.087 20.598 30.342 40.671 10.217 90.087 30.449 30.000 10.000 30.253 20.477 51.000 10.000 10.118 40.000 20.905 10.071 110.710 20.076 10.047 150.665 10.376 80.981 10.000 10.000 20.466 60.632 70.113 30.769 10.956 30.795 10.031 90.314 10.936 10.000 10.390 20.601 10.000 70.458 70.366 20.719 30.440 40.564 10.699 30.314 10.464 60.784 20.200 10.283 50.973 10.142 80.000 10.250 70.285 50.220 50.718 10.752 50.723 20.460 10.248 150.475 90.463 130.000 30.000 10.446 70.021 40.025 90.285 10.000 40.972 10.149 70.769 10.230 20.535 20.879 20.252 60.000 10.693 10.129 20.000 120.000 40.000 10.447 20.958 10.662 90.159 20.598 30.780 110.344 20.646 20.106 40.893 20.135 20.455 30.000 10.194 30.259 10.726 30.475 30.000 70.000 10.741 10.865 10.571 20.817 30.445 30.000 10.506 20.630 20.230 110.916 20.728 10.635 11.000 10.252 50.000 10.804 10.697 50.137 110.043 60.717 10.807 30.000 10.510 130.245 10.000 70.000 10.709 30.000 20.000 10.703 20.572 30.646 10.223 100.531 50.984 10.397 20.813 10.798 10.135 120.800 10.000 10.097 20.832 20.752 80.842 70.000 10.852 10.149 90.846 90.000 10.666 50.359 40.252 70.777 10.690 2
IMFSegNet0.334 80.532 120.251 100.179 60.486 90.041 150.139 120.003 10.283 30.000 10.274 140.191 140.457 130.704 130.795 70.197 80.830 50.000 30.710 80.055 150.064 40.518 50.305 90.458 160.216 110.027 50.284 120.000 10.000 30.044 110.406 90.561 50.000 10.080 110.000 20.873 90.021 140.683 80.000 70.076 80.494 90.363 90.648 150.000 10.000 20.425 90.649 40.000 100.668 110.908 60.740 100.010 140.206 70.862 90.000 10.000 100.560 80.000 70.359 120.237 110.631 110.408 110.411 40.322 140.246 40.439 90.599 120.047 40.213 60.940 100.139 100.000 10.369 40.124 90.188 110.495 100.624 100.626 70.320 130.595 40.495 70.496 100.000 30.000 10.340 110.014 50.032 60.135 50.000 40.903 80.277 50.612 80.196 60.344 110.848 130.260 40.000 10.574 120.073 140.062 40.000 40.000 10.091 50.839 30.776 20.123 110.392 80.756 120.274 50.518 110.029 150.842 30.000 50.357 120.000 10.035 60.000 30.444 110.793 10.245 40.000 10.512 150.512 140.159 140.713 120.000 80.000 10.336 120.484 110.569 20.852 80.615 60.120 110.068 100.228 70.000 10.733 90.773 10.190 40.000 90.608 50.792 40.000 10.597 60.000 130.025 20.000 10.573 160.000 20.000 10.508 100.555 70.363 90.139 110.610 20.947 80.305 60.594 90.527 80.009 160.633 120.000 10.060 30.820 50.604 140.799 80.000 10.799 100.034 130.784 120.000 10.618 60.424 10.134 150.646 120.214 14
GSTran0.334 90.533 110.250 110.179 70.487 80.041 150.139 120.003 10.273 40.000 10.273 150.189 150.465 120.704 130.794 80.198 70.831 40.000 30.712 70.055 150.063 50.518 50.306 80.459 150.217 90.028 40.282 130.000 10.000 30.044 110.405 100.558 60.000 10.080 110.000 20.873 90.020 150.684 70.000 70.075 110.496 80.363 90.651 140.000 10.000 20.425 90.648 50.000 100.669 100.914 50.741 90.009 150.200 80.864 80.000 10.000 100.560 80.000 70.357 130.233 120.633 100.408 110.411 40.320 150.242 50.440 80.598 130.047 40.205 70.940 100.139 100.000 10.372 30.138 80.191 80.495 100.618 120.624 80.321 110.595 40.496 60.499 80.000 30.000 10.340 110.014 50.032 60.136 40.000 40.903 80.279 40.601 90.198 40.345 100.849 110.260 40.000 10.573 130.072 150.060 50.000 40.000 10.089 60.838 40.775 30.125 100.381 100.752 130.274 50.517 120.032 140.841 40.000 50.354 130.000 10.047 50.000 30.439 120.787 20.252 30.000 10.512 150.507 150.158 150.717 110.000 80.000 10.337 110.483 120.570 10.853 70.614 70.121 100.070 90.229 60.000 10.732 100.773 10.193 30.000 90.606 60.791 50.000 10.593 80.000 130.010 50.000 10.574 150.000 20.000 10.507 110.554 80.361 100.136 120.608 30.948 70.304 70.593 100.533 70.011 150.634 110.000 10.060 30.821 40.613 120.797 90.000 10.799 100.036 120.782 130.000 10.609 70.423 20.133 160.647 110.213 15
OA-CNN-L_ScanNet2000.333 100.558 40.269 80.124 120.448 140.080 80.272 40.000 30.000 60.000 10.342 70.515 20.524 70.713 120.789 90.158 110.384 110.000 30.806 50.125 60.000 90.496 70.332 60.498 130.227 70.024 60.474 20.000 10.003 20.071 80.487 30.000 100.000 10.110 70.000 20.876 70.013 160.703 30.000 70.076 80.473 120.355 110.906 60.000 10.000 20.476 50.706 10.000 100.672 90.835 120.748 80.015 130.223 60.860 100.000 10.000 100.572 60.000 70.509 60.313 70.662 40.398 130.396 70.411 110.276 20.527 30.711 50.000 80.076 120.946 60.166 50.000 10.022 100.160 60.183 120.493 120.699 80.637 50.403 40.330 120.406 120.526 50.024 20.000 10.392 100.000 100.016 150.000 110.196 30.915 60.112 110.557 100.197 50.352 90.877 30.000 110.000 10.592 110.103 90.000 120.067 10.000 10.089 60.735 70.625 110.130 90.568 60.836 70.271 70.534 80.043 120.799 100.001 40.445 50.000 10.000 70.024 20.661 40.000 40.262 20.000 10.591 70.517 120.373 80.788 60.021 70.000 10.455 30.517 80.320 80.823 110.200 160.001 160.150 50.100 110.000 10.736 80.668 90.103 140.052 50.662 20.720 80.000 10.602 50.112 60.002 60.000 10.637 80.000 20.000 10.621 90.569 40.398 80.412 60.234 110.949 60.363 40.492 140.495 100.251 40.665 80.000 10.001 110.805 70.833 60.794 100.000 10.821 50.314 50.843 100.000 10.560 100.245 50.262 50.713 40.370 10
PonderV2 ScanNet2000.346 50.552 70.270 70.175 80.497 70.070 110.239 60.000 30.000 60.000 10.232 160.412 70.584 30.842 30.804 50.212 60.540 90.000 30.433 150.106 90.000 90.590 40.290 110.548 50.243 60.000 90.356 100.000 10.000 30.062 90.398 120.441 80.000 10.104 90.000 20.888 40.076 90.682 90.030 30.094 60.491 100.351 120.869 90.000 10.063 10.403 110.700 20.000 100.660 120.881 80.761 30.050 80.186 90.852 120.000 10.007 80.570 70.100 20.565 20.326 60.641 90.431 50.290 130.621 50.259 30.408 100.622 90.125 20.082 110.950 40.179 40.000 10.263 50.424 40.193 70.558 60.880 20.545 120.375 60.727 30.445 110.499 80.000 30.000 10.475 60.002 80.034 50.083 80.000 40.924 30.290 30.636 60.115 130.400 50.874 40.186 80.000 10.611 70.128 30.113 20.000 40.000 10.000 100.584 110.636 100.103 130.385 90.843 60.283 40.603 60.080 60.825 90.000 50.377 90.000 10.000 70.000 30.457 100.000 40.000 70.000 10.574 110.608 80.481 30.792 40.394 40.000 10.357 90.503 100.261 100.817 120.504 130.304 70.472 40.115 100.000 10.750 60.677 80.202 20.000 90.509 80.729 60.000 10.519 120.000 130.000 70.000 10.620 110.000 20.000 10.660 60.560 60.486 50.384 70.346 90.952 50.247 130.667 40.436 110.269 30.691 60.000 10.010 70.787 90.889 30.880 40.000 10.810 70.336 40.860 70.000 10.606 80.009 90.248 80.681 60.392 8
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
LGroundpermissive0.272 140.485 140.184 140.106 140.476 110.077 90.218 70.000 30.000 60.000 10.547 10.295 100.540 50.746 90.745 140.058 150.112 150.005 10.658 100.077 140.000 90.322 130.178 150.512 110.190 120.199 20.277 140.000 10.000 30.173 60.399 110.000 100.000 10.039 150.000 20.858 140.085 60.676 110.002 50.103 50.498 70.323 130.703 110.000 10.000 20.296 140.549 110.216 10.702 50.768 130.718 130.028 100.092 150.786 150.000 10.000 100.453 150.022 50.251 160.252 90.572 140.348 140.321 100.514 60.063 130.279 150.552 140.000 80.019 150.932 140.132 150.000 10.000 120.000 140.156 160.457 140.623 110.518 130.265 150.358 110.381 140.395 140.000 30.000 10.127 160.012 70.051 10.000 110.000 40.886 130.014 130.437 160.179 70.244 140.826 140.000 110.000 10.599 90.136 10.085 30.000 40.000 10.000 100.565 120.612 130.143 50.207 140.566 140.232 140.446 140.127 20.708 140.000 50.384 80.000 10.000 70.000 30.402 130.000 40.059 50.000 10.525 140.566 100.229 110.659 140.000 80.000 10.265 140.446 130.147 150.720 160.597 80.066 130.000 110.187 80.000 10.726 120.467 160.134 120.000 90.413 140.629 120.000 10.363 150.055 90.022 30.000 10.626 100.000 20.000 10.323 140.479 160.154 150.117 140.028 150.901 140.243 140.415 150.295 160.143 70.610 150.000 10.000 120.777 110.397 160.324 150.000 10.778 140.179 80.702 150.000 10.274 160.404 30.233 90.622 140.398 7
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
Minkowski 34Dpermissive0.253 150.463 150.154 160.102 150.381 160.084 70.134 140.000 30.000 60.000 10.386 60.141 160.279 160.737 110.703 150.014 160.164 140.000 30.663 90.092 130.000 90.224 140.291 100.531 80.056 160.000 90.242 150.000 10.000 30.013 140.331 150.000 100.000 10.035 160.001 10.858 140.059 120.650 150.000 70.056 130.353 150.299 140.670 120.000 10.000 20.284 150.484 140.071 80.594 150.720 150.710 140.027 110.068 160.813 130.000 10.005 90.492 130.164 10.274 150.111 150.571 150.307 160.293 120.307 160.150 80.163 160.531 150.002 70.545 40.932 140.093 160.000 10.000 120.002 130.159 140.368 160.581 140.440 160.228 160.406 90.282 160.294 150.000 30.000 10.189 150.060 20.036 40.000 110.000 40.897 110.000 160.525 130.025 160.205 160.771 160.000 110.000 10.593 100.108 80.044 60.000 40.000 10.000 100.282 160.589 140.094 150.169 150.466 160.227 150.419 160.125 30.757 130.002 30.334 150.000 10.000 70.000 30.357 140.000 40.000 70.000 10.582 90.513 130.337 100.612 160.000 80.000 10.250 150.352 160.136 160.724 150.655 40.280 80.000 110.046 150.000 10.606 160.559 140.159 70.102 20.445 90.655 90.000 10.310 160.117 50.000 70.000 10.581 140.026 10.000 10.265 160.483 150.084 160.097 160.044 140.865 160.142 160.588 110.351 140.272 20.596 160.000 10.003 100.622 150.720 90.096 160.000 10.771 150.016 140.772 140.000 10.302 140.194 70.214 110.621 150.197 16
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
AWCS0.305 130.508 130.225 130.142 100.463 130.063 120.195 80.000 30.000 60.000 10.467 30.551 10.504 80.773 60.764 130.142 130.029 160.000 30.626 120.100 100.000 90.360 120.179 140.507 120.137 140.006 80.300 110.000 10.000 30.172 70.364 140.512 70.000 10.056 130.000 20.865 130.093 40.634 160.000 70.071 120.396 140.296 150.876 80.000 10.000 20.373 130.436 150.063 90.749 20.877 90.721 110.131 40.124 130.804 140.000 10.000 100.515 110.010 60.452 90.252 90.578 130.417 80.179 160.484 80.171 70.337 130.606 110.000 80.115 90.937 130.142 80.000 10.008 110.000 140.157 150.484 130.402 160.501 140.339 80.553 70.529 20.478 120.000 30.000 10.404 90.001 90.022 110.077 90.000 40.894 120.219 60.628 70.093 140.305 130.886 10.233 70.000 10.603 80.112 50.023 90.000 40.000 10.000 100.741 60.664 80.097 140.253 130.782 100.264 100.523 100.154 10.707 150.000 50.411 70.000 10.000 70.000 30.332 150.000 40.000 70.000 10.602 60.595 90.185 120.656 150.159 50.000 10.355 100.424 140.154 140.729 140.516 110.220 90.620 30.084 120.000 10.707 130.651 120.173 50.014 80.381 160.582 140.000 10.619 20.049 110.000 70.000 10.702 40.000 20.000 10.302 150.489 140.317 120.334 80.392 70.922 130.254 120.533 130.394 120.129 140.613 140.000 10.000 120.820 50.649 100.749 120.000 10.782 130.282 60.863 50.000 10.288 150.006 100.220 100.633 130.542 3
CSC-Pretrainpermissive0.249 160.455 160.171 150.079 160.418 150.059 130.186 90.000 30.000 60.000 10.335 90.250 120.316 150.766 70.697 160.142 130.170 130.003 20.553 130.112 80.097 10.201 150.186 130.476 140.081 150.000 90.216 160.000 10.000 30.001 160.314 160.000 100.000 10.055 140.000 20.832 160.094 30.659 140.002 50.076 80.310 160.293 160.664 130.000 10.000 20.175 160.634 60.130 20.552 160.686 160.700 160.076 70.110 140.770 160.000 10.000 100.430 160.000 70.319 140.166 140.542 160.327 150.205 150.332 130.052 140.375 120.444 160.000 80.012 160.930 160.203 20.000 10.000 120.046 110.175 130.413 150.592 130.471 150.299 140.152 160.340 150.247 160.000 30.000 10.225 140.058 30.037 30.000 110.207 20.862 150.014 130.548 120.033 150.233 150.816 150.000 110.000 10.542 140.123 40.121 10.019 20.000 10.000 100.463 150.454 160.045 160.128 160.557 150.235 130.441 150.063 90.484 160.000 50.308 160.000 10.000 70.000 30.318 160.000 40.000 70.000 10.545 130.543 110.164 130.734 80.000 80.000 10.215 160.371 150.198 130.743 130.205 150.062 140.000 110.079 130.000 10.683 150.547 150.142 100.000 90.441 100.579 150.000 10.464 140.098 80.041 10.000 10.590 130.000 20.000 10.373 120.494 130.174 140.105 150.001 160.895 150.222 150.537 120.307 150.180 60.625 130.000 10.000 120.591 160.609 130.398 140.000 10.766 160.014 150.638 160.000 10.377 130.004 120.206 120.609 160.465 5
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021


ScanNet200 3D Semantic Instance Benchmark

This table lists the benchmark results for the ScanNet200 3D semantic instance scenario.




Method Infoavg ap 25%head ap 25%common ap 25%tail ap 25%alarm clockarmchairbackpackbagballbarbasketbathroom cabinetbathroom counterbathroom stallbathroom stall doorbathroom vanitybathtubbedbenchbicyclebinblackboardblanketblindsboardbookbookshelfbottlebowlboxbroombucketbulletin boardcabinetcalendarcandlecartcase of water bottlescd caseceilingceiling lightchairclockclosetcloset doorcloset rodcloset wallclothesclothes dryercoat rackcoffee kettlecoffee makercoffee tablecolumncomputer towercontainercopiercouchcountercratecupcurtaincushiondecorationdeskdining tabledish rackdishwasherdividerdoordoorframedresserdumbbelldustpanend tablefanfile cabinetfire alarmfire extinguisherfireplacefolded chairfurnitureguitarguitar casehair dryerhandicap barhatheadphonesironing boardjacketkeyboardkeyboard pianokitchen cabinetkitchen counterladderlamplaptoplaundry basketlaundry detergentlaundry hamperledgelightlight switchluggagemachinemailboxmatmattressmicrowavemini fridgemirrormonitormousemusic standnightstandobjectoffice chairottomanovenpaperpaper bagpaper cutterpaper towel dispenserpaper towel rollpersonpianopicturepillarpillowpipeplantplateplungerposterpotted plantpower outletpower stripprinterprojectorprojector screenpurserackradiatorrailrange hoodrecycling binrefrigeratorscaleseatshelfshoeshowershower curtainshower curtain rodshower doorshower floorshower headshower wallsignsinksoap dishsoap dispensersofa chairspeakerstair railstairsstandstoolstorage binstorage containerstorage organizerstovestructurestuffed animalsuitcasetabletelephonetissue boxtoastertoaster oventoilettoilet papertoilet paper dispensertoilet paper holdertoilet seat cover dispensertoweltrash bintrash cantraytubetvtv standvacuum cleanerventwardrobewashing machinewater bottlewater coolerwater pitcherwhiteboardwindowwindowsill
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
TD3D Scannet200permissive0.379 20.603 20.306 20.190 20.635 20.073 20.500 10.000 10.000 10.000 10.495 30.735 20.275 51.000 10.979 20.590 20.000 40.021 20.000 30.146 30.000 20.356 20.173 50.795 10.226 20.000 10.173 20.000 10.000 20.226 20.390 20.000 20.000 10.250 10.000 10.706 20.061 30.885 10.093 20.186 20.259 40.200 10.667 10.000 20.000 10.667 20.825 10.250 40.834 41.000 10.958 10.553 10.111 30.748 10.220 20.051 20.866 20.792 10.390 50.045 50.800 20.302 50.517 10.533 30.113 20.427 10.843 20.000 20.458 10.600 10.000 10.101 20.000 10.259 10.717 20.500 20.615 20.520 20.526 20.457 10.270 40.000 10.000 10.400 20.088 20.294 20.181 20.000 11.000 10.400 10.710 50.103 30.477 50.905 20.061 20.000 10.906 20.102 20.232 10.125 20.000 20.003 20.792 31.000 10.000 20.102 30.125 40.559 50.523 30.075 20.715 10.000 20.424 50.000 10.396 20.250 10.638 10.000 10.000 20.000 10.622 50.833 20.221 10.970 10.250 20.038 10.260 20.415 10.125 21.000 11.000 10.857 20.000 20.908 10.012 10.869 30.836 10.635 10.111 10.625 11.000 10.020 20.510 10.003 30.009 21.000 10.778 10.000 10.000 10.370 30.755 10.288 20.333 30.274 21.000 10.557 10.731 20.456 20.433 30.769 50.000 10.000 20.621 41.000 10.458 40.000 10.196 20.817 10.000 10.472 10.222 30.205 50.689 20.274 3
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
LGround Inst.permissive0.314 30.529 30.225 30.155 30.578 50.010 30.500 10.000 10.000 10.000 10.515 20.556 30.696 11.000 10.927 30.400 30.083 30.000 31.000 10.252 10.000 20.167 30.350 20.731 20.067 30.000 10.123 40.000 10.000 20.036 30.372 30.000 20.000 10.250 10.000 10.569 40.031 50.810 30.000 30.000 40.630 10.183 20.278 30.000 20.000 10.582 40.589 50.500 20.863 31.000 10.940 20.000 40.144 10.716 30.000 30.000 30.484 30.000 30.500 30.400 30.798 30.500 20.278 40.750 10.093 30.166 40.783 30.000 20.200 20.400 20.000 10.000 30.000 10.219 20.539 30.500 20.578 30.413 30.181 50.457 20.375 20.000 10.000 10.050 50.000 40.077 40.000 30.000 10.500 50.000 50.743 30.250 20.488 40.846 30.000 30.000 10.800 30.069 30.000 30.000 30.000 20.000 31.000 10.607 40.000 20.200 10.500 10.694 20.528 20.063 30.659 20.000 20.594 20.000 10.000 30.000 20.571 20.000 10.000 20.000 10.716 40.647 50.221 20.857 40.000 30.000 30.217 30.346 30.071 50.530 51.000 10.429 30.000 20.286 30.000 30.826 50.706 30.208 40.000 30.250 40.744 50.000 30.500 20.042 10.000 30.000 20.746 30.000 10.000 10.517 10.625 30.085 50.333 30.000 41.000 10.378 40.533 50.376 40.042 50.814 30.000 10.000 20.765 31.000 10.600 30.000 10.000 40.667 30.000 10.472 10.333 20.337 30.605 30.305 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.permissive0.280 40.488 40.192 50.124 40.593 40.010 40.500 10.000 10.000 10.000 10.447 40.535 40.445 31.000 10.861 40.400 30.225 20.000 30.000 30.142 40.000 20.074 40.342 30.467 50.067 30.000 10.119 50.000 10.000 20.000 40.337 50.000 20.000 10.000 40.000 10.506 50.070 20.804 40.000 30.000 40.333 30.172 30.150 50.000 20.000 10.479 50.745 30.000 50.830 51.000 10.904 30.167 20.090 40.732 20.000 30.000 30.443 40.000 30.500 30.542 10.772 50.396 40.077 50.385 40.044 40.118 50.777 40.000 20.000 40.200 30.000 10.000 30.000 10.148 40.502 40.500 20.419 40.159 50.281 40.404 50.317 30.000 10.000 10.200 30.000 40.077 30.000 30.000 10.750 30.200 30.715 40.021 40.551 20.828 50.000 30.000 10.743 40.059 50.000 30.000 30.000 20.000 30.125 50.648 30.000 20.191 20.500 10.669 40.502 40.000 50.568 40.000 20.516 40.000 10.000 30.000 20.305 50.000 10.000 20.000 10.825 10.833 20.021 50.918 20.000 30.000 30.191 40.346 40.100 40.981 31.000 10.286 40.000 20.000 50.000 30.868 40.648 50.292 30.000 30.375 31.000 10.000 30.500 20.000 40.333 10.000 20.538 50.000 10.000 10.213 50.518 40.098 40.528 10.250 30.997 30.284 50.677 30.398 30.167 40.790 40.000 10.000 20.618 50.903 50.200 50.000 10.333 10.333 40.000 10.442 30.083 40.213 40.587 40.131 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.275 50.466 50.218 40.110 50.625 30.007 50.500 10.000 10.000 10.000 10.000 50.222 50.377 41.000 10.661 50.400 30.000 40.000 30.000 30.119 50.000 20.000 50.277 40.685 40.067 30.000 10.132 30.000 10.000 20.000 40.367 40.000 20.000 10.000 40.000 10.591 30.055 40.783 50.000 30.014 30.500 20.161 40.278 30.000 20.000 10.667 20.768 20.500 20.866 21.000 10.829 50.000 40.019 50.555 50.000 30.000 30.305 50.000 30.750 10.200 40.783 40.429 30.395 30.677 20.020 50.286 30.584 50.000 20.000 40.115 50.000 10.000 30.000 10.145 50.423 50.500 20.364 50.369 40.571 10.448 30.206 50.000 10.000 10.200 30.106 10.065 50.000 30.000 10.750 30.200 30.774 20.000 50.501 30.841 40.000 30.000 10.692 50.063 40.000 30.000 30.000 20.000 30.500 40.649 20.000 20.084 40.125 40.719 10.413 50.004 40.450 50.000 20.638 10.000 10.000 30.000 20.505 30.000 10.000 20.000 10.727 30.833 20.221 20.779 50.000 30.000 30.168 50.311 50.125 20.571 40.500 50.143 50.000 20.250 40.000 30.869 20.667 40.162 50.000 30.250 41.000 10.000 30.500 20.000 40.000 30.000 20.689 40.000 10.000 10.312 40.383 50.114 30.333 30.000 40.997 30.420 30.613 40.212 50.500 20.819 20.000 10.000 20.768 21.000 10.918 10.000 10.000 40.278 50.000 10.333 50.000 50.353 20.546 50.258 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Mask3D Scannet2000.445 10.653 10.392 10.254 10.648 10.097 10.125 50.000 10.000 10.000 10.657 10.971 10.451 21.000 11.000 10.640 10.500 10.045 11.000 10.241 20.409 10.363 10.440 10.686 30.300 10.000 10.201 10.000 10.009 10.290 10.556 11.000 10.000 10.063 30.000 10.830 10.573 10.844 20.333 10.204 10.058 50.158 50.552 20.056 10.000 11.000 10.725 40.750 10.927 11.000 10.888 40.042 30.120 20.615 40.226 10.250 10.890 10.792 10.677 20.510 20.818 10.699 10.512 20.167 50.125 10.315 20.943 10.309 10.017 30.200 30.000 10.188 10.000 10.183 30.815 11.000 10.827 10.741 10.442 30.414 40.600 10.000 10.000 10.458 10.049 30.321 10.381 10.000 10.908 20.400 10.841 10.260 10.710 10.966 10.265 10.000 10.924 10.152 10.025 20.500 10.027 10.028 11.000 10.556 50.016 10.080 50.500 10.694 30.608 10.084 10.604 30.194 10.538 30.000 10.500 10.000 20.354 40.000 11.000 10.000 10.761 20.930 10.053 40.890 31.000 10.008 20.262 10.358 21.000 11.000 10.792 40.966 11.000 10.765 20.004 20.930 10.780 20.330 20.027 20.625 10.974 40.050 10.412 50.021 20.000 30.000 20.778 10.000 10.000 10.493 20.746 20.454 10.335 20.396 10.930 50.551 21.000 10.552 10.606 10.853 10.000 10.004 10.806 11.000 10.727 20.000 10.042 30.745 20.000 10.399 40.391 10.630 10.721 10.619 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023


ScanNet Benchmark

3D Semantic Label Benchmark

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
PTv3-PPT-ALCcopyleft0.798 10.911 100.812 210.854 70.770 130.856 140.555 150.943 10.660 250.735 20.979 10.606 70.492 10.792 40.934 30.841 20.819 50.716 80.947 100.906 10.822 1
PTv3 ScanNet0.794 20.941 30.813 200.851 90.782 60.890 30.597 10.916 50.696 90.713 50.979 10.635 20.384 30.793 30.907 100.821 50.790 330.696 140.967 30.903 20.805 2
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
DITR ScanNet0.793 30.811 400.852 20.889 10.774 100.907 10.592 20.927 30.719 10.718 30.961 170.652 10.348 120.817 10.927 50.795 100.824 20.749 10.948 90.887 70.771 11
PonderV20.785 40.978 10.800 300.833 260.788 40.853 190.545 190.910 80.713 20.705 60.979 10.596 90.390 20.769 160.832 440.821 50.792 320.730 20.975 10.897 50.785 6
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
Mix3Dpermissive0.781 50.964 20.855 10.843 180.781 70.858 130.575 70.831 360.685 150.714 40.979 10.594 100.310 300.801 20.892 180.841 20.819 50.723 50.940 150.887 70.725 28
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 60.861 220.818 150.836 230.790 30.875 50.576 60.905 90.704 60.739 10.969 110.611 30.349 110.756 260.958 10.702 490.805 160.708 90.916 360.898 40.801 3
TTT-KD0.773 70.646 950.818 150.809 380.774 100.878 40.581 30.943 10.687 130.704 70.978 50.607 60.336 180.775 120.912 80.838 40.823 30.694 150.967 30.899 30.794 5
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ResLFE_HDS0.772 80.939 40.824 70.854 70.771 120.840 340.564 110.900 110.686 140.677 140.961 170.537 350.348 120.769 160.903 120.785 140.815 80.676 260.939 160.880 130.772 10
PPT-SpUNet-Joint0.766 90.932 50.794 360.829 280.751 260.854 170.540 230.903 100.630 380.672 180.963 150.565 250.357 90.788 50.900 140.737 290.802 170.685 200.950 70.887 70.780 7
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormerpermissive0.766 90.925 70.808 260.849 110.786 50.846 290.566 100.876 190.690 110.674 160.960 190.576 210.226 700.753 280.904 110.777 160.815 80.722 60.923 310.877 160.776 9
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
OccuSeg+Semantic0.764 110.758 610.796 340.839 210.746 290.907 10.562 120.850 280.680 170.672 180.978 50.610 40.335 200.777 100.819 480.847 10.830 10.691 170.972 20.885 100.727 26
CU-Hybrid Net0.764 110.924 80.819 130.840 200.757 210.853 190.580 40.848 290.709 40.643 280.958 230.587 150.295 370.753 280.884 220.758 230.815 80.725 40.927 270.867 250.743 19
O-CNNpermissive0.762 130.924 80.823 80.844 170.770 130.852 210.577 50.847 310.711 30.640 320.958 230.592 110.217 760.762 210.888 190.758 230.813 120.726 30.932 250.868 240.744 18
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
DiffSegNet0.758 140.725 780.789 410.843 180.762 170.856 140.562 120.920 40.657 280.658 220.958 230.589 130.337 170.782 60.879 230.787 120.779 390.678 220.926 290.880 130.799 4
DTC0.757 150.843 280.820 110.847 140.791 20.862 110.511 370.870 210.707 50.652 240.954 380.604 80.279 470.760 220.942 20.734 300.766 480.701 130.884 580.874 220.736 20
OA-CNN-L_ScanNet200.756 160.783 470.826 60.858 50.776 80.837 370.548 180.896 150.649 300.675 150.962 160.586 160.335 200.771 150.802 520.770 190.787 350.691 170.936 190.880 130.761 13
PNE0.755 170.786 450.835 50.834 250.758 190.849 240.570 90.836 350.648 310.668 200.978 50.581 200.367 70.683 380.856 320.804 70.801 210.678 220.961 50.889 60.716 33
P. Hermosilla: Point Neighborhood Embeddings.
ConDaFormer0.755 170.927 60.822 90.836 230.801 10.849 240.516 340.864 250.651 290.680 130.958 230.584 180.282 440.759 240.855 340.728 320.802 170.678 220.880 630.873 230.756 15
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
DMF-Net0.752 190.906 130.793 380.802 440.689 430.825 500.556 140.867 220.681 160.602 480.960 190.555 310.365 80.779 90.859 290.747 260.795 290.717 70.917 350.856 340.764 12
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
PointTransformerV20.752 190.742 680.809 250.872 20.758 190.860 120.552 160.891 170.610 450.687 80.960 190.559 290.304 330.766 190.926 60.767 200.797 250.644 370.942 130.876 190.722 30
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
BPNetcopyleft0.749 210.909 110.818 150.811 360.752 240.839 360.485 510.842 320.673 200.644 270.957 280.528 410.305 320.773 130.859 290.788 110.818 70.693 160.916 360.856 340.723 29
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer0.749 210.793 430.790 390.807 400.750 280.856 140.524 300.881 180.588 570.642 310.977 90.591 120.274 500.781 80.929 40.804 70.796 260.642 380.947 100.885 100.715 34
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
MSP0.748 230.623 980.804 280.859 40.745 300.824 520.501 410.912 70.690 110.685 100.956 290.567 240.320 270.768 180.918 70.720 370.802 170.676 260.921 330.881 120.779 8
StratifiedFormerpermissive0.747 240.901 140.803 290.845 160.757 210.846 290.512 360.825 390.696 90.645 260.956 290.576 210.262 610.744 330.861 280.742 270.770 460.705 110.899 480.860 310.734 21
Xin Lai*, Jianhui Liu*, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
VMNetpermissive0.746 250.870 200.838 30.858 50.729 350.850 230.501 410.874 200.587 580.658 220.956 290.564 260.299 350.765 200.900 140.716 400.812 130.631 430.939 160.858 320.709 35
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
Virtual MVFusion0.746 250.771 550.819 130.848 130.702 410.865 100.397 880.899 120.699 70.664 210.948 590.588 140.330 220.746 320.851 380.764 210.796 260.704 120.935 200.866 260.728 24
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
DiffSeg3D20.745 270.725 780.814 190.837 220.751 260.831 440.514 350.896 150.674 190.684 110.960 190.564 260.303 340.773 130.820 470.713 430.798 240.690 190.923 310.875 200.757 14
Retro-FPN0.744 280.842 290.800 300.767 580.740 310.836 390.541 210.914 60.672 210.626 360.958 230.552 320.272 520.777 100.886 210.696 500.801 210.674 290.941 140.858 320.717 31
Peng Xiang*, Xin Wen*, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
EQ-Net0.743 290.620 990.799 330.849 110.730 340.822 540.493 480.897 130.664 220.681 120.955 320.562 280.378 40.760 220.903 120.738 280.801 210.673 300.907 400.877 160.745 16
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
MVF-GNN0.743 290.731 730.810 240.726 650.775 90.843 320.528 290.897 130.679 180.674 160.954 380.583 190.322 260.782 60.720 670.802 90.785 360.707 100.935 200.863 280.745 16
SAT0.742 310.860 230.765 530.819 310.769 150.848 260.533 250.829 370.663 230.631 350.955 320.586 160.274 500.753 280.896 160.729 310.760 540.666 320.921 330.855 360.733 22
LRPNet0.742 310.816 370.806 270.807 400.752 240.828 480.575 70.839 340.699 70.637 330.954 380.520 430.320 270.755 270.834 420.760 220.772 430.676 260.915 380.862 290.717 31
LargeKernel3D0.739 330.909 110.820 110.806 420.740 310.852 210.545 190.826 380.594 560.643 280.955 320.541 340.263 600.723 360.858 310.775 180.767 470.678 220.933 230.848 410.694 40
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN0.736 340.776 510.790 390.851 90.754 230.854 170.491 500.866 230.596 550.686 90.955 320.536 360.342 150.624 530.869 250.787 120.802 170.628 440.927 270.875 200.704 37
MinkowskiNetpermissive0.736 340.859 240.818 150.832 270.709 390.840 340.521 320.853 270.660 250.643 280.951 490.544 330.286 420.731 340.893 170.675 580.772 430.683 210.874 690.852 390.727 26
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 360.890 160.837 40.864 30.726 360.873 60.530 280.824 400.489 900.647 250.978 50.609 50.336 180.624 530.733 610.758 230.776 410.570 680.949 80.877 160.728 24
SparseConvNet0.725 370.647 940.821 100.846 150.721 370.869 70.533 250.754 610.603 510.614 400.955 320.572 230.325 240.710 370.870 240.724 350.823 30.628 440.934 220.865 270.683 43
PointTransformer++0.725 370.727 770.811 230.819 310.765 160.841 330.502 400.814 450.621 410.623 380.955 320.556 300.284 430.620 550.866 260.781 150.757 580.648 350.932 250.862 290.709 35
MatchingNet0.724 390.812 390.812 210.810 370.735 330.834 410.495 470.860 260.572 640.602 480.954 380.512 450.280 460.757 250.845 400.725 340.780 380.606 540.937 180.851 400.700 39
INS-Conv-semantic0.717 400.751 640.759 570.812 350.704 400.868 80.537 240.842 320.609 470.608 440.953 430.534 380.293 380.616 560.864 270.719 390.793 300.640 390.933 230.845 450.663 48
PointMetaBase0.714 410.835 300.785 420.821 290.684 450.846 290.531 270.865 240.614 420.596 520.953 430.500 480.246 660.674 390.888 190.692 510.764 500.624 460.849 850.844 460.675 45
contrastBoundarypermissive0.705 420.769 580.775 470.809 380.687 440.820 570.439 760.812 460.661 240.591 540.945 670.515 440.171 950.633 500.856 320.720 370.796 260.668 310.889 550.847 420.689 41
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 430.774 530.800 300.793 490.760 180.847 280.471 550.802 490.463 970.634 340.968 130.491 510.271 540.726 350.910 90.706 450.815 80.551 800.878 640.833 470.570 80
RFCR0.702 440.889 170.745 670.813 340.672 480.818 620.493 480.815 440.623 390.610 420.947 610.470 600.249 650.594 590.848 390.705 460.779 390.646 360.892 530.823 530.611 63
Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma: Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning. CVPR2021
One Thing One Click0.701 450.825 340.796 340.723 660.716 380.832 430.433 780.816 420.634 360.609 430.969 110.418 860.344 140.559 710.833 430.715 410.808 150.560 740.902 450.847 420.680 44
JSENetpermissive0.699 460.881 190.762 540.821 290.667 490.800 740.522 310.792 520.613 430.607 450.935 870.492 500.205 810.576 640.853 360.691 520.758 560.652 340.872 720.828 500.649 52
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
One-Thing-One-Click0.693 470.743 670.794 360.655 890.684 450.822 540.497 460.719 710.622 400.617 390.977 90.447 730.339 160.750 310.664 790.703 480.790 330.596 580.946 120.855 360.647 53
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 480.732 720.772 480.786 500.677 470.866 90.517 330.848 290.509 830.626 360.952 470.536 360.225 720.545 770.704 700.689 550.810 140.564 730.903 440.854 380.729 23
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 490.884 180.754 610.795 470.647 560.818 620.422 800.802 490.612 440.604 460.945 670.462 630.189 890.563 700.853 360.726 330.765 490.632 420.904 420.821 560.606 67
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 500.704 840.741 710.754 620.656 510.829 460.501 410.741 660.609 470.548 610.950 530.522 420.371 50.633 500.756 560.715 410.771 450.623 470.861 800.814 590.658 49
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 510.866 210.748 640.819 310.645 580.794 770.450 660.802 490.587 580.604 460.945 670.464 620.201 840.554 730.840 410.723 360.732 690.602 560.907 400.822 550.603 70
DGNet0.684 520.712 830.784 430.782 540.658 500.835 400.499 450.823 410.641 330.597 510.950 530.487 530.281 450.575 650.619 830.647 710.764 500.620 490.871 750.846 440.688 42
VACNN++0.684 520.728 760.757 600.776 550.690 420.804 720.464 600.816 420.577 630.587 550.945 670.508 470.276 490.671 400.710 680.663 630.750 620.589 630.881 610.832 490.653 51
KP-FCNN0.684 520.847 270.758 590.784 520.647 560.814 650.473 540.772 550.605 490.594 530.935 870.450 710.181 920.587 600.805 510.690 530.785 360.614 500.882 600.819 570.632 59
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
PointContrast_LA_SEM0.683 550.757 620.784 430.786 500.639 600.824 520.408 830.775 540.604 500.541 630.934 910.532 390.269 560.552 740.777 540.645 740.793 300.640 390.913 390.824 520.671 46
Superpoint Network0.683 550.851 260.728 750.800 460.653 530.806 700.468 570.804 470.572 640.602 480.946 640.453 700.239 690.519 830.822 450.689 550.762 530.595 600.895 510.827 510.630 60
VI-PointConv0.676 570.770 570.754 610.783 530.621 640.814 650.552 160.758 590.571 660.557 590.954 380.529 400.268 580.530 800.682 740.675 580.719 720.603 550.888 560.833 470.665 47
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 580.789 440.748 640.763 600.635 620.814 650.407 850.747 630.581 620.573 560.950 530.484 540.271 540.607 570.754 570.649 680.774 420.596 580.883 590.823 530.606 67
SALANet0.670 590.816 370.770 510.768 570.652 540.807 690.451 630.747 630.659 270.545 620.924 980.473 590.149 1050.571 670.811 500.635 770.746 630.623 470.892 530.794 710.570 80
O3DSeg0.668 600.822 350.771 500.496 1090.651 550.833 420.541 210.761 580.555 720.611 410.966 140.489 520.370 60.388 1020.580 860.776 170.751 600.570 680.956 60.817 580.646 54
PointConvpermissive0.666 610.781 480.759 570.699 740.644 590.822 540.475 530.779 530.564 690.504 800.953 430.428 800.203 830.586 620.754 570.661 640.753 590.588 640.902 450.813 610.642 55
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 610.703 850.781 450.751 640.655 520.830 450.471 550.769 560.474 930.537 650.951 490.475 580.279 470.635 480.698 730.675 580.751 600.553 790.816 920.806 630.703 38
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PPCNN++permissive0.663 630.746 650.708 780.722 670.638 610.820 570.451 630.566 990.599 530.541 630.950 530.510 460.313 290.648 450.819 480.616 820.682 870.590 620.869 760.810 620.656 50
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 640.778 490.702 810.806 420.619 650.813 680.468 570.693 790.494 860.524 720.941 790.449 720.298 360.510 850.821 460.675 580.727 710.568 710.826 900.803 650.637 57
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 650.698 870.743 690.650 900.564 820.820 570.505 390.758 590.631 370.479 840.945 670.480 560.226 700.572 660.774 550.690 530.735 670.614 500.853 840.776 860.597 73
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 660.752 630.734 730.664 870.583 770.815 640.399 870.754 610.639 340.535 670.942 770.470 600.309 310.665 410.539 890.650 670.708 770.635 410.857 830.793 730.642 55
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 670.778 490.731 740.699 740.577 780.829 460.446 680.736 670.477 920.523 740.945 670.454 670.269 560.484 920.749 600.618 800.738 640.599 570.827 890.792 760.621 62
PointConv-SFPN0.641 680.776 510.703 800.721 680.557 850.826 490.451 630.672 850.563 700.483 830.943 760.425 830.162 1000.644 460.726 620.659 650.709 760.572 670.875 670.786 810.559 86
MVPNetpermissive0.641 680.831 310.715 760.671 840.590 730.781 830.394 890.679 820.642 320.553 600.937 840.462 630.256 620.649 440.406 1020.626 780.691 840.666 320.877 650.792 760.608 66
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 700.717 820.701 820.692 770.576 790.801 730.467 590.716 720.563 700.459 900.953 430.429 790.169 970.581 630.854 350.605 830.710 740.550 810.894 520.793 730.575 78
FPConvpermissive0.639 710.785 460.760 560.713 720.603 680.798 750.392 900.534 1040.603 510.524 720.948 590.457 650.250 640.538 780.723 650.598 870.696 820.614 500.872 720.799 660.567 83
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 720.797 420.769 520.641 950.590 730.820 570.461 610.537 1030.637 350.536 660.947 610.388 930.206 800.656 420.668 770.647 710.732 690.585 650.868 770.793 730.473 106
PointSPNet0.637 730.734 710.692 890.714 710.576 790.797 760.446 680.743 650.598 540.437 950.942 770.403 890.150 1040.626 520.800 530.649 680.697 810.557 770.846 860.777 850.563 84
SConv0.636 740.830 320.697 850.752 630.572 810.780 850.445 700.716 720.529 760.530 680.951 490.446 740.170 960.507 870.666 780.636 760.682 870.541 870.886 570.799 660.594 74
Supervoxel-CNN0.635 750.656 920.711 770.719 690.613 660.757 940.444 730.765 570.534 750.566 570.928 960.478 570.272 520.636 470.531 910.664 620.645 970.508 950.864 790.792 760.611 63
joint point-basedpermissive0.634 760.614 1000.778 460.667 860.633 630.825 500.420 810.804 470.467 950.561 580.951 490.494 490.291 390.566 680.458 970.579 940.764 500.559 760.838 870.814 590.598 72
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 770.731 730.688 920.675 810.591 720.784 820.444 730.565 1000.610 450.492 810.949 570.456 660.254 630.587 600.706 690.599 860.665 930.612 530.868 770.791 790.579 77
PointNet2-SFPN0.631 780.771 550.692 890.672 820.524 900.837 370.440 750.706 770.538 740.446 920.944 730.421 850.219 750.552 740.751 590.591 900.737 650.543 860.901 470.768 890.557 87
APCF-Net0.631 780.742 680.687 940.672 820.557 850.792 800.408 830.665 860.545 730.508 770.952 470.428 800.186 900.634 490.702 710.620 790.706 780.555 780.873 700.798 680.581 76
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
3DSM_DMMF0.631 780.626 970.745 670.801 450.607 670.751 950.506 380.729 700.565 680.491 820.866 1120.434 750.197 870.595 580.630 820.709 440.705 790.560 740.875 670.740 970.491 101
FusionAwareConv0.630 810.604 1020.741 710.766 590.590 730.747 960.501 410.734 680.503 850.527 700.919 1020.454 670.323 250.550 760.420 1010.678 570.688 850.544 840.896 500.795 700.627 61
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 820.800 410.625 1040.719 690.545 870.806 700.445 700.597 940.448 1000.519 750.938 830.481 550.328 230.489 910.499 960.657 660.759 550.592 610.881 610.797 690.634 58
SegGroup_sempermissive0.627 830.818 360.747 660.701 730.602 690.764 910.385 940.629 910.490 880.508 770.931 950.409 880.201 840.564 690.725 630.618 800.692 830.539 880.873 700.794 710.548 90
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 840.830 320.694 870.757 610.563 830.772 890.448 670.647 890.520 790.509 760.949 570.431 780.191 880.496 890.614 840.647 710.672 910.535 900.876 660.783 820.571 79
dtc_net0.625 840.703 850.751 630.794 480.535 880.848 260.480 520.676 840.528 770.469 870.944 730.454 670.004 1170.464 940.636 810.704 470.758 560.548 830.924 300.787 800.492 100
HPEIN0.618 860.729 750.668 950.647 920.597 710.766 900.414 820.680 810.520 790.525 710.946 640.432 760.215 770.493 900.599 850.638 750.617 1020.570 680.897 490.806 630.605 69
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-GCNpermissive0.610 870.858 250.772 480.489 1100.532 890.792 800.404 860.643 900.570 670.507 790.935 870.414 870.046 1140.510 850.702 710.602 850.705 790.549 820.859 810.773 870.534 93
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 880.760 600.667 960.649 910.521 910.793 780.457 620.648 880.528 770.434 970.947 610.401 900.153 1030.454 950.721 660.648 700.717 730.536 890.904 420.765 900.485 102
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
Weakly-Openseg v30.604 890.901 140.762 540.627 970.478 970.820 570.346 1000.689 800.353 1100.528 690.933 920.217 1150.172 940.530 800.725 630.593 890.737 650.515 920.858 820.772 880.515 96
wsss-transformer0.600 900.634 960.743 690.697 760.601 700.781 830.437 770.585 970.493 870.446 920.933 920.394 910.011 1160.654 430.661 800.603 840.733 680.526 910.832 880.761 920.480 103
LAP-D0.594 910.720 800.692 890.637 960.456 1010.773 880.391 920.730 690.587 580.445 940.940 810.381 940.288 400.434 980.453 990.591 900.649 950.581 660.777 960.749 960.610 65
DPC0.592 920.720 800.700 830.602 1010.480 960.762 930.380 950.713 750.585 610.437 950.940 810.369 960.288 400.434 980.509 950.590 920.639 1000.567 720.772 970.755 940.592 75
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 930.766 590.659 990.683 790.470 1000.740 980.387 930.620 930.490 880.476 850.922 1000.355 990.245 670.511 840.511 940.571 950.643 980.493 990.872 720.762 910.600 71
ROSMRF0.580 940.772 540.707 790.681 800.563 830.764 910.362 970.515 1050.465 960.465 890.936 860.427 820.207 790.438 960.577 870.536 980.675 900.486 1000.723 1030.779 830.524 95
SD-DETR0.576 950.746 650.609 1080.445 1140.517 920.643 1090.366 960.714 740.456 980.468 880.870 1110.432 760.264 590.558 720.674 750.586 930.688 850.482 1010.739 1010.733 990.537 92
SQN_0.1%0.569 960.676 890.696 860.657 880.497 930.779 860.424 790.548 1010.515 810.376 1020.902 1090.422 840.357 90.379 1030.456 980.596 880.659 940.544 840.685 1060.665 1100.556 88
TextureNetpermissive0.566 970.672 910.664 970.671 840.494 940.719 990.445 700.678 830.411 1060.396 1000.935 870.356 980.225 720.412 1000.535 900.565 960.636 1010.464 1030.794 950.680 1070.568 82
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
DVVNet0.562 980.648 930.700 830.770 560.586 760.687 1030.333 1020.650 870.514 820.475 860.906 1060.359 970.223 740.340 1050.442 1000.422 1090.668 920.501 960.708 1040.779 830.534 93
Pointnet++ & Featurepermissive0.557 990.735 700.661 980.686 780.491 950.744 970.392 900.539 1020.451 990.375 1030.946 640.376 950.205 810.403 1010.356 1050.553 970.643 980.497 970.824 910.756 930.515 96
GMLPs0.538 1000.495 1100.693 880.647 920.471 990.793 780.300 1050.477 1060.505 840.358 1040.903 1080.327 1020.081 1110.472 930.529 920.448 1070.710 740.509 930.746 990.737 980.554 89
PanopticFusion-label0.529 1010.491 1110.688 920.604 1000.386 1060.632 1100.225 1160.705 780.434 1030.293 1100.815 1140.348 1000.241 680.499 880.669 760.507 1000.649 950.442 1090.796 940.602 1140.561 85
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
subcloud_weak0.516 1020.676 890.591 1110.609 980.442 1020.774 870.335 1010.597 940.422 1050.357 1050.932 940.341 1010.094 1100.298 1070.528 930.473 1050.676 890.495 980.602 1120.721 1020.349 114
Online SegFusion0.515 1030.607 1010.644 1020.579 1030.434 1030.630 1110.353 980.628 920.440 1010.410 980.762 1170.307 1040.167 980.520 820.403 1030.516 990.565 1050.447 1070.678 1070.701 1040.514 98
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
3DMV, FTSDF0.501 1040.558 1060.608 1090.424 1160.478 970.690 1020.246 1120.586 960.468 940.450 910.911 1040.394 910.160 1010.438 960.212 1120.432 1080.541 1100.475 1020.742 1000.727 1000.477 104
PCNN0.498 1050.559 1050.644 1020.560 1050.420 1050.711 1010.229 1140.414 1070.436 1020.352 1060.941 790.324 1030.155 1020.238 1120.387 1040.493 1010.529 1110.509 930.813 930.751 950.504 99
3DMV0.484 1060.484 1120.538 1140.643 940.424 1040.606 1140.310 1030.574 980.433 1040.378 1010.796 1150.301 1050.214 780.537 790.208 1130.472 1060.507 1140.413 1120.693 1050.602 1140.539 91
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 1070.577 1040.611 1070.356 1180.321 1140.715 1000.299 1070.376 1110.328 1140.319 1080.944 730.285 1070.164 990.216 1150.229 1100.484 1030.545 1090.456 1050.755 980.709 1030.475 105
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 1080.679 880.604 1100.578 1040.380 1070.682 1040.291 1080.106 1180.483 910.258 1160.920 1010.258 1110.025 1150.231 1140.325 1060.480 1040.560 1070.463 1040.725 1020.666 1090.231 118
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 1090.474 1130.623 1050.463 1120.366 1090.651 1070.310 1030.389 1100.349 1120.330 1070.937 840.271 1090.126 1070.285 1080.224 1110.350 1140.577 1040.445 1080.625 1100.723 1010.394 110
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
PNET20.442 1100.548 1070.548 1130.597 1020.363 1100.628 1120.300 1050.292 1130.374 1080.307 1090.881 1100.268 1100.186 900.238 1120.204 1140.407 1100.506 1150.449 1060.667 1080.620 1130.462 108
SurfaceConvPF0.442 1100.505 1090.622 1060.380 1170.342 1120.654 1060.227 1150.397 1090.367 1090.276 1120.924 980.240 1120.198 860.359 1040.262 1080.366 1110.581 1030.435 1100.640 1090.668 1080.398 109
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 1120.437 1150.646 1010.474 1110.369 1080.645 1080.353 980.258 1150.282 1170.279 1110.918 1030.298 1060.147 1060.283 1090.294 1070.487 1020.562 1060.427 1110.619 1110.633 1120.352 113
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1130.525 1080.647 1000.522 1060.324 1130.488 1180.077 1190.712 760.353 1100.401 990.636 1190.281 1080.176 930.340 1050.565 880.175 1180.551 1080.398 1130.370 1190.602 1140.361 112
SPLAT Netcopyleft0.393 1140.472 1140.511 1150.606 990.311 1150.656 1050.245 1130.405 1080.328 1140.197 1170.927 970.227 1140.000 1190.001 1200.249 1090.271 1170.510 1120.383 1150.593 1130.699 1050.267 116
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 1150.297 1170.491 1160.432 1150.358 1110.612 1130.274 1100.116 1170.411 1060.265 1130.904 1070.229 1130.079 1120.250 1100.185 1150.320 1150.510 1120.385 1140.548 1140.597 1170.394 110
PointNet++permissive0.339 1160.584 1030.478 1170.458 1130.256 1170.360 1190.250 1110.247 1160.278 1180.261 1150.677 1180.183 1160.117 1080.212 1160.145 1170.364 1120.346 1190.232 1190.548 1140.523 1180.252 117
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
GrowSP++0.323 1170.114 1190.589 1120.499 1080.147 1190.555 1150.290 1090.336 1120.290 1160.262 1140.865 1130.102 1190.000 1190.037 1180.000 1200.000 1200.462 1160.381 1160.389 1180.664 1110.473 106
SSC-UNetpermissive0.308 1180.353 1160.290 1190.278 1190.166 1180.553 1160.169 1180.286 1140.147 1190.148 1190.908 1050.182 1170.064 1130.023 1190.018 1190.354 1130.363 1170.345 1170.546 1160.685 1060.278 115
ScanNetpermissive0.306 1190.203 1180.366 1180.501 1070.311 1150.524 1170.211 1170.002 1200.342 1130.189 1180.786 1160.145 1180.102 1090.245 1110.152 1160.318 1160.348 1180.300 1180.460 1170.437 1190.182 119
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 1200.000 1200.041 1200.172 1200.030 1200.062 1200.001 1200.035 1190.004 1200.051 1200.143 1200.019 1200.003 1180.041 1170.050 1180.003 1190.054 1200.018 1200.005 1200.264 1200.082 120


3D Semantic Instance Benchmark

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




Method Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PointRel0.901 11.000 10.978 230.928 30.879 10.962 50.882 40.749 360.947 30.912 20.802 30.753 170.820 21.000 10.984 40.919 50.894 31.000 10.815 14
: Relation3D (PointRel): Enhancing Relation Modeling for Point Cloud Instance Segmentation.
OneFormer3Dcopyleft0.896 21.000 11.000 10.913 60.858 60.951 90.786 140.837 180.916 120.908 40.778 80.803 60.750 141.000 10.976 60.926 40.882 70.995 470.849 1
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
Competitor-MAFT0.896 21.000 11.000 10.872 160.847 110.967 30.955 10.778 320.901 150.919 10.784 50.812 10.770 121.000 10.949 80.865 330.868 171.000 10.840 4
MG-Former0.887 41.000 10.991 140.837 250.801 230.935 180.887 30.857 100.946 40.891 100.748 170.805 50.739 161.000 10.993 20.809 570.876 141.000 10.842 3
UniPerception0.884 51.000 10.979 200.872 160.869 30.892 270.806 110.890 60.835 290.892 90.755 130.811 20.779 100.955 470.951 70.876 220.914 10.997 390.840 5
KmaxOneFormerNetpermissive0.883 61.000 11.000 10.798 390.848 100.971 10.853 50.903 30.827 320.910 30.748 160.809 40.724 181.000 10.980 50.855 390.844 231.000 10.832 6
InsSSM0.883 61.000 10.996 60.800 380.865 40.960 60.808 100.852 150.940 60.899 80.785 40.810 30.700 211.000 10.912 190.851 420.895 20.997 390.827 8
Lei Yao, Yi Wang, Moyun Liu, Lap-Pui Chau: SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation. TCSVT, 2024
Competitor-SPFormer0.881 81.000 11.000 10.845 230.854 70.962 40.714 210.857 110.904 140.902 60.782 70.789 110.662 271.000 10.988 30.874 250.886 60.997 390.847 2
TST3D0.879 91.000 10.994 90.921 50.807 220.939 150.771 150.887 70.923 100.862 170.722 220.768 140.756 131.000 10.910 290.904 70.836 260.999 380.824 10
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
SIM3D0.878 101.000 10.972 250.863 190.817 200.952 80.821 80.783 290.890 180.902 70.735 200.797 70.799 91.000 10.931 160.893 130.853 211.000 10.792 17
EV3D0.877 111.000 10.996 80.873 140.854 80.950 100.691 250.783 300.926 70.889 130.754 140.794 100.820 21.000 10.912 190.900 90.860 191.000 10.779 20
Spherical Mask(CtoF)0.875 121.000 10.991 150.873 140.850 90.946 120.691 250.752 350.926 70.889 120.759 110.794 90.820 21.000 10.912 190.900 90.878 111.000 10.769 22
TD3Dpermissive0.875 121.000 10.976 240.877 120.783 290.970 20.889 20.828 190.945 50.803 220.713 240.720 240.709 191.000 10.936 140.934 30.873 151.000 10.791 18
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
SoftGroup++0.874 141.000 10.972 260.947 10.839 140.898 260.556 400.913 20.881 210.756 240.828 20.748 190.821 11.000 10.937 130.937 10.887 51.000 10.821 11
Queryformer0.874 141.000 10.978 220.809 360.876 20.936 170.702 220.716 410.920 110.875 160.766 90.772 130.818 61.000 10.995 10.916 60.892 41.000 10.767 23
Mask3D0.870 161.000 10.985 170.782 460.818 190.938 160.760 160.749 360.923 90.877 150.760 100.785 120.820 21.000 10.912 190.864 350.878 110.983 530.825 9
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
ExtMask3D0.867 171.000 11.000 10.756 530.816 210.940 140.795 120.760 340.862 230.888 140.739 180.763 150.774 111.000 10.929 170.878 210.879 91.000 10.819 13
SoftGrouppermissive0.865 181.000 10.969 270.860 200.860 50.913 220.558 370.899 40.911 130.760 230.828 10.736 210.802 80.981 440.919 180.875 230.877 131.000 10.820 12
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
MAFT0.860 191.000 10.990 160.810 350.829 150.949 110.809 90.688 470.836 280.904 50.751 150.796 80.741 151.000 10.864 390.848 440.837 241.000 10.828 7
IPCA-Inst0.851 201.000 10.968 280.884 110.842 130.862 390.693 240.812 240.888 200.677 360.783 60.698 250.807 71.000 10.911 260.865 340.865 181.000 10.757 26
SPFormerpermissive0.851 201.000 10.994 100.806 370.774 310.942 130.637 290.849 160.859 250.889 110.720 230.730 220.665 261.000 10.911 260.868 320.873 161.000 10.796 16
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
Mask3D_evaluation0.843 221.000 10.955 330.847 220.795 250.932 190.750 180.780 310.891 170.818 190.737 190.633 340.703 201.000 10.902 310.870 280.820 270.941 610.805 15
SphereSeg0.835 231.000 10.963 310.891 90.794 260.954 70.822 70.710 420.961 20.721 280.693 300.530 470.653 291.000 10.867 380.857 380.859 200.991 500.771 21
ISBNetpermissive0.835 231.000 10.950 340.731 550.819 170.918 200.790 130.740 380.851 270.831 180.661 320.742 200.650 301.000 10.937 120.814 560.836 251.000 10.765 24
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
GraphCut0.832 251.000 10.922 480.724 570.798 240.902 250.701 230.856 130.859 240.715 290.706 250.748 180.640 411.000 10.934 150.862 360.880 81.000 10.729 29
TopoSeg0.832 251.000 10.981 190.933 20.819 180.826 480.524 460.841 170.811 340.681 350.759 120.687 260.727 170.981 440.911 260.883 170.853 221.000 10.756 27
PBNetpermissive0.825 271.000 10.963 300.837 270.843 120.865 340.822 60.647 500.878 220.733 260.639 390.683 270.650 301.000 10.853 400.870 290.820 281.000 10.744 28
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
SSEC0.820 281.000 10.983 180.924 40.826 160.817 510.415 550.899 50.793 380.673 370.731 210.636 320.653 281.000 10.939 110.804 590.878 101.000 10.780 19
DKNet0.815 291.000 10.930 400.844 240.765 350.915 210.534 440.805 260.805 360.807 210.654 330.763 160.650 301.000 10.794 520.881 180.766 321.000 10.758 25
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN0.806 301.000 10.992 120.789 410.723 480.891 280.650 280.810 250.832 300.665 390.699 280.658 280.700 211.000 10.881 330.832 480.774 300.997 390.613 49
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAISpermissive0.803 311.000 10.994 100.820 310.759 360.855 400.554 410.882 80.827 330.615 450.676 310.638 310.646 391.000 10.912 190.797 620.767 310.994 480.726 30
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask0.803 311.000 10.962 320.874 130.707 520.887 310.686 270.598 550.961 10.715 300.694 290.469 520.700 211.000 10.912 190.902 80.753 370.997 390.637 43
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group0.792 331.000 10.968 290.812 320.766 340.864 350.460 490.815 230.888 190.598 490.651 360.639 300.600 470.918 500.941 90.896 120.721 441.000 10.723 31
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained0.791 341.000 10.996 60.829 300.767 330.889 300.600 320.819 220.770 430.594 500.620 430.541 440.700 211.000 10.941 90.889 150.763 331.000 10.526 59
SSTNetpermissive0.789 351.000 10.840 620.888 100.717 490.835 440.717 200.684 480.627 580.724 270.652 350.727 230.600 471.000 10.912 190.822 510.757 361.000 10.691 37
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN0.788 361.000 10.978 210.867 180.781 300.833 450.527 450.824 200.806 350.549 580.596 460.551 400.700 211.000 10.853 400.935 20.733 411.000 10.651 40
DENet0.786 371.000 10.929 410.736 540.750 420.720 640.755 170.934 10.794 370.590 510.561 520.537 450.650 301.000 10.882 320.804 600.789 291.000 10.719 32
DANCENET0.786 371.000 10.936 370.783 440.737 450.852 420.742 190.647 500.765 450.811 200.624 420.579 370.632 441.000 10.909 300.898 110.696 490.944 570.601 52
DualGroup0.782 391.000 10.927 420.811 330.772 320.853 410.631 310.805 260.773 400.613 460.611 440.610 350.650 300.835 610.881 330.879 200.750 391.000 10.675 38
PointGroup0.778 401.000 10.900 520.798 400.715 500.863 360.493 470.706 430.895 160.569 560.701 260.576 380.639 421.000 10.880 350.851 410.719 450.997 390.709 34
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]
PE0.776 411.000 10.900 530.860 200.728 470.869 320.400 560.857 120.774 390.568 570.701 270.602 360.646 390.933 490.843 430.890 140.691 530.997 390.709 33
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA0.767 421.000 10.937 360.810 340.740 440.906 230.550 420.800 280.706 500.577 550.624 410.544 430.596 520.857 530.879 370.880 190.750 380.992 490.658 39
DD-UNet+Group0.764 431.000 10.897 550.837 260.753 390.830 470.459 510.824 200.699 520.629 430.653 340.438 550.650 301.000 10.880 350.858 370.690 541.000 10.650 41
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
INS-Conv-instance0.762 441.000 10.923 450.765 490.785 280.905 240.600 320.655 490.646 570.683 340.647 370.530 460.650 301.000 10.824 450.830 490.693 520.944 570.644 42
Dyco3Dcopyleft0.761 451.000 10.935 380.893 80.752 410.863 370.600 320.588 560.742 470.641 410.633 400.546 420.550 540.857 530.789 540.853 400.762 340.987 510.699 35
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance0.742 461.000 10.923 450.785 420.745 430.867 330.557 380.578 590.729 480.670 380.644 380.488 500.577 531.000 10.794 520.830 490.620 621.000 10.550 55
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg0.739 471.000 10.899 540.759 510.753 400.823 490.282 610.691 460.658 550.582 540.594 470.547 410.628 451.000 10.795 510.868 310.728 431.000 10.692 36
3D-MPA0.737 481.000 10.933 390.785 420.794 270.831 460.279 630.588 560.695 530.616 440.559 530.556 390.650 301.000 10.809 490.875 240.696 501.000 10.608 51
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML0.731 491.000 10.992 120.779 480.609 610.746 590.308 600.867 90.601 610.607 470.539 560.519 480.550 541.000 10.824 450.869 300.729 421.000 10.616 47
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS0.725 501.000 10.885 580.653 630.657 580.801 520.576 360.695 450.828 310.698 320.534 570.457 540.500 610.857 530.831 440.841 460.627 601.000 10.619 46
SSEN0.724 511.000 10.926 430.781 470.661 560.845 430.596 350.529 620.764 460.653 400.489 630.461 530.500 610.859 520.765 550.872 270.761 351.000 10.577 53
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF0.718 521.000 10.945 350.901 70.754 380.817 500.460 490.700 440.772 410.688 330.568 510.000 740.500 610.981 440.606 650.872 260.740 401.000 10.614 48
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Sparse R-CNN0.714 531.000 10.926 440.694 580.699 540.890 290.636 300.516 630.693 540.743 250.588 480.369 590.601 460.594 670.800 500.886 160.676 550.986 520.546 56
SALoss-ResNet0.695 541.000 10.855 600.579 680.589 630.735 620.484 480.588 560.856 260.634 420.571 500.298 600.500 611.000 10.824 450.818 520.702 480.935 640.545 57
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)
PanopticFusion-inst0.693 551.000 10.852 610.655 620.616 600.788 540.334 580.763 330.771 420.457 680.555 540.652 290.518 580.857 530.765 550.732 680.631 580.944 570.577 54
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Occipital-SCS0.688 561.000 10.913 490.730 560.737 460.743 610.442 520.855 140.655 560.546 590.546 550.263 620.508 600.889 510.568 660.771 650.705 470.889 670.625 45
3D-BoNet0.687 571.000 10.887 570.836 280.587 640.643 710.550 420.620 520.724 490.522 630.501 610.243 630.512 591.000 10.751 570.807 580.661 570.909 660.612 50
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
ClickSeg_Instance0.685 581.000 10.818 640.600 660.715 510.795 530.557 380.533 610.591 630.601 480.519 590.429 570.638 430.938 480.706 600.817 540.624 610.944 570.502 61
PCJC0.684 591.000 10.895 560.757 520.659 570.862 380.189 700.739 390.606 600.712 310.581 490.515 490.650 300.857 530.357 710.785 630.631 590.889 670.635 44
SPG_WSIS0.678 601.000 10.880 590.836 280.701 530.727 630.273 650.607 540.706 510.541 610.515 600.174 660.600 470.857 530.716 590.846 450.711 461.000 10.506 60
One_Thing_One_Clickpermissive0.675 611.000 10.823 630.782 450.621 590.766 560.211 670.736 400.560 650.586 520.522 580.636 330.453 650.641 650.853 400.850 430.694 510.997 390.411 66
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_inspermissive0.637 621.000 10.923 470.593 670.561 650.746 600.143 720.504 640.766 440.485 660.442 640.372 580.530 570.714 620.815 480.775 640.673 561.000 10.431 65
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASCpermissive0.615 630.711 700.802 650.540 690.757 370.777 550.029 730.577 600.588 640.521 640.600 450.436 560.534 560.697 630.616 640.838 470.526 640.980 540.534 58
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone0.605 641.000 10.909 500.764 500.603 620.704 650.415 540.301 690.548 660.461 670.394 650.267 610.386 670.857 530.649 630.817 530.504 660.959 550.356 69
3D-SISpermissive0.558 651.000 10.773 660.614 650.503 680.691 670.200 680.412 650.498 690.546 600.311 700.103 700.600 470.857 530.382 680.799 610.445 720.938 630.371 67
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.544 660.500 730.655 720.661 610.663 550.765 570.432 530.214 720.612 590.584 530.499 620.204 650.286 710.429 700.655 620.650 730.539 630.950 560.499 62
Hier3Dcopyleft0.540 671.000 10.727 670.626 640.467 710.693 660.200 680.412 650.480 700.528 620.318 690.077 730.600 470.688 640.382 680.768 660.472 680.941 610.350 70
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class0.497 680.250 750.902 510.689 590.540 660.747 580.276 640.610 530.268 740.489 650.348 660.000 740.243 740.220 730.663 610.814 550.459 700.928 650.496 63
Sem_Recon_ins0.484 690.764 690.608 740.470 710.521 670.637 720.311 590.218 710.348 730.365 720.223 710.222 640.258 720.629 660.734 580.596 740.509 650.858 700.444 64
tmp0.474 701.000 10.727 670.433 730.481 700.673 690.022 750.380 670.517 680.436 700.338 680.128 680.343 690.429 700.291 730.728 690.473 670.833 710.300 72
SemRegionNet-20cls0.470 711.000 10.727 670.447 720.481 690.678 680.024 740.380 670.518 670.440 690.339 670.128 680.350 680.429 700.212 740.711 700.465 690.833 710.290 73
ASIS0.422 720.333 740.707 700.676 600.401 720.650 700.350 570.177 730.594 620.376 710.202 720.077 720.404 660.571 680.197 750.674 720.447 710.500 740.260 74
3D-BEVIS0.401 730.667 710.687 710.419 740.137 750.587 730.188 710.235 700.359 720.211 740.093 750.080 710.311 700.571 680.382 680.754 670.300 740.874 690.357 68
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.390 740.556 720.636 730.493 700.353 730.539 740.271 660.160 740.450 710.359 730.178 730.146 670.250 730.143 740.347 720.698 710.436 730.667 730.331 71
MaskRCNN 2d->3d Proj0.261 750.903 680.081 750.008 750.233 740.175 750.280 620.106 750.150 750.203 750.175 740.480 510.218 750.143 740.542 670.404 750.153 750.393 750.049 75


2D Semantic Label Benchmark

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 20.512 10.422 170.898 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_2Dcopyleft0.670 20.822 30.795 30.836 20.659 30.481 20.451 130.769 40.656 30.567 40.931 30.395 60.390 50.700 40.534 40.689 100.770 20.574 30.865 90.831 30.675 5
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MVF-GNN（2D）0.636 30.606 140.794 40.434 160.688 10.337 80.464 120.798 30.632 50.589 30.908 80.420 20.329 120.743 20.594 20.738 20.676 50.527 40.906 20.818 60.715 3
CU-Hybrid-2D Net0.636 30.825 20.820 20.179 230.648 40.463 30.549 20.742 70.676 20.628 20.961 10.420 20.379 60.684 80.381 180.732 30.723 30.599 20.827 160.851 20.634 7
CMX0.613 50.681 80.725 120.502 120.634 60.297 180.478 100.830 20.651 40.537 70.924 40.375 70.315 140.686 70.451 140.714 50.543 210.504 60.894 70.823 50.688 4
DMMF_3d0.605 60.651 90.744 100.782 30.637 50.387 40.536 30.732 80.590 70.540 60.856 210.359 110.306 150.596 140.539 30.627 200.706 40.497 80.785 210.757 190.476 22
EMSANet0.600 70.716 40.746 90.395 180.614 90.382 50.523 40.713 110.571 110.503 100.922 60.404 50.397 40.655 90.400 160.626 210.663 60.469 130.900 40.827 40.577 14
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
MCA-Net0.595 80.533 200.756 80.746 40.590 100.334 100.506 70.670 150.587 80.500 120.905 100.366 100.352 90.601 130.506 80.669 160.648 90.501 70.839 150.769 150.516 21
RFBNet0.592 90.616 110.758 70.659 50.581 110.330 110.469 110.655 180.543 140.524 80.924 40.355 130.336 110.572 170.479 100.671 140.648 90.480 100.814 190.814 70.614 10
FAN_NV_RVC0.586 100.510 210.764 60.079 260.620 80.330 110.494 80.753 50.573 90.556 50.884 160.405 40.303 160.718 30.452 130.672 130.658 70.509 50.898 50.813 80.727 2
DCRedNet0.583 110.682 70.723 130.542 110.510 200.310 150.451 130.668 160.549 130.520 90.920 70.375 70.446 20.528 200.417 150.670 150.577 180.478 110.862 100.806 90.628 9
MIX6D_RVC0.582 120.695 50.687 170.225 210.632 70.328 130.550 10.748 60.623 60.494 150.890 140.350 150.254 230.688 60.454 120.716 40.597 170.489 90.881 80.768 160.575 15
SSMAcopyleft0.577 130.695 50.716 150.439 140.563 140.314 140.444 150.719 90.551 120.503 100.887 150.346 160.348 100.603 120.353 200.709 60.600 150.457 140.901 30.786 110.599 13
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DMMF0.567 140.623 100.767 50.238 200.571 130.347 60.413 190.719 90.472 200.418 220.895 130.357 120.260 220.696 50.523 70.666 170.642 110.437 180.895 60.793 100.603 12
UNIV_CNP_RVC_UE0.566 150.569 190.686 190.435 150.524 170.294 190.421 180.712 120.543 140.463 170.872 170.320 170.363 80.611 110.477 110.686 110.627 120.443 170.862 100.775 140.639 6
EMSAFormer0.564 160.581 160.736 110.564 100.546 160.219 230.517 50.675 140.486 190.427 210.904 110.352 140.320 130.589 150.528 50.708 70.464 240.413 220.847 140.786 110.611 11
SN_RN152pyrx8_RVCcopyleft0.546 170.572 170.663 210.638 70.518 180.298 170.366 240.633 210.510 170.446 190.864 190.296 200.267 190.542 190.346 210.704 80.575 190.431 190.853 130.766 170.630 8
UDSSEG_RVC0.545 180.610 130.661 220.588 80.556 150.268 210.482 90.642 200.572 100.475 160.836 230.312 180.367 70.630 100.189 230.639 190.495 230.452 150.826 170.756 200.541 17
segfomer with 6d0.542 190.594 150.687 170.146 240.579 120.308 160.515 60.703 130.472 200.498 130.868 180.369 90.282 170.589 150.390 170.701 90.556 200.416 210.860 120.759 180.539 19
FuseNetpermissive0.535 200.570 180.681 200.182 220.512 190.290 200.431 160.659 170.504 180.495 140.903 120.308 190.428 30.523 210.365 190.676 120.621 140.470 120.762 220.779 130.541 17
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 210.613 120.722 140.418 170.358 260.337 80.370 230.479 240.443 220.368 240.907 90.207 230.213 250.464 240.525 60.618 220.657 80.450 160.788 200.721 230.408 25
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 220.481 240.612 230.579 90.456 220.343 70.384 210.623 220.525 160.381 230.845 220.254 220.264 210.557 180.182 240.581 240.598 160.429 200.760 230.661 250.446 24
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 230.505 220.709 160.092 250.427 230.241 220.411 200.654 190.385 260.457 180.861 200.053 260.279 180.503 220.481 90.645 180.626 130.365 240.748 240.725 220.529 20
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 240.490 230.581 240.289 190.507 210.067 260.379 220.610 230.417 240.435 200.822 250.278 210.267 190.503 220.228 220.616 230.533 220.375 230.820 180.729 210.560 16
Enet (reimpl)0.376 250.264 260.452 260.452 130.365 240.181 240.143 260.456 250.409 250.346 250.769 260.164 240.218 240.359 250.123 260.403 260.381 260.313 260.571 250.685 240.472 23
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)permissive0.330 260.293 250.521 250.657 60.361 250.161 250.250 250.004 260.440 230.183 260.836 230.125 250.060 260.319 260.132 250.417 250.412 250.344 250.541 260.427 260.109 26
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17


2D Semantic Instance Benchmark

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
EMSANet (Instance)0.241 10.401 10.439 10.085 10.242 10.220 10.081 10.289 20.117 20.121 10.182 10.126 10.346 10.181 20.181 20.358 10.156 10.675 20.131 1
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
UniDet_RVC0.205 20.381 20.323 30.037 30.226 30.177 30.063 20.277 30.120 10.067 30.131 30.074 30.317 20.080 30.235 10.289 30.141 30.678 10.080 3
FKNet0.204 30.334 30.358 20.038 20.234 20.184 20.025 30.318 10.042 40.088 20.141 20.053 40.300 30.207 10.171 30.292 20.149 20.636 30.109 2
MaskRCNN_ScanNetpermissive0.119 40.129 40.212 40.002 40.112 40.148 40.014 40.205 40.044 30.066 40.078 40.095 20.142 40.030 40.128 40.139 40.080 40.459 40.057 4
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17


Scene Type Classification Benchmark

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
LAST-PCL-type0.780 10.250 31.000 11.000 11.000 11.000 11.000 10.500 21.000 10.500 20.889 10.000 21.000 11.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, and Jian Zhang: Language-Assisted 3D Scene Understanding. arxiv23.12
multi-taskpermissive0.700 20.500 11.000 10.882 30.500 31.000 11.000 10.500 21.000 11.000 10.778 20.000 20.938 20.000 3
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
3DASPP-SCE0.691 30.500 10.938 30.824 41.000 11.000 10.500 31.000 10.857 30.500 20.556 40.000 20.812 30.500 2
SE-ResNeXt-SSMA0.498 40.000 50.812 40.941 20.500 30.500 40.500 30.500 20.429 50.500 20.667 30.500 10.625 40.000 3
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
resnet50_scannet0.353 50.250 30.812 40.529 50.500 30.500 40.000 50.500 20.571 40.000 50.556 40.000 20.375 50.000 3