The 3D semantic labeling task involves predicting a semantic labeling of a 3D scan mesh.

Evaluation and metrics

Our evaluation ranks all methods according to the PASCAL VOC intersection-over-union metric (IoU). IoU = TP/(TP+FP+FN), where TP, FP, and FN are the numbers of true positive, false positive, and false negative pixels, respectively. Predicted labels are evaluated per-vertex over the respective 3D scan mesh; for 3D approaches that operate on other representations like grids or points, the predicted labels should be mapped onto the mesh vertices (e.g., one such example for grid to mesh vertices is provided in the evaluation helpers).



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 bysort bysort bysort bysort 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 by
DITR0.409 20.616 10.351 10.215 30.651 10.238 10.400 20.000 10.340 10.000 10.534 20.476 40.585 20.687 140.853 10.143 120.854 30.000 30.865 30.167 60.000 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 70.037 150.791 10.053 20.118 30.479 110.429 40.940 30.000 10.000 20.461 80.562 100.093 50.628 140.991 10.762 30.135 30.270 30.917 30.000 10.140 40.597 20.000 70.361 130.375 10.730 20.431 50.459 30.410 130.008 150.656 10.814 10.036 50.554 40.947 60.139 110.000 10.263 30.896 10.191 100.615 40.839 30.757 10.399 60.877 10.504 50.524 60.000 40.000 10.587 30.000 80.022 100.077 90.921 10.928 20.132 90.670 40.759 10.652 10.862 70.091 100.000 10.662 30.072 160.000 110.000 40.000 10.496 10.852 20.752 20.152 30.743 10.953 10.301 30.625 30.053 130.913 10.399 10.452 50.000 10.000 70.000 40.742 20.000 30.000 60.000 10.694 20.643 40.444 60.784 70.000 90.000 10.571 10.614 30.491 30.938 10.559 90.357 50.107 80.404 10.000 20.796 20.688 40.148 60.186 10.629 60.827 20.000 10.558 100.198 40.000 60.000 10.723 20.000 20.000 10.833 10.619 10.609 20.478 40.617 10.959 40.370 30.597 100.737 20.191 50.752 20.000 10.118 10.853 10.925 20.670 130.000 10.831 30.000 150.873 30.000 10.699 10.005 100.360 10.723 30.235 14
PTv3 ScanNet2000.393 30.592 30.330 20.216 20.520 40.109 40.108 150.000 10.337 20.000 10.310 120.394 80.494 120.753 90.848 20.256 50.717 70.000 30.842 50.192 40.065 40.449 70.346 40.546 60.190 110.000 80.384 60.000 10.000 30.218 30.505 10.791 20.000 10.136 30.000 20.903 20.073 110.687 80.000 70.168 10.551 50.387 80.941 20.000 10.000 20.397 120.654 40.000 100.714 50.759 140.752 90.118 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 30.971 20.188 30.000 10.133 80.593 20.349 10.650 30.717 80.699 30.455 20.790 20.523 30.636 10.301 10.000 10.622 20.000 80.017 140.259 30.000 50.921 40.337 20.733 20.210 40.514 30.860 80.407 10.000 10.688 20.109 80.000 110.000 40.000 10.151 40.671 80.782 10.115 110.641 20.903 20.349 10.616 40.088 60.832 50.000 60.480 30.000 10.428 10.000 40.497 100.000 30.000 60.000 10.662 40.690 20.612 10.828 10.575 10.000 10.404 70.644 10.325 70.887 40.728 10.009 140.134 60.026 160.000 20.761 30.731 10.172 40.077 30.528 70.727 70.000 10.603 50.220 30.022 30.000 10.740 10.000 20.000 10.661 40.586 20.566 30.436 50.531 30.978 20.457 10.708 40.583 60.141 80.748 30.000 10.026 50.822 50.871 40.879 50.000 10.851 20.405 20.914 10.000 10.682 30.000 140.281 40.738 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)
OA-CNN-L_ScanNet2000.333 100.558 40.269 90.124 120.448 140.080 80.272 50.000 10.000 40.000 10.342 70.515 20.524 80.713 130.789 80.158 110.384 110.000 30.806 70.125 80.000 90.496 50.332 70.498 140.227 70.024 40.474 20.000 10.003 20.071 90.487 30.000 100.000 10.110 80.000 20.876 80.013 160.703 40.000 70.076 100.473 120.355 110.906 60.000 10.000 20.476 50.706 10.000 100.672 110.835 120.748 100.015 140.223 70.860 90.000 10.000 110.572 60.000 70.509 60.313 70.662 60.398 110.396 50.411 120.276 40.527 30.711 50.000 80.076 110.946 80.166 60.000 10.022 100.160 80.183 120.493 110.699 90.637 60.403 50.330 120.406 120.526 50.024 30.000 10.392 110.000 80.016 150.000 110.196 30.915 60.112 110.557 90.197 50.352 90.877 30.000 110.000 10.592 130.103 110.000 110.067 10.000 10.089 50.735 60.625 110.130 100.568 60.836 80.271 60.534 100.043 140.799 90.001 50.445 60.000 10.000 70.024 30.661 40.000 30.262 20.000 10.591 70.517 140.373 80.788 60.021 80.000 10.455 30.517 90.320 80.823 100.200 160.001 150.150 50.100 100.000 20.736 100.668 80.103 120.052 50.662 30.720 80.000 10.602 60.112 60.002 50.000 10.637 90.000 20.000 10.621 90.569 40.398 90.412 60.234 100.949 70.363 50.492 140.495 100.251 40.665 90.000 10.001 110.805 70.833 60.794 100.000 10.821 50.314 50.843 110.000 10.560 80.245 30.262 60.713 40.370 12
L3DETR-ScanNet_2000.336 90.533 120.279 50.155 90.508 60.073 100.101 160.000 10.058 30.000 10.294 140.233 140.548 40.927 10.788 90.264 30.463 100.000 30.638 110.098 140.014 70.411 90.226 120.525 110.225 80.010 50.397 50.000 10.000 30.192 50.380 130.598 40.000 10.117 60.000 20.883 60.082 80.689 60.000 70.032 160.549 60.417 60.910 50.000 10.000 20.448 90.613 80.000 100.697 70.960 20.759 50.158 20.293 20.883 70.000 10.312 30.583 30.079 40.422 110.068 160.660 90.418 70.298 110.430 110.114 100.526 40.776 30.051 40.679 10.946 80.152 70.000 10.183 60.000 140.211 70.511 100.409 150.565 110.355 80.448 80.512 40.557 20.000 40.000 10.420 90.000 80.007 160.104 60.000 50.125 160.330 30.514 130.146 110.321 120.860 80.174 90.000 10.629 70.075 140.000 110.000 40.000 10.002 70.671 80.712 50.141 70.339 110.856 50.261 110.529 110.067 90.835 30.000 60.369 130.000 10.259 20.000 40.629 50.000 30.487 10.000 10.579 110.646 30.107 160.720 100.122 60.000 10.333 120.505 100.303 90.908 30.503 140.565 20.074 90.324 20.000 20.740 90.661 90.109 110.000 100.427 120.563 160.000 10.579 90.108 80.000 60.000 10.664 50.000 20.000 10.641 70.539 90.416 70.515 20.256 90.940 110.312 60.209 160.620 30.138 120.636 120.000 10.000 120.775 120.861 50.765 110.000 10.801 110.119 120.860 80.000 10.687 20.001 130.192 140.679 90.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
GSTran0.339 70.536 100.273 60.169 70.491 90.071 120.365 30.000 10.000 40.000 10.178 160.246 130.458 130.754 80.788 90.316 10.834 50.000 30.872 20.202 30.079 30.318 130.286 110.538 70.156 130.004 70.310 120.000 10.000 30.009 140.397 120.297 70.000 10.093 110.000 20.876 80.060 130.690 50.000 70.086 80.517 80.358 100.667 130.000 10.000 20.473 60.670 30.000 100.731 30.896 70.765 20.061 80.256 50.889 60.000 10.000 110.480 130.000 70.412 120.279 80.690 40.366 130.373 70.466 90.357 10.514 50.648 80.024 60.615 20.949 50.183 40.000 10.162 70.564 30.196 80.535 80.413 140.638 50.410 40.682 50.445 90.470 110.289 20.000 10.358 120.000 80.022 100.161 40.008 40.877 130.495 10.461 150.161 100.348 100.853 110.199 70.000 10.643 40.109 80.014 80.000 40.000 10.000 80.681 70.705 60.079 150.441 80.872 30.282 50.593 70.096 50.786 110.021 30.495 10.000 10.118 50.000 40.487 110.000 30.002 50.000 10.589 80.563 120.144 150.682 130.109 70.000 10.235 150.455 120.368 60.659 160.609 60.000 160.060 100.033 150.000 20.746 80.648 120.084 140.000 100.803 10.832 10.000 10.614 40.000 140.497 10.000 10.597 130.000 20.000 10.621 90.506 120.459 60.252 110.228 120.913 130.369 40.665 60.598 40.139 100.666 80.000 10.097 20.841 20.698 110.857 60.000 10.811 70.129 110.784 130.000 10.386 100.012 70.317 30.696 50.425 8
BFANet ScanNet200permissive0.360 40.553 60.293 40.193 40.483 100.096 50.266 60.000 10.000 40.000 10.298 130.255 110.661 10.810 50.810 30.194 90.785 60.000 30.000 160.161 70.000 90.494 60.382 20.574 40.258 40.000 80.372 80.000 10.000 30.043 120.436 70.000 100.000 10.239 20.000 20.901 30.105 10.689 60.025 40.128 20.614 20.436 10.493 150.000 10.000 20.526 40.546 120.109 40.651 130.953 40.753 80.101 60.143 120.897 40.000 10.431 10.469 140.000 70.522 50.337 50.661 80.459 20.409 40.666 40.102 120.508 60.757 40.000 80.060 130.970 30.497 10.000 10.376 20.511 50.262 50.688 20.921 10.617 90.321 120.590 60.491 60.556 30.000 40.000 10.481 50.093 10.043 20.284 20.000 50.875 140.135 80.669 50.124 120.394 60.849 120.298 20.000 10.476 160.088 130.042 50.000 40.000 10.254 30.653 100.741 40.215 10.573 50.852 60.266 80.654 10.056 110.835 30.000 60.492 20.000 10.000 70.000 40.612 80.000 30.000 60.000 10.616 50.469 160.460 40.698 120.516 20.000 10.378 80.563 40.476 40.863 50.574 80.330 60.000 110.282 40.000 20.760 40.710 20.233 10.000 100.641 40.814 30.000 10.585 80.053 110.000 60.000 10.629 100.000 20.000 10.678 30.528 110.534 40.129 130.596 20.973 30.264 110.772 20.526 80.139 100.707 40.000 10.000 120.764 130.591 150.848 70.000 10.827 40.338 30.806 120.000 10.568 70.151 60.358 20.659 100.510 4
ALS-MinkowskiNetcopyleft0.414 10.610 20.322 30.271 10.542 20.153 20.159 110.000 10.000 40.000 10.404 40.503 30.532 70.672 160.804 50.285 20.888 10.000 30.900 10.226 10.087 20.598 30.342 50.671 10.217 90.087 30.449 30.000 10.000 30.253 20.477 51.000 10.000 10.118 40.000 20.905 10.071 120.710 30.076 10.047 150.665 10.376 90.981 10.000 10.000 20.466 70.632 60.113 30.769 10.956 30.795 10.031 100.314 10.936 10.000 10.390 20.601 10.000 70.458 80.366 20.719 30.440 40.564 10.699 30.314 20.464 70.784 20.200 10.283 60.973 10.142 90.000 10.250 50.285 70.220 60.718 10.752 60.723 20.460 10.248 150.475 70.463 120.000 40.000 10.446 80.021 40.025 80.285 10.000 50.972 10.149 70.769 10.230 20.535 20.879 20.252 40.000 10.693 10.129 20.000 110.000 40.000 10.447 20.958 10.662 80.159 20.598 30.780 130.344 20.646 20.106 40.893 20.135 20.455 40.000 10.194 30.259 10.726 30.475 20.000 60.000 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 60.000 20.804 10.697 30.137 90.043 60.717 20.807 40.000 10.510 120.245 10.000 60.000 10.709 30.000 20.000 10.703 20.572 30.646 10.223 120.531 30.984 10.397 20.813 10.798 10.135 130.800 10.000 10.097 20.832 30.752 90.842 80.000 10.852 10.149 90.846 100.000 10.666 50.359 20.252 80.777 10.690 2
OctFormer ScanNet200permissive0.326 120.539 90.265 110.131 110.499 70.110 30.522 10.000 10.000 40.000 10.318 110.427 60.455 140.743 110.765 120.175 100.842 40.000 30.828 60.204 20.033 60.429 80.335 60.601 30.312 30.000 80.357 90.000 10.000 30.047 110.423 80.000 100.000 10.105 90.000 20.873 110.079 90.670 120.000 70.117 40.471 130.432 30.829 100.000 10.000 20.584 20.417 160.089 60.684 100.837 110.705 150.021 130.178 90.892 50.000 10.028 70.505 100.000 70.457 90.200 130.662 60.412 90.244 140.496 70.000 160.451 80.626 90.000 80.102 90.943 110.138 120.000 10.000 120.149 90.291 30.534 90.722 70.632 80.331 100.253 140.453 80.487 90.000 40.000 10.479 60.000 80.022 100.000 110.000 50.900 90.128 100.684 30.164 80.413 40.854 100.000 110.000 10.512 150.074 150.003 90.000 40.000 10.000 80.469 140.613 120.132 90.529 70.871 40.227 150.582 80.026 160.787 100.000 60.339 140.000 10.000 70.000 40.626 60.000 30.029 40.000 10.587 90.612 70.411 70.724 90.000 90.000 10.407 50.552 50.513 20.849 70.655 40.408 30.000 110.296 30.000 20.686 140.645 130.145 70.022 80.414 130.633 110.000 10.637 10.224 20.000 60.000 10.650 70.000 20.000 10.622 80.535 100.343 110.483 30.230 110.943 90.289 90.618 80.596 50.140 90.679 70.000 10.022 60.783 100.620 130.906 10.000 10.806 100.137 100.865 50.000 10.378 110.000 140.168 160.680 80.227 15
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
IMFSegNet0.337 80.535 110.266 100.169 80.527 30.072 110.147 120.000 10.000 40.000 10.341 80.152 150.544 50.678 150.803 70.264 30.868 20.000 30.853 40.181 50.040 50.398 100.357 30.366 160.208 100.000 80.317 110.000 10.000 30.187 60.418 90.274 80.000 10.118 40.000 20.884 50.095 20.715 20.000 70.095 60.592 30.424 50.472 160.000 10.000 20.426 100.564 90.000 100.692 80.915 50.759 50.001 160.170 110.831 120.000 10.004 100.493 110.000 70.492 70.228 120.675 50.396 120.382 60.277 160.311 30.442 90.551 140.177 20.066 120.947 60.126 150.000 10.051 90.544 40.263 40.469 130.786 50.633 70.311 130.708 40.422 110.432 130.000 40.000 10.497 40.000 80.038 30.122 50.000 50.910 80.251 50.655 60.211 30.343 110.840 130.204 60.000 10.637 50.112 50.000 110.000 40.000 10.000 80.743 40.660 90.143 50.359 100.821 100.264 90.571 90.054 120.810 80.000 60.380 100.000 10.133 40.094 20.576 90.667 10.000 60.000 10.546 140.572 100.361 90.699 110.000 90.000 10.406 60.524 80.568 10.829 80.505 120.196 100.119 70.263 50.032 10.755 50.683 50.036 160.026 70.634 50.791 50.000 10.383 140.109 70.000 60.000 10.645 80.000 20.000 10.469 110.545 80.373 100.297 90.447 50.953 50.300 80.728 30.509 90.132 150.642 110.000 10.031 40.824 40.769 70.839 90.000 10.810 80.000 150.867 40.000 10.378 110.004 110.177 150.644 120.442 7
PonderV2 ScanNet2000.346 50.552 70.270 80.175 60.497 80.070 130.239 70.000 10.000 40.000 10.232 150.412 70.584 30.842 30.804 50.212 80.540 90.000 30.433 150.106 110.000 90.590 40.290 100.548 50.243 60.000 80.356 100.000 10.000 30.062 100.398 110.441 60.000 10.104 100.000 20.888 40.076 100.682 90.030 30.094 70.491 100.351 120.869 90.000 10.063 10.403 110.700 20.000 100.660 120.881 80.761 40.050 90.186 80.852 110.000 10.007 80.570 70.100 20.565 20.326 60.641 110.431 50.290 130.621 50.259 50.408 100.622 100.125 30.082 100.950 40.179 50.000 10.263 30.424 60.193 90.558 60.880 20.545 120.375 70.727 30.445 90.499 80.000 40.000 10.475 70.002 60.034 60.083 80.000 50.924 30.290 40.636 70.115 130.400 50.874 40.186 80.000 10.611 90.128 30.113 20.000 40.000 10.000 80.584 110.636 100.103 120.385 90.843 70.283 40.603 60.080 70.825 70.000 60.377 110.000 10.000 70.000 40.457 120.000 30.000 60.000 10.574 120.608 80.481 30.792 40.394 40.000 10.357 100.503 110.261 100.817 110.504 130.304 70.472 40.115 90.000 20.750 70.677 70.202 20.000 100.509 80.729 60.000 10.519 110.000 140.000 60.000 10.620 120.000 20.000 10.660 60.560 60.486 50.384 70.346 80.952 60.247 130.667 50.436 110.269 30.691 60.000 10.010 70.787 90.889 30.880 40.000 10.810 80.336 40.860 80.000 10.606 60.009 80.248 90.681 70.392 10
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.
PPT-SpUNet-F.T.0.332 110.556 50.270 70.123 130.519 50.091 60.349 40.000 10.000 40.000 10.339 90.383 90.498 110.833 40.807 40.241 60.584 80.000 30.755 80.124 90.000 90.608 20.330 80.530 100.314 20.000 80.374 70.000 10.000 30.197 40.459 60.000 100.000 10.117 60.000 20.876 80.095 20.682 90.000 70.086 80.518 70.433 20.930 40.000 10.000 20.563 30.542 130.077 70.715 40.858 100.756 70.008 150.171 100.874 80.000 10.039 60.550 80.000 70.545 40.256 90.657 100.453 30.351 90.449 100.213 60.392 110.611 110.000 80.037 140.946 80.138 120.000 10.000 120.063 100.308 20.537 70.796 40.673 40.323 110.392 100.400 130.509 70.000 40.000 10.649 10.000 80.023 90.000 110.000 50.914 70.002 150.506 140.163 90.359 80.872 50.000 110.000 10.623 80.112 50.001 100.000 40.000 10.021 60.753 30.565 150.150 40.579 40.806 110.267 70.616 40.042 150.783 120.000 60.374 120.000 10.000 70.000 40.620 70.000 30.000 60.000 10.572 130.634 50.350 100.792 40.000 90.000 10.376 90.535 60.378 50.855 60.672 30.074 110.000 110.185 80.000 20.727 110.660 100.076 150.000 100.432 110.646 100.000 10.594 70.006 130.000 60.000 10.658 60.000 20.000 10.661 40.549 70.300 130.291 100.045 130.942 100.304 70.600 90.572 70.135 130.695 50.000 10.008 90.793 80.942 10.899 20.000 10.816 60.181 70.897 20.000 10.679 40.223 40.264 50.691 60.345 13
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
CSC-Pretrainpermissive0.249 160.455 160.171 150.079 160.418 150.059 150.186 100.000 10.000 40.000 10.335 100.250 120.316 150.766 70.697 160.142 130.170 130.003 20.553 130.112 100.097 10.201 150.186 130.476 150.081 150.000 80.216 160.000 10.000 30.001 160.314 160.000 100.000 10.055 140.000 20.832 160.094 40.659 140.002 50.076 100.310 160.293 160.664 140.000 10.000 20.175 160.634 50.130 20.552 160.686 160.700 160.076 70.110 140.770 160.000 10.000 110.430 160.000 70.319 140.166 140.542 160.327 150.205 150.332 140.052 140.375 120.444 160.000 80.012 160.930 160.203 20.000 10.000 120.046 110.175 130.413 150.592 120.471 150.299 140.152 160.340 150.247 160.000 40.000 10.225 140.058 30.037 40.000 110.207 20.862 150.014 130.548 110.033 150.233 150.816 150.000 110.000 10.542 140.123 40.121 10.019 20.000 10.000 80.463 150.454 160.045 160.128 160.557 150.235 130.441 150.063 100.484 160.000 60.308 160.000 10.000 70.000 40.318 160.000 30.000 60.000 10.545 150.543 130.164 140.734 80.000 90.000 10.215 160.371 150.198 130.743 120.205 150.062 130.000 110.079 120.000 20.683 150.547 150.142 80.000 100.441 100.579 150.000 10.464 130.098 90.041 20.000 10.590 150.000 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 10.000 120.591 160.609 140.398 140.000 10.766 160.014 140.638 160.000 10.377 130.004 110.206 130.609 160.465 5
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
AWCS0.305 130.508 130.225 130.142 100.463 130.063 140.195 90.000 10.000 40.000 10.467 30.551 10.504 90.773 60.764 130.142 130.029 160.000 30.626 120.100 120.000 90.360 110.179 140.507 130.137 140.006 60.300 130.000 10.000 30.172 80.364 140.512 50.000 10.056 130.000 20.865 130.093 50.634 160.000 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 10.000 110.515 90.010 60.452 100.252 100.578 130.417 80.179 160.484 80.171 70.337 130.606 120.000 80.115 80.937 130.142 90.000 10.008 110.000 140.157 150.484 120.402 160.501 140.339 90.553 70.529 20.478 100.000 40.000 10.404 100.001 70.022 100.077 90.000 50.894 110.219 60.628 80.093 140.305 130.886 10.233 50.000 10.603 100.112 50.023 70.000 40.000 10.000 80.741 50.664 70.097 130.253 130.782 120.264 90.523 120.154 10.707 150.000 60.411 80.000 10.000 70.000 40.332 150.000 30.000 60.000 10.602 60.595 90.185 130.656 150.159 50.000 10.355 110.424 140.154 140.729 130.516 100.220 90.620 30.084 110.000 20.707 130.651 110.173 30.014 90.381 160.582 140.000 10.619 20.049 120.000 60.000 10.702 40.000 20.000 10.302 150.489 140.317 120.334 80.392 60.922 120.254 120.533 130.394 120.129 160.613 140.000 10.000 120.820 60.649 120.749 120.000 10.782 130.282 60.863 60.000 10.288 150.006 90.220 110.633 130.542 3
CeCo0.340 60.551 80.247 120.181 50.475 120.057 160.142 130.000 10.000 40.000 10.387 50.463 50.499 100.924 20.774 110.213 70.257 120.000 30.546 140.100 120.006 80.615 10.177 160.534 80.246 50.000 80.400 40.000 10.338 10.006 150.484 40.609 30.000 10.083 120.000 20.873 110.089 60.661 130.000 70.048 140.560 40.408 70.892 70.000 10.000 20.586 10.616 70.000 100.692 80.900 60.721 110.162 10.228 60.860 90.000 10.000 110.575 40.083 30.550 30.347 40.624 120.410 100.360 80.740 20.109 110.321 140.660 70.000 80.121 70.939 120.143 80.000 10.400 10.003 120.190 110.564 50.652 100.615 100.421 30.304 130.579 10.547 40.000 40.000 10.296 130.000 80.030 70.096 70.000 50.916 50.037 120.551 100.171 70.376 70.865 60.286 30.000 10.633 60.102 120.027 60.011 30.000 10.000 80.474 130.742 30.133 80.311 120.824 90.242 120.503 130.068 80.828 60.000 60.429 70.000 10.063 60.000 40.781 10.000 30.000 60.000 10.665 30.633 60.450 50.818 20.000 90.000 10.429 40.532 70.226 120.825 90.510 110.377 40.709 20.079 120.000 20.753 60.683 50.102 130.063 40.401 150.620 130.000 10.619 20.000 140.000 60.000 10.595 140.000 20.000 10.345 130.564 50.411 80.603 10.384 70.945 80.266 100.643 70.367 130.304 10.663 100.000 10.010 70.726 140.767 80.898 30.000 10.784 120.435 10.861 70.000 10.447 90.000 140.257 70.656 110.377 11
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
LGroundpermissive0.272 140.485 140.184 140.106 140.476 110.077 90.218 80.000 10.000 40.000 10.547 10.295 100.540 60.746 100.745 140.058 150.112 150.005 10.658 100.077 160.000 90.322 120.178 150.512 120.190 110.199 20.277 140.000 10.000 30.173 70.399 100.000 100.000 10.039 150.000 20.858 140.085 70.676 110.002 50.103 50.498 90.323 130.703 110.000 10.000 20.296 140.549 110.216 10.702 60.768 130.718 130.028 110.092 150.786 150.000 10.000 110.453 150.022 50.251 160.252 100.572 140.348 140.321 100.514 60.063 130.279 150.552 130.000 80.019 150.932 140.132 140.000 10.000 120.000 140.156 160.457 140.623 110.518 130.265 150.358 110.381 140.395 140.000 40.000 10.127 160.012 50.051 10.000 110.000 50.886 120.014 130.437 160.179 60.244 140.826 140.000 110.000 10.599 110.136 10.085 30.000 40.000 10.000 80.565 120.612 130.143 50.207 140.566 140.232 140.446 140.127 20.708 140.000 60.384 90.000 10.000 70.000 40.402 130.000 30.059 30.000 10.525 160.566 110.229 120.659 140.000 90.000 10.265 130.446 130.147 150.720 150.597 70.066 120.000 110.187 70.000 20.726 120.467 160.134 100.000 100.413 140.629 120.000 10.363 150.055 100.022 30.000 10.626 110.000 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 10.233 100.622 140.398 9
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 10.000 40.000 10.386 60.141 160.279 160.737 120.703 150.014 160.164 140.000 30.663 90.092 150.000 90.224 140.291 90.531 90.056 160.000 80.242 150.000 10.000 30.013 130.331 150.000 100.000 10.035 160.001 10.858 140.059 140.650 150.000 70.056 130.353 150.299 140.670 120.000 10.000 20.284 150.484 140.071 80.594 150.720 150.710 140.027 120.068 160.813 130.000 10.005 90.492 120.164 10.274 150.111 150.571 150.307 160.293 120.307 150.150 80.163 160.531 150.002 70.545 50.932 140.093 160.000 10.000 120.002 130.159 140.368 160.581 130.440 160.228 160.406 90.282 160.294 150.000 40.000 10.189 150.060 20.036 50.000 110.000 50.897 100.000 160.525 120.025 160.205 160.771 160.000 110.000 10.593 120.108 100.044 40.000 40.000 10.000 80.282 160.589 140.094 140.169 150.466 160.227 150.419 160.125 30.757 130.002 40.334 150.000 10.000 70.000 40.357 140.000 30.000 60.000 10.582 100.513 150.337 110.612 160.000 90.000 10.250 140.352 160.136 160.724 140.655 40.280 80.000 110.046 140.000 20.606 160.559 140.159 50.102 20.445 90.655 90.000 10.310 160.117 50.000 60.000 10.581 160.026 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 10.003 100.622 150.720 100.096 160.000 10.771 150.016 130.772 140.000 10.302 140.194 50.214 120.621 150.197 16
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019