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 iouwallchairfloortabledoorcouchcabinetshelfdeskoffice chairbedpillowsinkpicturewindowtoiletbookshelfmonitorcurtainbookarmchaircoffee tableboxrefrigeratorlampkitchen cabinettowelclothestvnightstandcounterdresserstoolcushionplantceilingbathtubend tabledining tablekeyboardbagbackpacktoilet paperprintertv standwhiteboardblanketshower curtaintrash canclosetstairsmicrowavestoveshoecomputer towerbottlebinottomanbenchboardwashing machinemirrorcopierbasketsofa chairfile cabinetfanlaptopshowerpaperpersonpaper towel dispenserovenblindsrackplateblackboardpianosuitcaserailradiatorrecycling bincontainerwardrobesoap dispensertelephonebucketclockstandlightlaundry basketpipeclothes dryerguitartoilet paper holderseatspeakercolumnbicycleladderbathroom stallshower wallcupjacketstorage bincoffee makerdishwasherpaper towel rollmachinematwindowsillbartoasterbulletin boardironing boardfireplacesoap dishkitchen counterdoorframetoilet paper dispensermini fridgefire extinguisherballhatshower curtain rodwater coolerpaper cuttertrayshower doorpillarledgetoaster ovenmousetoilet seat cover dispenserfurniturecartstorage containerscaletissue boxlight switchcratepower outletdecorationsignprojectorcloset doorvacuum cleanercandleplungerstuffed animalheadphonesdish rackbroomguitar caserange hooddustpanhair dryerwater bottlehandicap barpurseventshower floorwater pitchermailboxbowlpaper bagalarm clockmusic standprojector screendividerlaundry detergentbathroom counterobjectbathroom vanitycloset walllaundry hamperbathroom stall doorceiling lighttrash bindumbbellstair railtubebathroom cabinetcd casecloset rodcoffee kettlestructureshower headkeyboard pianocase of water bottlescoat rackstorage organizerfolded chairfire alarmpower stripcalendarposterpotted plantluggagemattress
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 bysort bysort bysort bysort bysort bysort 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 by
DITR0.409 20.616 10.351 10.215 30.831 30.791 10.947 60.619 10.730 20.762 30.494 20.571 10.597 20.000 110.853 10.625 30.796 20.301 30.723 30.959 40.617 20.862 70.917 30.573 10.562 100.591 10.784 70.504 50.757 10.737 20.429 40.853 10.662 30.135 30.459 30.558 100.000 10.913 10.878 70.687 140.008 150.000 70.615 40.238 10.651 10.370 30.742 20.925 20.360 10.167 60.938 10.752 20.118 30.827 20.670 40.723 20.614 30.628 140.372 10.000 30.143 120.175 160.873 30.652 10.991 10.340 10.148 60.814 10.656 10.524 60.491 30.000 10.743 10.752 20.000 40.000 90.000 10.399 10.865 30.953 10.833 10.694 20.444 60.000 150.688 40.609 20.000 30.053 20.000 10.022 100.000 40.053 130.940 30.000 10.186 10.093 50.854 30.877 10.534 20.404 10.270 30.191 100.198 40.461 80.375 10.152 30.921 10.132 90.235 140.000 10.617 10.330 10.896 10.399 60.431 50.597 100.759 10.554 40.400 20.000 10.559 90.699 10.852 20.000 10.000 80.091 100.385 10.000 60.000 90.478 40.077 90.000 70.140 40.000 20.000 30.670 130.000 10.452 50.000 10.263 30.361 130.000 10.643 40.000 10.000 10.357 50.005 100.928 20.362 10.496 10.000 10.000 60.000 10.072 160.585 20.587 30.476 40.037 150.191 50.410 130.629 60.118 10.000 10.479 110.000 20.000 20.107 80.839 30.000 20.000 10.000 10.139 110.036 50.000 40.247 90.000 1
L3DETR-ScanNet_2000.336 90.533 120.279 50.155 90.801 110.689 60.946 80.539 90.660 90.759 50.380 130.333 120.583 30.000 110.788 90.529 110.740 90.261 110.679 90.940 110.525 110.860 80.883 70.226 120.613 80.397 50.720 100.512 40.565 110.620 30.417 60.775 120.629 70.158 20.298 110.579 90.000 10.835 30.883 60.927 10.114 100.079 40.511 100.073 100.508 60.312 60.629 50.861 50.192 140.098 140.908 30.636 120.032 160.563 160.514 130.664 50.505 100.697 70.225 80.000 30.264 30.411 90.860 80.321 120.960 20.058 30.109 110.776 30.526 40.557 20.303 90.000 10.339 110.712 50.000 40.014 70.000 10.000 60.638 110.856 50.641 70.579 110.107 160.119 120.661 90.416 70.000 30.000 70.000 10.007 160.000 40.067 90.910 50.000 10.000 100.000 100.463 100.448 80.294 140.324 20.293 20.211 70.108 80.448 90.068 160.141 70.000 50.330 30.699 10.000 10.256 90.192 50.000 140.355 80.418 70.209 160.146 110.679 10.101 160.000 10.503 140.687 20.671 80.000 10.000 80.174 90.117 60.000 60.122 60.515 20.104 60.259 20.312 30.000 20.000 30.765 110.000 10.369 130.000 10.183 60.422 110.000 10.646 30.000 10.000 10.565 20.001 130.125 160.010 50.002 70.000 10.487 10.000 10.075 140.548 40.420 90.233 140.082 80.138 120.430 110.427 120.000 120.000 10.549 60.000 20.000 20.074 90.409 150.000 20.000 10.000 10.152 70.051 40.000 40.598 40.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
OctFormer ScanNet200permissive0.326 120.539 90.265 110.131 110.806 100.670 120.943 110.535 100.662 60.705 150.423 80.407 50.505 100.003 90.765 120.582 80.686 140.227 150.680 80.943 90.601 30.854 100.892 50.335 60.417 160.357 90.724 90.453 80.632 80.596 50.432 30.783 100.512 150.021 130.244 140.637 10.000 10.787 100.873 110.743 110.000 160.000 70.534 90.110 30.499 70.289 90.626 60.620 130.168 160.204 20.849 70.679 70.117 40.633 110.684 30.650 70.552 50.684 100.312 30.000 30.175 100.429 80.865 50.413 40.837 110.000 40.145 70.626 90.451 80.487 90.513 20.000 10.529 70.613 120.000 40.033 60.000 10.000 60.828 60.871 40.622 80.587 90.411 70.137 100.645 130.343 110.000 30.000 70.000 10.022 100.000 40.026 160.829 100.000 10.022 80.089 60.842 40.253 140.318 110.296 30.178 90.291 30.224 20.584 20.200 130.132 90.000 50.128 100.227 150.000 10.230 110.047 110.149 90.331 100.412 90.618 80.164 80.102 90.522 10.000 10.655 40.378 110.469 140.000 10.000 80.000 110.105 90.000 60.000 90.483 30.000 110.000 70.028 70.000 20.000 30.906 10.000 10.339 140.000 10.000 120.457 90.000 10.612 70.000 10.000 10.408 30.000 140.900 90.000 80.000 80.000 10.029 40.000 10.074 150.455 140.479 60.427 60.079 90.140 90.496 70.414 130.022 60.000 10.471 130.000 20.000 20.000 110.722 70.000 20.000 10.000 10.138 120.000 80.000 40.000 100.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
BFANet ScanNet200permissive0.360 40.553 60.293 40.193 40.827 40.689 60.970 30.528 110.661 80.753 80.436 70.378 80.469 140.042 50.810 30.654 10.760 40.266 80.659 100.973 30.574 40.849 120.897 40.382 20.546 120.372 80.698 120.491 60.617 90.526 80.436 10.764 130.476 160.101 60.409 40.585 80.000 10.835 30.901 30.810 50.102 120.000 70.688 20.096 50.483 100.264 110.612 80.591 150.358 20.161 70.863 50.707 40.128 20.814 30.669 50.629 100.563 40.651 130.258 40.000 30.194 90.494 60.806 120.394 60.953 40.000 40.233 10.757 40.508 60.556 30.476 40.000 10.573 50.741 40.000 40.000 90.000 10.000 60.000 160.852 60.678 30.616 50.460 40.338 30.710 20.534 40.000 30.025 40.000 10.043 20.000 40.056 110.493 150.000 10.000 100.109 40.785 60.590 60.298 130.282 40.143 120.262 50.053 110.526 40.337 50.215 10.000 50.135 80.510 40.000 10.596 20.043 120.511 50.321 120.459 20.772 20.124 120.060 130.266 60.000 10.574 80.568 70.653 100.000 10.093 10.298 20.239 20.000 60.516 20.129 130.284 20.000 70.431 10.000 20.000 30.848 70.000 10.492 20.000 10.376 20.522 50.000 10.469 160.000 10.000 10.330 60.151 60.875 140.000 80.254 30.000 10.000 60.000 10.088 130.661 10.481 50.255 110.105 10.139 100.666 40.641 40.000 120.000 10.614 20.000 20.000 20.000 110.921 10.000 20.000 10.000 10.497 10.000 80.000 40.000 100.000 1
IMFSegNet0.337 80.535 110.266 100.169 80.810 80.715 20.947 60.545 80.675 50.759 50.418 90.406 60.493 110.000 110.803 70.571 90.755 50.264 90.644 120.953 50.366 160.840 130.831 120.357 30.564 90.317 110.699 110.422 110.633 70.509 90.424 50.824 40.637 50.001 160.382 60.383 140.000 10.810 80.884 50.678 150.311 30.000 70.469 130.072 110.527 30.300 80.576 90.769 70.177 150.181 50.829 80.642 110.095 60.791 50.655 60.645 80.524 80.692 80.208 100.000 30.264 30.398 100.867 40.343 110.915 50.000 40.036 160.551 140.442 90.432 130.568 10.000 10.359 100.660 90.000 40.040 50.000 10.000 60.853 40.821 100.469 110.546 140.361 90.000 150.683 50.373 100.000 30.000 70.000 10.038 30.000 40.054 120.472 160.000 10.026 70.000 100.868 20.708 40.341 80.263 50.170 110.263 40.109 70.426 100.228 120.143 50.000 50.251 50.442 70.000 10.447 50.187 60.544 40.311 130.396 120.728 30.211 30.066 120.147 120.000 10.505 120.378 110.743 40.000 10.000 80.204 60.118 40.000 60.000 90.297 90.122 50.133 40.004 100.032 10.667 10.839 90.000 10.380 100.000 10.051 90.492 70.000 10.572 100.000 10.000 10.196 100.004 110.910 80.000 80.000 80.000 10.000 60.000 10.112 50.544 50.497 40.152 150.095 20.132 150.277 160.634 50.031 40.000 10.592 30.000 20.000 20.119 70.786 50.000 20.000 10.000 10.126 150.177 20.094 20.274 80.000 1
ALS-MinkowskiNetcopyleft0.414 10.610 20.322 30.271 10.852 10.710 30.973 10.572 30.719 30.795 10.477 50.506 20.601 10.000 110.804 50.646 20.804 10.344 20.777 10.984 10.671 10.879 20.936 10.342 50.632 60.449 30.817 30.475 70.723 20.798 10.376 90.832 30.693 10.031 100.564 10.510 120.000 10.893 20.905 10.672 160.314 20.000 70.718 10.153 20.542 20.397 20.726 30.752 90.252 80.226 10.916 20.800 10.047 150.807 40.769 10.709 30.630 20.769 10.217 90.000 30.285 20.598 30.846 100.535 20.956 30.000 40.137 90.784 20.464 70.463 120.230 110.000 10.598 30.662 80.000 40.087 20.000 10.135 20.900 10.780 130.703 20.741 10.571 20.149 90.697 30.646 10.000 30.076 10.000 10.025 80.000 40.106 40.981 10.000 10.043 60.113 30.888 10.248 150.404 40.252 60.314 10.220 60.245 10.466 70.366 20.159 20.000 50.149 70.690 20.000 10.531 30.253 20.285 70.460 10.440 40.813 10.230 20.283 60.159 110.000 10.728 10.666 50.958 10.000 10.021 40.252 40.118 40.000 60.445 30.223 120.285 10.194 30.390 20.000 20.475 20.842 80.000 10.455 40.000 10.250 50.458 80.000 10.865 10.000 10.000 10.635 10.359 20.972 10.087 30.447 20.000 10.000 60.000 10.129 20.532 70.446 80.503 30.071 120.135 130.699 30.717 20.097 20.000 10.665 10.000 20.000 21.000 10.752 60.000 20.000 10.000 10.142 90.200 10.259 11.000 10.000 1
LGroundpermissive0.272 140.485 140.184 140.106 140.778 140.676 110.932 140.479 160.572 140.718 130.399 100.265 130.453 150.085 30.745 140.446 140.726 120.232 140.622 140.901 140.512 120.826 140.786 150.178 150.549 110.277 140.659 140.381 140.518 130.295 160.323 130.777 110.599 110.028 110.321 100.363 150.000 10.708 140.858 140.746 100.063 130.022 50.457 140.077 90.476 110.243 140.402 130.397 160.233 100.077 160.720 150.610 150.103 50.629 120.437 160.626 110.446 130.702 60.190 110.005 10.058 150.322 120.702 150.244 140.768 130.000 40.134 100.552 130.279 150.395 140.147 150.000 10.207 140.612 130.000 40.000 90.000 10.000 60.658 100.566 140.323 140.525 160.229 120.179 80.467 160.154 150.000 30.002 50.000 10.051 10.000 40.127 20.703 110.000 10.000 100.216 10.112 150.358 110.547 10.187 70.092 150.156 160.055 100.296 140.252 100.143 50.000 50.014 130.398 90.000 10.028 150.173 70.000 140.265 150.348 140.415 150.179 60.019 150.218 80.000 10.597 70.274 160.565 120.000 10.012 50.000 110.039 150.022 30.000 90.117 140.000 110.000 70.000 110.000 20.000 30.324 150.000 10.384 90.000 10.000 120.251 160.000 10.566 110.000 10.000 10.066 120.404 10.886 120.199 20.000 80.000 10.059 30.000 10.136 10.540 60.127 160.295 100.085 70.143 70.514 60.413 140.000 120.000 10.498 90.000 20.000 20.000 110.623 110.000 20.000 10.000 10.132 140.000 80.000 40.000 100.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
PPT-SpUNet-F.T.0.332 110.556 50.270 70.123 130.816 60.682 90.946 80.549 70.657 100.756 70.459 60.376 90.550 80.001 100.807 40.616 40.727 110.267 70.691 60.942 100.530 100.872 50.874 80.330 80.542 130.374 70.792 40.400 130.673 40.572 70.433 20.793 80.623 80.008 150.351 90.594 70.000 10.783 120.876 80.833 40.213 60.000 70.537 70.091 60.519 50.304 70.620 70.942 10.264 50.124 90.855 60.695 50.086 80.646 100.506 140.658 60.535 60.715 40.314 20.000 30.241 60.608 20.897 20.359 80.858 100.000 40.076 150.611 110.392 110.509 70.378 50.000 10.579 40.565 150.000 40.000 90.000 10.000 60.755 80.806 110.661 40.572 130.350 100.181 70.660 100.300 130.000 30.000 70.000 10.023 90.000 40.042 150.930 40.000 10.000 100.077 70.584 80.392 100.339 90.185 80.171 100.308 20.006 130.563 30.256 90.150 40.000 50.002 150.345 130.000 10.045 130.197 40.063 100.323 110.453 30.600 90.163 90.037 140.349 40.000 10.672 30.679 40.753 30.000 10.000 80.000 110.117 60.000 60.000 90.291 100.000 110.000 70.039 60.000 20.000 30.899 20.000 10.374 120.000 10.000 120.545 40.000 10.634 50.000 10.000 10.074 110.223 40.914 70.000 80.021 60.000 10.000 60.000 10.112 50.498 110.649 10.383 90.095 20.135 130.449 100.432 110.008 90.000 10.518 70.000 20.000 20.000 110.796 40.000 20.000 10.000 10.138 120.000 80.000 40.000 100.000 1
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
PonderV2 ScanNet2000.346 50.552 70.270 80.175 60.810 80.682 90.950 40.560 60.641 110.761 40.398 110.357 100.570 70.113 20.804 50.603 60.750 70.283 40.681 70.952 60.548 50.874 40.852 110.290 100.700 20.356 100.792 40.445 90.545 120.436 110.351 120.787 90.611 90.050 90.290 130.519 110.000 10.825 70.888 40.842 30.259 50.100 20.558 60.070 130.497 80.247 130.457 120.889 30.248 90.106 110.817 110.691 60.094 70.729 60.636 70.620 120.503 110.660 120.243 60.000 30.212 80.590 40.860 80.400 50.881 80.000 40.202 20.622 100.408 100.499 80.261 100.000 10.385 90.636 100.000 40.000 90.000 10.000 60.433 150.843 70.660 60.574 120.481 30.336 40.677 70.486 50.000 30.030 30.000 10.034 60.000 40.080 70.869 90.000 10.000 100.000 100.540 90.727 30.232 150.115 90.186 80.193 90.000 140.403 110.326 60.103 120.000 50.290 40.392 100.000 10.346 80.062 100.424 60.375 70.431 50.667 50.115 130.082 100.239 70.000 10.504 130.606 60.584 110.000 10.002 60.186 80.104 100.000 60.394 40.384 70.083 80.000 70.007 80.000 20.000 30.880 40.000 10.377 110.000 10.263 30.565 20.000 10.608 80.000 10.000 10.304 70.009 80.924 30.000 80.000 80.000 10.000 60.000 10.128 30.584 30.475 70.412 70.076 100.269 30.621 50.509 80.010 70.000 10.491 100.063 10.000 20.472 40.880 20.000 20.000 10.000 10.179 50.125 30.000 40.441 60.000 1
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.
OA-CNN-L_ScanNet2000.333 100.558 40.269 90.124 120.821 50.703 40.946 80.569 40.662 60.748 100.487 30.455 30.572 60.000 110.789 80.534 100.736 100.271 60.713 40.949 70.498 140.877 30.860 90.332 70.706 10.474 20.788 60.406 120.637 60.495 100.355 110.805 70.592 130.015 140.396 50.602 60.000 10.799 90.876 80.713 130.276 40.000 70.493 110.080 80.448 140.363 50.661 40.833 60.262 60.125 80.823 100.665 90.076 100.720 80.557 90.637 90.517 90.672 110.227 70.000 30.158 110.496 50.843 110.352 90.835 120.000 40.103 120.711 50.527 30.526 50.320 80.000 10.568 60.625 110.067 10.000 90.000 10.001 50.806 70.836 80.621 90.591 70.373 80.314 50.668 80.398 90.003 20.000 70.000 10.016 150.024 30.043 140.906 60.000 10.052 50.000 100.384 110.330 120.342 70.100 100.223 70.183 120.112 60.476 50.313 70.130 100.196 30.112 110.370 120.000 10.234 100.071 90.160 80.403 50.398 110.492 140.197 50.076 110.272 50.000 10.200 160.560 80.735 60.000 10.000 80.000 110.110 80.002 50.021 80.412 60.000 110.000 70.000 110.000 20.000 30.794 100.000 10.445 60.000 10.022 100.509 60.000 10.517 140.000 10.000 10.001 150.245 30.915 60.024 40.089 50.000 10.262 20.000 10.103 110.524 80.392 110.515 20.013 160.251 40.411 120.662 30.001 110.000 10.473 120.000 20.000 20.150 50.699 90.000 20.000 10.000 10.166 60.000 80.024 30.000 100.000 1
AWCS0.305 130.508 130.225 130.142 100.782 130.634 160.937 130.489 140.578 130.721 110.364 140.355 110.515 90.023 70.764 130.523 120.707 130.264 90.633 130.922 120.507 130.886 10.804 140.179 140.436 150.300 130.656 150.529 20.501 140.394 120.296 150.820 60.603 100.131 40.179 160.619 20.000 10.707 150.865 130.773 60.171 70.010 60.484 120.063 140.463 130.254 120.332 150.649 120.220 110.100 120.729 130.613 140.071 120.582 140.628 80.702 40.424 140.749 20.137 140.000 30.142 130.360 110.863 60.305 130.877 90.000 40.173 30.606 120.337 130.478 100.154 140.000 10.253 130.664 70.000 40.000 90.000 10.000 60.626 120.782 120.302 150.602 60.185 130.282 60.651 110.317 120.000 30.000 70.000 10.022 100.000 40.154 10.876 80.000 10.014 90.063 90.029 160.553 70.467 30.084 110.124 130.157 150.049 120.373 130.252 100.097 130.000 50.219 60.542 30.000 10.392 60.172 80.000 140.339 90.417 80.533 130.093 140.115 80.195 90.000 10.516 100.288 150.741 50.000 10.001 70.233 50.056 130.000 60.159 50.334 80.077 90.000 70.000 110.000 20.000 30.749 120.000 10.411 80.000 10.008 110.452 100.000 10.595 90.000 10.000 10.220 90.006 90.894 110.006 60.000 80.000 10.000 60.000 10.112 50.504 90.404 100.551 10.093 50.129 160.484 80.381 160.000 120.000 10.396 140.000 20.000 20.620 30.402 160.000 20.000 10.000 10.142 90.000 80.000 40.512 50.000 1
CeCo0.340 60.551 80.247 120.181 50.784 120.661 130.939 120.564 50.624 120.721 110.484 40.429 40.575 40.027 60.774 110.503 130.753 60.242 120.656 110.945 80.534 80.865 60.860 90.177 160.616 70.400 40.818 20.579 10.615 100.367 130.408 70.726 140.633 60.162 10.360 80.619 20.000 10.828 60.873 110.924 20.109 110.083 30.564 50.057 160.475 120.266 100.781 10.767 80.257 70.100 120.825 90.663 100.048 140.620 130.551 100.595 140.532 70.692 80.246 50.000 30.213 70.615 10.861 70.376 70.900 60.000 40.102 130.660 70.321 140.547 40.226 120.000 10.311 120.742 30.011 30.006 80.000 10.000 60.546 140.824 90.345 130.665 30.450 50.435 10.683 50.411 80.338 10.000 70.000 10.030 70.000 40.068 80.892 70.000 10.063 40.000 100.257 120.304 130.387 50.079 120.228 60.190 110.000 140.586 10.347 40.133 80.000 50.037 120.377 110.000 10.384 70.006 150.003 120.421 30.410 100.643 70.171 70.121 70.142 130.000 10.510 110.447 90.474 130.000 10.000 80.286 30.083 120.000 60.000 90.603 10.096 70.063 60.000 110.000 20.000 30.898 30.000 10.429 70.000 10.400 10.550 30.000 10.633 60.000 10.000 10.377 40.000 140.916 50.000 80.000 80.000 10.000 60.000 10.102 120.499 100.296 130.463 50.089 60.304 10.740 20.401 150.010 70.000 10.560 40.000 20.000 20.709 20.652 100.000 20.000 10.000 10.143 80.000 80.000 40.609 30.000 1
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
CSC-Pretrainpermissive0.249 160.455 160.171 150.079 160.766 160.659 140.930 160.494 130.542 160.700 160.314 160.215 160.430 160.121 10.697 160.441 150.683 150.235 130.609 160.895 150.476 150.816 150.770 160.186 130.634 50.216 160.734 80.340 150.471 150.307 150.293 160.591 160.542 140.076 70.205 150.464 130.000 10.484 160.832 160.766 70.052 140.000 70.413 150.059 150.418 150.222 150.318 160.609 140.206 130.112 100.743 120.625 130.076 100.579 150.548 110.590 150.371 150.552 160.081 150.003 20.142 130.201 150.638 160.233 150.686 160.000 40.142 80.444 160.375 120.247 160.198 130.000 10.128 160.454 160.019 20.097 10.000 10.000 60.553 130.557 150.373 120.545 150.164 140.014 140.547 150.174 140.000 30.002 50.000 10.037 40.000 40.063 100.664 140.000 10.000 100.130 20.170 130.152 160.335 100.079 120.110 140.175 130.098 90.175 160.166 140.045 160.207 20.014 130.465 50.000 10.001 160.001 160.046 110.299 140.327 150.537 120.033 150.012 160.186 100.000 10.205 150.377 130.463 150.000 10.058 30.000 110.055 140.041 20.000 90.105 150.000 110.000 70.000 110.000 20.000 30.398 140.000 10.308 160.000 10.000 120.319 140.000 10.543 130.000 10.000 10.062 130.004 110.862 150.000 80.000 80.000 10.000 60.000 10.123 40.316 150.225 140.250 120.094 40.180 60.332 140.441 100.000 120.000 10.310 160.000 20.000 20.000 110.592 120.000 20.000 10.000 10.203 20.000 80.000 40.000 100.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 150.463 150.154 160.102 150.771 150.650 150.932 140.483 150.571 150.710 140.331 150.250 140.492 120.044 40.703 150.419 160.606 160.227 150.621 150.865 160.531 90.771 160.813 130.291 90.484 140.242 150.612 160.282 160.440 160.351 140.299 140.622 150.593 120.027 120.293 120.310 160.000 10.757 130.858 140.737 120.150 80.164 10.368 160.084 70.381 160.142 160.357 140.720 100.214 120.092 150.724 140.596 160.056 130.655 90.525 120.581 160.352 160.594 150.056 160.000 30.014 160.224 140.772 140.205 160.720 150.000 40.159 50.531 150.163 160.294 150.136 160.000 10.169 150.589 140.000 40.000 90.000 10.002 40.663 90.466 160.265 160.582 100.337 110.016 130.559 140.084 160.000 30.000 70.000 10.036 50.000 40.125 30.670 120.000 10.102 20.071 80.164 140.406 90.386 60.046 140.068 160.159 140.117 50.284 150.111 150.094 140.000 50.000 160.197 160.000 10.044 140.013 130.002 130.228 160.307 160.588 110.025 160.545 50.134 140.000 10.655 40.302 140.282 160.000 10.060 20.000 110.035 160.000 60.000 90.097 160.000 110.000 70.005 90.000 20.000 30.096 160.000 10.334 150.000 10.000 120.274 150.000 10.513 150.000 10.000 10.280 80.194 50.897 100.000 80.000 80.000 10.000 60.000 10.108 100.279 160.189 150.141 160.059 140.272 20.307 150.445 90.003 100.000 10.353 150.000 20.026 10.000 110.581 130.001 10.000 10.000 10.093 160.002 70.000 40.000 100.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
GSTran0.339 70.536 100.273 60.169 70.811 70.690 50.949 50.506 120.690 40.765 20.397 120.235 150.480 130.014 80.788 90.593 70.746 80.282 50.696 50.913 130.538 70.853 110.889 60.286 110.670 30.310 120.682 130.445 90.638 50.598 40.358 100.841 20.643 40.061 80.373 70.614 40.000 10.786 110.876 80.754 80.357 10.000 70.535 80.071 120.491 90.369 40.487 110.698 110.317 30.202 30.659 160.666 80.086 80.832 10.461 150.597 130.455 120.731 30.156 130.000 30.316 10.318 130.784 130.348 100.896 70.000 40.084 140.648 80.514 50.470 110.368 60.000 10.441 80.705 60.000 40.079 30.000 10.021 30.872 20.872 30.621 90.589 80.144 150.129 110.648 120.459 60.000 30.000 70.000 10.022 100.289 20.096 50.667 130.000 10.000 100.000 100.834 50.682 50.178 160.033 150.256 50.196 80.000 140.473 60.279 80.079 150.008 40.495 10.425 80.000 10.228 120.009 140.564 30.410 40.366 130.665 60.161 100.615 20.365 30.000 10.609 60.386 100.681 70.000 10.000 80.199 70.093 110.497 10.109 70.252 110.161 40.118 50.000 110.000 20.000 30.857 60.000 10.495 10.000 10.162 70.412 120.000 10.563 120.000 10.000 10.000 160.012 70.877 130.004 70.000 80.000 10.002 50.000 10.109 80.458 130.358 120.246 130.060 130.139 100.466 90.803 10.097 20.000 10.517 80.000 20.000 20.060 100.413 140.000 20.000 10.000 10.183 40.024 60.000 40.297 70.000 1
PTv3 ScanNet2000.393 30.592 30.330 20.216 20.851 20.687 80.971 20.586 20.755 10.752 90.505 10.404 70.575 40.000 110.848 20.616 40.761 30.349 10.738 20.978 20.546 60.860 80.926 20.346 40.654 40.384 60.828 10.523 30.699 30.583 60.387 80.822 50.688 20.118 50.474 20.603 50.000 10.832 50.903 20.753 90.140 90.000 70.650 30.109 40.520 40.457 10.497 100.871 40.281 40.192 40.887 40.748 30.168 10.727 70.733 20.740 10.644 10.714 50.190 110.000 30.256 50.449 70.914 10.514 30.759 140.337 20.172 40.692 60.617 20.636 10.325 70.000 10.641 20.782 10.000 40.065 40.000 10.000 60.842 50.903 20.661 40.662 40.612 10.405 20.731 10.566 30.000 30.000 70.000 10.017 140.301 10.088 60.941 20.000 10.077 30.000 100.717 70.790 20.310 120.026 160.264 40.349 10.220 30.397 120.366 20.115 110.000 50.337 20.463 60.000 10.531 30.218 30.593 20.455 20.469 10.708 40.210 40.592 30.108 150.000 10.728 10.682 30.671 80.000 10.000 80.407 10.136 30.022 30.575 10.436 50.259 30.428 10.048 50.000 20.000 30.879 50.000 10.480 30.000 10.133 80.597 10.000 10.690 20.000 10.000 10.009 140.000 140.921 40.000 80.151 40.000 10.000 60.000 10.109 80.494 120.622 20.394 80.073 110.141 80.798 10.528 70.026 50.000 10.551 50.000 20.000 20.134 60.717 80.000 20.000 10.000 10.188 30.000 80.000 40.791 20.000 1
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)