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 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 by
PPT-SpUNet-F.T.0.332 110.556 50.270 60.123 130.816 60.682 90.946 60.549 90.657 80.756 50.459 60.376 80.550 100.001 110.807 40.616 40.727 110.267 80.691 50.942 110.530 90.872 50.874 70.330 70.542 130.374 70.792 40.400 130.673 40.572 60.433 20.793 80.623 60.008 160.351 90.594 70.000 10.783 120.876 70.833 40.213 60.000 70.537 70.091 60.519 40.304 70.620 70.942 10.264 40.124 70.855 60.695 50.086 70.646 100.506 150.658 60.535 60.715 30.314 20.000 30.241 40.608 20.897 20.359 80.858 100.000 60.076 160.611 100.392 110.509 70.378 60.000 10.579 40.565 150.000 40.000 90.000 10.000 50.755 60.806 90.661 40.572 120.350 90.181 70.660 110.300 130.000 30.000 70.000 10.023 100.000 30.042 130.930 40.000 10.000 90.077 70.584 80.392 100.339 80.185 90.171 110.308 20.006 120.563 30.256 80.150 40.000 40.002 150.345 110.000 30.045 130.197 40.063 100.323 100.453 30.600 70.163 100.037 140.349 30.000 10.672 30.679 40.753 50.000 10.000 100.000 110.117 50.000 70.000 80.291 90.000 110.000 70.039 60.000 10.000 40.899 20.000 10.374 100.000 10.000 120.545 40.000 10.634 50.000 10.000 10.074 120.223 60.914 70.000 90.021 80.000 10.000 70.000 10.112 50.498 100.649 10.383 90.095 20.135 120.449 90.432 110.008 90.000 10.518 60.000 20.000 20.000 110.796 40.000 20.000 10.000 10.138 130.000 80.000 30.000 100.000 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
DITR0.409 20.616 10.351 10.215 30.831 30.791 10.947 50.619 10.730 20.762 20.494 20.571 10.597 20.000 120.853 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 30.558 110.000 10.913 10.878 60.687 150.008 150.000 70.615 40.238 10.651 10.370 30.742 20.925 20.360 10.167 40.938 10.752 20.118 30.827 10.670 40.723 20.614 30.628 140.372 10.000 30.143 120.175 160.873 30.652 10.991 10.340 10.148 80.814 10.656 10.524 60.491 40.000 10.743 10.752 40.000 40.000 90.000 10.399 10.865 20.953 10.833 10.694 20.444 60.000 160.688 60.609 20.000 30.053 20.000 10.022 110.000 30.053 110.940 30.000 10.186 10.093 50.854 20.877 10.534 20.404 10.270 30.191 80.198 40.461 70.375 10.152 30.921 10.132 90.235 120.000 30.617 10.330 10.896 10.399 50.431 50.597 80.759 10.554 30.400 20.000 10.559 100.699 10.852 20.000 10.000 100.091 100.385 10.000 70.000 80.478 40.077 90.000 70.140 40.000 10.000 40.670 130.000 10.452 40.000 10.263 50.361 110.000 10.643 40.000 10.000 10.357 50.005 110.928 20.362 10.496 10.000 10.000 70.000 10.072 150.585 20.587 30.476 40.037 130.191 50.410 120.629 40.118 10.000 10.479 110.000 20.000 20.107 70.839 30.000 20.000 10.000 10.139 100.036 60.000 30.247 90.000 1
PonderV2 ScanNet2000.346 50.552 70.270 70.175 80.810 70.682 90.950 40.560 60.641 90.761 30.398 120.357 90.570 70.113 20.804 50.603 60.750 60.283 40.681 60.952 50.548 50.874 40.852 120.290 110.700 20.356 100.792 40.445 110.545 120.436 110.351 120.787 90.611 70.050 80.290 130.519 120.000 10.825 90.888 40.842 30.259 30.100 20.558 60.070 110.497 70.247 130.457 100.889 30.248 80.106 90.817 120.691 60.094 60.729 60.636 60.620 110.503 100.660 120.243 60.000 30.212 60.590 40.860 70.400 50.881 80.000 60.202 20.622 90.408 100.499 80.261 100.000 10.385 90.636 100.000 40.000 90.000 10.000 50.433 150.843 60.660 60.574 110.481 30.336 40.677 80.486 50.000 30.030 30.000 10.034 50.000 30.080 60.869 90.000 10.000 90.000 100.540 90.727 30.232 160.115 100.186 90.193 70.000 130.403 110.326 60.103 130.000 40.290 30.392 80.000 30.346 90.062 90.424 40.375 60.431 50.667 40.115 130.082 110.239 60.000 10.504 130.606 80.584 110.000 10.002 80.186 80.104 90.000 70.394 40.384 70.083 80.000 70.007 80.000 10.000 40.880 40.000 10.377 90.000 10.263 50.565 20.000 10.608 80.000 10.000 10.304 70.009 90.924 30.000 90.000 100.000 10.000 70.000 10.128 30.584 30.475 60.412 70.076 90.269 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 40.125 20.000 30.441 80.000 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.
PTv3 ScanNet2000.393 30.592 30.330 20.216 20.851 20.687 60.971 20.586 20.755 10.752 70.505 10.404 60.575 40.000 120.848 20.616 40.761 30.349 10.738 20.978 20.546 60.860 80.926 20.346 30.654 30.384 60.828 10.523 30.699 30.583 50.387 70.822 30.688 20.118 50.474 20.603 40.000 10.832 70.903 20.753 80.140 90.000 70.650 30.109 40.520 30.457 10.497 90.871 40.281 30.192 30.887 40.748 30.168 10.727 70.733 20.740 10.644 10.714 40.190 120.000 30.256 30.449 90.914 10.514 30.759 140.337 20.172 60.692 60.617 20.636 10.325 70.000 10.641 20.782 10.000 40.065 30.000 10.000 50.842 30.903 20.661 40.662 40.612 10.405 20.731 30.566 30.000 30.000 70.000 10.017 140.301 10.088 50.941 20.000 10.077 30.000 100.717 70.790 20.310 110.026 160.264 40.349 10.220 30.397 120.366 20.115 120.000 40.337 10.463 60.000 30.531 50.218 30.593 20.455 20.469 10.708 30.210 30.592 20.108 150.000 10.728 10.682 30.671 80.000 10.000 100.407 10.136 30.022 30.575 10.436 50.259 30.428 10.048 50.000 10.000 40.879 50.000 10.480 20.000 10.133 90.597 10.000 10.690 20.000 10.000 10.009 150.000 140.921 40.000 90.151 40.000 10.000 70.000 10.109 70.494 110.622 20.394 80.073 100.141 80.798 10.528 70.026 50.000 10.551 40.000 20.000 20.134 60.717 70.000 20.000 10.000 10.188 30.000 80.000 30.791 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)
L3DETR-ScanNet_2000.336 70.533 100.279 50.155 90.801 90.689 40.946 60.539 100.660 70.759 40.380 130.333 130.583 30.000 120.788 100.529 90.740 70.261 110.679 80.940 120.525 100.860 80.883 60.226 120.613 90.397 50.720 100.512 40.565 110.620 30.417 50.775 120.629 50.158 20.298 110.579 100.000 10.835 50.883 50.927 10.114 100.079 40.511 90.073 100.508 50.312 50.629 50.861 50.192 130.098 120.908 30.636 100.032 160.563 160.514 140.664 50.505 90.697 60.225 80.000 30.264 20.411 110.860 70.321 120.960 20.058 50.109 130.776 30.526 40.557 20.303 90.000 10.339 110.712 70.000 40.014 70.000 10.000 50.638 110.856 40.641 70.579 100.107 160.119 110.661 100.416 60.000 30.000 70.000 10.007 160.000 30.067 80.910 50.000 10.000 90.000 100.463 100.448 80.294 130.324 20.293 20.211 60.108 70.448 80.068 160.141 60.000 40.330 20.699 10.000 30.256 100.192 50.000 140.355 70.418 70.209 160.146 110.679 10.101 160.000 10.503 140.687 20.671 80.000 10.000 100.174 90.117 50.000 70.122 60.515 20.104 60.259 20.312 30.000 10.000 40.765 110.000 10.369 110.000 10.183 80.422 100.000 10.646 30.000 10.000 10.565 20.001 130.125 160.010 70.002 90.000 10.487 10.000 10.075 120.548 40.420 80.233 130.082 70.138 110.430 100.427 120.000 120.000 10.549 50.000 20.000 20.074 80.409 150.000 20.000 10.000 10.152 60.051 30.000 30.598 40.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
OA-CNN-L_ScanNet2000.333 100.558 40.269 80.124 120.821 50.703 30.946 60.569 40.662 40.748 80.487 30.455 30.572 60.000 120.789 90.534 80.736 80.271 70.713 40.949 60.498 130.877 30.860 100.332 60.706 10.474 20.788 60.406 120.637 50.495 100.355 110.805 70.592 110.015 130.396 70.602 50.000 10.799 100.876 70.713 120.276 20.000 70.493 120.080 80.448 140.363 40.661 40.833 60.262 50.125 60.823 110.665 80.076 80.720 80.557 100.637 80.517 80.672 90.227 70.000 30.158 110.496 70.843 100.352 90.835 120.000 60.103 140.711 50.527 30.526 50.320 80.000 10.568 60.625 110.067 10.000 90.000 10.001 40.806 50.836 70.621 90.591 70.373 80.314 50.668 90.398 80.003 20.000 70.000 10.016 150.024 20.043 120.906 60.000 10.052 50.000 100.384 110.330 120.342 70.100 110.223 60.183 120.112 60.476 50.313 70.130 90.196 30.112 110.370 100.000 30.234 110.071 80.160 60.403 40.398 130.492 140.197 50.076 120.272 40.000 10.200 160.560 100.735 70.000 10.000 100.000 110.110 70.002 60.021 70.412 60.000 110.000 70.000 100.000 10.000 40.794 100.000 10.445 50.000 10.022 100.509 60.000 10.517 120.000 10.000 10.001 160.245 50.915 60.024 60.089 60.000 10.262 20.000 10.103 90.524 70.392 100.515 20.013 160.251 40.411 110.662 20.001 110.000 10.473 120.000 20.000 20.150 50.699 80.000 20.000 10.000 10.166 50.000 80.024 20.000 100.000 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 80.774 110.503 130.753 50.242 120.656 100.945 90.534 70.865 60.860 100.177 160.616 80.400 40.818 20.579 10.615 100.367 130.408 60.726 140.633 40.162 10.360 80.619 20.000 10.828 80.873 90.924 20.109 110.083 30.564 50.057 140.475 120.266 100.781 10.767 70.257 60.100 100.825 100.663 90.048 140.620 130.551 110.595 120.532 70.692 70.246 50.000 30.213 50.615 10.861 60.376 70.900 70.000 60.102 150.660 70.321 140.547 40.226 120.000 10.311 120.742 50.011 30.006 80.000 10.000 50.546 140.824 80.345 130.665 30.450 50.435 10.683 70.411 70.338 10.000 70.000 10.030 80.000 30.068 70.892 70.000 10.063 40.000 100.257 120.304 130.387 50.079 130.228 50.190 100.000 130.586 10.347 40.133 70.000 40.037 120.377 90.000 30.384 80.006 150.003 120.421 30.410 100.643 50.171 80.121 80.142 110.000 10.510 120.447 110.474 130.000 10.000 100.286 30.083 100.000 70.000 80.603 10.096 70.063 40.000 100.000 10.000 40.898 30.000 10.429 60.000 10.400 10.550 30.000 10.633 60.000 10.000 10.377 40.000 140.916 50.000 90.000 100.000 10.000 70.000 10.102 100.499 90.296 130.463 50.089 50.304 10.740 20.401 150.010 70.000 10.560 30.000 20.000 20.709 20.652 90.000 20.000 10.000 10.143 70.000 80.000 30.609 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
ALS-MinkowskiNetcopyleft0.414 10.610 20.322 30.271 10.852 10.710 20.973 10.572 30.719 30.795 10.477 50.506 20.601 10.000 120.804 50.646 20.804 10.344 20.777 10.984 10.671 10.879 20.936 10.342 40.632 70.449 30.817 30.475 90.723 20.798 10.376 80.832 20.693 10.031 90.564 10.510 130.000 10.893 20.905 10.672 160.314 10.000 70.718 10.153 20.542 20.397 20.726 30.752 80.252 70.226 10.916 20.800 10.047 150.807 30.769 10.709 30.630 20.769 10.217 90.000 30.285 10.598 30.846 90.535 20.956 30.000 60.137 110.784 20.464 60.463 130.230 110.000 10.598 30.662 90.000 40.087 20.000 10.135 20.900 10.780 110.703 20.741 10.571 20.149 90.697 50.646 10.000 30.076 10.000 10.025 90.000 30.106 40.981 10.000 10.043 60.113 30.888 10.248 150.404 40.252 50.314 10.220 50.245 10.466 60.366 20.159 20.000 40.149 70.690 20.000 30.531 50.253 20.285 50.460 10.440 40.813 10.230 20.283 50.159 100.000 10.728 10.666 50.958 10.000 10.021 40.252 60.118 40.000 70.445 30.223 100.285 10.194 30.390 20.000 10.475 30.842 70.000 10.455 30.000 10.250 70.458 70.000 10.865 10.000 10.000 10.635 10.359 40.972 10.087 30.447 20.000 10.000 70.000 10.129 20.532 60.446 70.503 30.071 110.135 120.699 30.717 10.097 20.000 10.665 10.000 20.000 21.000 10.752 50.000 20.000 10.000 10.142 80.200 10.259 11.000 10.000 1
Minkowski 34Dpermissive0.253 150.463 150.154 160.102 150.771 150.650 150.932 140.483 150.571 150.710 140.331 150.250 150.492 130.044 60.703 150.419 160.606 160.227 150.621 150.865 160.531 80.771 160.813 130.291 100.484 140.242 150.612 160.282 160.440 160.351 140.299 140.622 150.593 100.027 110.293 120.310 160.000 10.757 130.858 140.737 110.150 80.164 10.368 160.084 70.381 160.142 160.357 140.720 90.214 110.092 130.724 150.596 160.056 130.655 90.525 130.581 140.352 160.594 150.056 160.000 30.014 160.224 140.772 140.205 160.720 150.000 60.159 70.531 150.163 160.294 150.136 160.000 10.169 150.589 140.000 40.000 90.000 10.002 30.663 90.466 160.265 160.582 90.337 100.016 140.559 140.084 160.000 30.000 70.000 10.036 40.000 30.125 30.670 120.000 10.102 20.071 80.164 140.406 90.386 60.046 150.068 160.159 140.117 50.284 150.111 150.094 150.000 40.000 160.197 160.000 30.044 140.013 140.002 130.228 160.307 160.588 110.025 160.545 40.134 140.000 10.655 40.302 140.282 160.000 10.060 20.000 110.035 160.000 70.000 80.097 160.000 110.000 70.005 90.000 10.000 40.096 160.000 10.334 150.000 10.000 120.274 150.000 10.513 130.000 10.000 10.280 80.194 70.897 110.000 90.000 100.000 10.000 70.000 10.108 80.279 160.189 150.141 160.059 120.272 20.307 160.445 90.003 100.000 10.353 150.000 20.026 10.000 110.581 140.001 10.000 10.000 10.093 160.002 70.000 30.000 100.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
AWCS0.305 130.508 130.225 130.142 100.782 130.634 160.937 130.489 140.578 130.721 110.364 140.355 100.515 110.023 90.764 130.523 100.707 130.264 100.633 130.922 130.507 120.886 10.804 140.179 140.436 150.300 110.656 150.529 20.501 140.394 120.296 150.820 50.603 80.131 40.179 160.619 20.000 10.707 150.865 130.773 60.171 70.010 60.484 130.063 120.463 130.254 120.332 150.649 100.220 100.100 100.729 140.613 140.071 120.582 140.628 70.702 40.424 140.749 20.137 140.000 30.142 130.360 120.863 50.305 130.877 90.000 60.173 50.606 110.337 130.478 120.154 140.000 10.253 130.664 80.000 40.000 90.000 10.000 50.626 120.782 100.302 150.602 60.185 120.282 60.651 120.317 120.000 30.000 70.000 10.022 110.000 30.154 10.876 80.000 10.014 80.063 90.029 160.553 70.467 30.084 120.124 130.157 150.049 110.373 130.252 90.097 140.000 40.219 60.542 30.000 30.392 70.172 70.000 140.339 80.417 80.533 130.093 140.115 90.195 80.000 10.516 110.288 150.741 60.000 10.001 90.233 70.056 130.000 70.159 50.334 80.077 90.000 70.000 100.000 10.000 40.749 120.000 10.411 70.000 10.008 110.452 90.000 10.595 90.000 10.000 10.220 90.006 100.894 120.006 80.000 100.000 10.000 70.000 10.112 50.504 80.404 90.551 10.093 40.129 140.484 80.381 160.000 120.000 10.396 140.000 20.000 20.620 30.402 160.000 20.000 10.000 10.142 80.000 80.000 30.512 70.000 1
OctFormer ScanNet200permissive0.326 120.539 90.265 90.131 110.806 80.670 120.943 90.535 110.662 40.705 150.423 80.407 50.505 120.003 100.765 120.582 70.686 140.227 150.680 70.943 100.601 30.854 100.892 50.335 50.417 160.357 90.724 90.453 100.632 60.596 40.432 30.783 100.512 150.021 120.244 140.637 10.000 10.787 110.873 90.743 100.000 160.000 70.534 80.110 30.499 60.289 90.626 60.620 110.168 140.204 20.849 90.679 70.117 40.633 110.684 30.650 70.552 50.684 80.312 30.000 30.175 100.429 100.865 40.413 40.837 110.000 60.145 90.626 80.451 70.487 110.513 30.000 10.529 70.613 120.000 40.033 60.000 10.000 50.828 40.871 30.622 80.587 80.411 70.137 100.645 130.343 110.000 30.000 70.000 10.022 110.000 30.026 160.829 100.000 10.022 70.089 60.842 30.253 140.318 100.296 30.178 100.291 30.224 20.584 20.200 130.132 80.000 40.128 100.227 130.000 30.230 120.047 100.149 70.331 90.412 90.618 60.164 90.102 100.522 10.000 10.655 40.378 120.469 140.000 10.000 100.000 110.105 80.000 70.000 80.483 30.000 110.000 70.028 70.000 10.000 40.906 10.000 10.339 140.000 10.000 120.457 80.000 10.612 70.000 10.000 10.408 30.000 140.900 100.000 90.000 100.000 10.029 60.000 10.074 130.455 140.479 50.427 60.079 80.140 90.496 70.414 130.022 60.000 10.471 130.000 20.000 20.000 110.722 60.000 20.000 10.000 10.138 130.000 80.000 30.000 100.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
GSTran0.334 90.533 110.250 110.179 70.799 100.684 70.940 100.554 80.633 100.741 90.405 100.337 110.560 80.060 50.794 80.517 120.732 100.274 50.647 110.948 70.459 150.849 110.864 80.306 80.648 50.282 130.717 110.496 60.624 80.533 70.363 90.821 40.573 130.009 150.411 40.593 80.000 10.841 40.873 90.704 130.242 50.000 70.495 100.041 150.487 80.304 70.439 120.613 120.133 160.055 150.853 70.634 110.075 110.791 50.601 90.574 150.483 120.669 100.217 90.000 30.198 70.518 50.782 130.345 100.914 50.273 40.193 30.598 130.440 80.499 80.570 10.000 10.381 100.775 30.000 40.063 50.000 10.000 50.712 70.752 130.507 110.512 150.158 150.036 120.773 10.361 100.000 30.000 70.000 10.032 60.000 30.032 140.651 140.000 10.000 90.000 100.831 40.595 40.273 150.229 60.200 80.191 80.000 130.425 90.233 120.125 100.000 40.279 40.213 150.003 10.608 30.044 110.138 80.321 110.408 110.593 100.198 40.205 70.139 120.000 10.614 70.609 70.838 40.000 10.014 50.260 40.080 110.010 50.000 80.136 120.136 40.047 50.000 100.000 10.787 20.797 90.000 10.354 130.000 10.372 30.357 130.000 10.507 150.000 10.000 10.121 100.423 20.903 80.028 40.089 60.000 10.252 30.000 10.072 150.465 120.340 110.189 150.020 150.011 150.320 150.606 60.060 30.000 10.496 80.000 20.000 20.070 90.618 120.000 20.000 10.000 10.139 100.047 40.000 30.558 60.000 1
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 10.697 160.441 150.683 150.235 130.609 160.895 150.476 140.816 150.770 160.186 130.634 60.216 160.734 80.340 150.471 150.307 150.293 160.591 160.542 140.076 70.205 150.464 140.000 10.484 160.832 160.766 70.052 140.000 70.413 150.059 130.418 150.222 150.318 160.609 130.206 120.112 80.743 130.625 130.076 80.579 150.548 120.590 130.371 150.552 160.081 150.003 20.142 130.201 150.638 160.233 150.686 160.000 60.142 100.444 160.375 120.247 160.198 130.000 10.128 160.454 160.019 20.097 10.000 10.000 50.553 130.557 150.373 120.545 130.164 130.014 150.547 150.174 140.000 30.002 50.000 10.037 30.000 30.063 90.664 130.000 10.000 90.130 20.170 130.152 160.335 90.079 130.110 140.175 130.098 80.175 160.166 140.045 160.207 20.014 130.465 50.000 30.001 160.001 160.046 110.299 140.327 150.537 120.033 150.012 160.186 90.000 10.205 150.377 130.463 150.000 10.058 30.000 110.055 140.041 10.000 80.105 150.000 110.000 70.000 100.000 10.000 40.398 140.000 10.308 160.000 10.000 120.319 140.000 10.543 110.000 10.000 10.062 140.004 120.862 150.000 90.000 100.000 10.000 70.000 10.123 40.316 150.225 140.250 120.094 30.180 60.332 130.441 100.000 120.000 10.310 160.000 20.000 20.000 110.592 130.000 20.000 10.000 10.203 20.000 80.000 30.000 100.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
IMFSegNet0.334 80.532 120.251 100.179 60.799 100.683 80.940 100.555 70.631 110.740 100.406 90.336 120.560 80.062 40.795 70.518 110.733 90.274 50.646 120.947 80.458 160.848 130.862 90.305 90.649 40.284 120.713 120.495 70.626 70.527 80.363 90.820 50.574 120.010 140.411 40.597 60.000 10.842 30.873 90.704 130.246 40.000 70.495 100.041 150.486 90.305 60.444 110.604 140.134 150.055 150.852 80.633 120.076 80.792 40.612 80.573 160.484 110.668 110.216 110.000 30.197 80.518 50.784 120.344 110.908 60.283 30.190 40.599 120.439 90.496 100.569 20.000 10.392 80.776 20.000 40.064 40.000 10.000 50.710 80.756 120.508 100.512 150.159 140.034 130.773 10.363 90.000 30.000 70.000 10.032 60.000 30.029 150.648 150.000 10.000 90.000 100.830 50.595 40.274 140.228 70.206 70.188 110.000 130.425 90.237 110.123 110.000 40.277 50.214 140.003 10.610 20.044 110.124 90.320 130.408 110.594 90.196 60.213 60.139 120.000 10.615 60.618 60.839 30.000 10.014 50.260 40.080 110.025 20.000 80.139 110.135 50.035 60.000 100.000 10.793 10.799 80.000 10.357 120.000 10.369 40.359 120.000 10.512 140.000 10.000 10.120 110.424 10.903 80.027 50.091 50.000 10.245 40.000 10.073 140.457 130.340 110.191 140.021 140.009 160.322 140.608 50.060 30.000 10.494 90.000 20.000 20.068 100.624 100.000 20.000 10.000 10.139 100.047 40.000 30.561 50.000 1
BFANet ScanNet200permissive0.360 40.553 60.293 40.193 40.827 40.689 40.970 30.528 120.661 60.753 60.436 70.378 70.469 140.042 70.810 30.654 10.760 40.266 90.659 90.973 30.574 40.849 110.897 40.382 20.546 120.372 80.698 130.491 80.617 90.526 90.436 10.764 130.476 160.101 60.409 60.585 90.000 10.835 50.901 30.810 50.102 120.000 70.688 20.096 50.483 100.264 110.612 80.591 150.358 20.161 50.863 50.707 40.128 20.814 20.669 50.629 90.563 40.651 130.258 40.000 30.194 90.494 80.806 110.394 60.953 40.000 60.233 10.757 40.508 50.556 30.476 50.000 10.573 50.741 60.000 40.000 90.000 10.000 50.000 160.852 50.678 30.616 50.460 40.338 30.710 40.534 40.000 30.025 40.000 10.043 20.000 30.056 100.493 160.000 10.000 90.109 40.785 60.590 60.298 120.282 40.143 120.262 40.053 100.526 40.337 50.215 10.000 40.135 80.510 40.000 30.596 40.043 130.511 30.321 110.459 20.772 20.124 120.060 130.266 50.000 10.574 90.568 90.653 100.000 10.093 10.298 20.239 20.000 70.516 20.129 130.284 20.000 70.431 10.000 10.000 40.848 60.000 10.492 10.000 10.376 20.522 50.000 10.469 160.000 10.000 10.330 60.151 80.875 140.000 90.254 30.000 10.000 70.000 10.088 110.661 10.481 40.255 110.105 10.139 100.666 40.641 30.000 120.000 10.614 20.000 20.000 20.000 110.921 10.000 20.000 10.000 10.497 10.000 80.000 30.000 100.000 1
LGroundpermissive0.272 140.485 140.184 140.106 140.778 140.676 110.932 140.479 160.572 140.718 130.399 110.265 140.453 150.085 30.745 140.446 140.726 120.232 140.622 140.901 140.512 110.826 140.786 150.178 150.549 110.277 140.659 140.381 140.518 130.295 160.323 130.777 110.599 90.028 100.321 100.363 150.000 10.708 140.858 140.746 90.063 130.022 50.457 140.077 90.476 110.243 140.402 130.397 160.233 90.077 140.720 160.610 150.103 50.629 120.437 160.626 100.446 130.702 50.190 120.005 10.058 150.322 130.702 150.244 140.768 130.000 60.134 120.552 140.279 150.395 140.147 150.000 10.207 140.612 130.000 40.000 90.000 10.000 50.658 100.566 140.323 140.525 140.229 110.179 80.467 160.154 150.000 30.002 50.000 10.051 10.000 30.127 20.703 110.000 10.000 90.216 10.112 150.358 110.547 10.187 80.092 150.156 160.055 90.296 140.252 90.143 50.000 40.014 130.398 70.000 30.028 150.173 60.000 140.265 150.348 140.415 150.179 70.019 150.218 70.000 10.597 80.274 160.565 120.000 10.012 70.000 110.039 150.022 30.000 80.117 140.000 110.000 70.000 100.000 10.000 40.324 150.000 10.384 80.000 10.000 120.251 160.000 10.566 100.000 10.000 10.066 130.404 30.886 130.199 20.000 100.000 10.059 50.000 10.136 10.540 50.127 160.295 100.085 60.143 70.514 60.413 140.000 120.000 10.498 70.000 20.000 20.000 110.623 110.000 20.000 10.000 10.132 150.000 80.000 30.000 100.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv