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 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 by
PTv3 ScanNet2000.393 10.592 10.330 10.216 10.520 10.109 20.108 110.000 10.337 10.000 10.310 90.394 60.494 90.753 80.848 10.256 20.717 30.000 30.842 10.192 20.065 20.449 60.346 20.546 40.190 80.000 50.384 40.000 10.000 30.218 10.505 10.791 10.000 10.136 20.000 20.903 10.073 100.687 40.000 50.168 10.551 30.387 60.941 10.000 10.000 20.397 80.654 30.000 80.714 30.759 100.752 50.118 40.264 20.926 10.000 10.048 30.575 20.000 70.597 10.366 10.755 10.469 10.474 10.798 10.140 60.617 10.692 40.000 40.592 20.971 10.188 30.000 10.133 50.593 10.349 10.650 20.717 50.699 10.455 10.790 10.523 30.636 10.301 10.000 10.622 20.000 70.017 100.259 20.000 30.921 20.337 10.733 10.210 10.514 10.860 60.407 10.000 10.688 10.109 60.000 100.000 40.000 10.151 20.671 40.782 10.115 80.641 10.903 10.349 10.616 20.088 40.832 30.000 30.480 20.000 10.428 10.000 20.497 70.000 10.000 50.000 10.662 20.690 10.612 10.828 10.575 10.000 10.404 40.644 10.325 40.887 20.728 10.009 110.134 50.026 120.000 10.761 10.731 10.172 40.077 20.528 30.727 30.000 10.603 40.220 20.022 20.000 10.740 10.000 20.000 10.661 20.586 10.566 10.436 40.531 20.978 10.457 10.708 20.583 30.141 70.748 10.000 10.026 10.822 10.871 30.879 50.000 10.851 10.405 20.914 10.000 10.682 20.000 100.281 20.738 10.463 5
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)
PPT-SpUNet-F.T.0.332 70.556 30.270 40.123 90.519 20.091 40.349 20.000 10.000 30.000 10.339 60.383 70.498 80.833 40.807 30.241 30.584 40.000 30.755 40.124 50.000 60.608 20.330 50.530 70.314 10.000 50.374 50.000 10.000 30.197 20.459 40.000 60.000 10.117 30.000 20.876 50.095 20.682 50.000 50.086 60.518 50.433 20.930 20.000 10.000 20.563 30.542 90.077 50.715 20.858 60.756 30.008 120.171 70.874 50.000 10.039 40.550 60.000 70.545 40.256 60.657 60.453 30.351 50.449 80.213 30.392 70.611 80.000 40.037 100.946 40.138 90.000 10.000 80.063 60.308 20.537 50.796 30.673 20.323 80.392 70.400 90.509 60.000 30.000 10.649 10.000 70.023 70.000 70.000 30.914 50.002 110.506 110.163 60.359 60.872 40.000 70.000 10.623 40.112 40.001 90.000 40.000 10.021 40.753 10.565 110.150 20.579 20.806 80.267 40.616 20.042 110.783 80.000 30.374 80.000 10.000 40.000 20.620 50.000 10.000 50.000 10.572 100.634 30.350 70.792 30.000 70.000 10.376 60.535 40.378 30.855 40.672 20.074 80.000 70.185 50.000 10.727 70.660 70.076 120.000 70.432 70.646 60.000 10.594 60.006 100.000 50.000 10.658 40.000 20.000 10.661 20.549 50.300 90.291 80.045 90.942 70.304 40.600 60.572 40.135 110.695 30.000 10.008 50.793 40.942 10.899 20.000 10.816 40.181 70.897 20.000 10.679 30.223 30.264 30.691 30.345 10
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
OA-CNN-L_ScanNet2000.333 60.558 20.269 60.124 80.448 100.080 60.272 30.000 10.000 30.000 10.342 50.515 20.524 50.713 120.789 50.158 80.384 70.000 30.806 30.125 40.000 60.496 40.332 40.498 110.227 60.024 20.474 10.000 10.003 20.071 60.487 20.000 60.000 10.110 50.000 20.876 50.013 120.703 10.000 50.076 70.473 80.355 70.906 40.000 10.000 20.476 50.706 10.000 80.672 80.835 80.748 60.015 110.223 40.860 60.000 10.000 80.572 40.000 70.509 60.313 50.662 20.398 90.396 30.411 100.276 10.527 20.711 30.000 40.076 80.946 40.166 50.000 10.022 60.160 40.183 80.493 80.699 60.637 30.403 30.330 90.406 80.526 50.024 20.000 10.392 80.000 70.016 110.000 70.196 20.915 40.112 70.557 60.197 20.352 70.877 20.000 70.000 10.592 90.103 80.000 100.067 10.000 10.089 30.735 30.625 70.130 70.568 40.836 60.271 30.534 60.043 100.799 60.001 20.445 30.000 10.000 40.024 10.661 20.000 10.262 20.000 10.591 50.517 100.373 60.788 50.021 60.000 10.455 10.517 60.320 50.823 70.200 120.001 120.150 40.100 70.000 10.736 60.668 50.103 100.052 40.662 10.720 40.000 10.602 50.112 40.002 40.000 10.637 60.000 20.000 10.621 70.569 20.398 60.412 50.234 70.949 40.363 20.492 100.495 60.251 40.665 60.000 10.001 70.805 30.833 50.794 70.000 10.821 30.314 50.843 80.000 10.560 60.245 20.262 40.713 20.370 9
OctFormer ScanNet200permissive0.326 80.539 70.265 70.131 70.499 40.110 10.522 10.000 10.000 30.000 10.318 80.427 40.455 100.743 100.765 80.175 70.842 10.000 30.828 20.204 10.033 30.429 70.335 30.601 10.312 20.000 50.357 70.000 10.000 30.047 80.423 60.000 60.000 10.105 60.000 20.873 70.079 80.670 80.000 50.117 30.471 90.432 30.829 80.000 10.000 20.584 20.417 120.089 40.684 70.837 70.705 110.021 100.178 60.892 30.000 10.028 50.505 80.000 70.457 70.200 90.662 20.412 70.244 100.496 60.000 120.451 50.626 60.000 40.102 60.943 70.138 90.000 10.000 80.149 50.291 30.534 60.722 40.632 40.331 70.253 110.453 60.487 80.000 30.000 10.479 40.000 70.022 80.000 70.000 30.900 60.128 60.684 20.164 50.413 20.854 80.000 70.000 10.512 110.074 120.003 80.000 40.000 10.000 60.469 100.613 80.132 60.529 50.871 20.227 110.582 50.026 120.787 70.000 30.339 100.000 10.000 40.000 20.626 40.000 10.029 40.000 10.587 60.612 50.411 50.724 70.000 70.000 10.407 30.552 30.513 10.849 50.655 30.408 20.000 70.296 20.000 10.686 100.645 90.145 60.022 50.414 90.633 70.000 10.637 10.224 10.000 50.000 10.650 50.000 20.000 10.622 60.535 70.343 70.483 30.230 80.943 60.289 50.618 50.596 20.140 80.679 50.000 10.022 20.783 60.620 90.906 10.000 10.806 60.137 90.865 30.000 10.378 80.000 100.168 120.680 50.227 11
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
BFANet ScanNet200permissive0.360 20.553 40.293 20.193 20.483 60.096 30.266 40.000 10.000 30.000 10.298 100.255 90.661 10.810 50.810 20.194 60.785 20.000 30.000 120.161 30.000 60.494 50.382 10.574 20.258 30.000 50.372 60.000 10.000 30.043 90.436 50.000 60.000 10.239 10.000 20.901 20.105 10.689 20.025 20.128 20.614 10.436 10.493 120.000 10.000 20.526 40.546 80.109 30.651 100.953 20.753 40.101 50.143 80.897 20.000 10.431 10.469 100.000 70.522 50.337 30.661 40.459 20.409 20.666 30.102 90.508 40.757 20.000 40.060 90.970 20.497 10.000 10.376 20.511 20.262 40.688 10.921 10.617 50.321 90.590 30.491 50.556 30.000 30.000 10.481 30.093 10.043 20.284 10.000 30.875 100.135 50.669 30.124 80.394 40.849 90.298 20.000 10.476 120.088 100.042 50.000 40.000 10.254 10.653 60.741 30.215 10.573 30.852 40.266 50.654 10.056 90.835 10.000 30.492 10.000 10.000 40.000 20.612 60.000 10.000 50.000 10.616 30.469 120.460 30.698 90.516 20.000 10.378 50.563 20.476 20.863 30.574 60.330 40.000 70.282 30.000 10.760 20.710 20.233 10.000 70.641 20.814 10.000 10.585 70.053 80.000 50.000 10.629 70.000 20.000 10.678 10.528 80.534 20.129 90.596 10.973 20.264 70.772 10.526 50.139 90.707 20.000 10.000 80.764 90.591 110.848 60.000 10.827 20.338 30.806 90.000 10.568 50.151 50.358 10.659 70.510 3
CeCo0.340 40.551 60.247 80.181 30.475 80.057 120.142 90.000 10.000 30.000 10.387 30.463 30.499 70.924 20.774 70.213 40.257 80.000 30.546 100.100 80.006 50.615 10.177 120.534 50.246 40.000 50.400 20.000 10.338 10.006 110.484 30.609 20.000 10.083 80.000 20.873 70.089 50.661 90.000 50.048 110.560 20.408 50.892 50.000 10.000 20.586 10.616 50.000 80.692 60.900 30.721 70.162 10.228 30.860 60.000 10.000 80.575 20.083 30.550 30.347 20.624 80.410 80.360 40.740 20.109 80.321 100.660 50.000 40.121 40.939 80.143 70.000 10.400 10.003 80.190 70.564 30.652 70.615 60.421 20.304 100.579 10.547 40.000 30.000 10.296 90.000 70.030 60.096 40.000 30.916 30.037 80.551 70.171 40.376 50.865 50.286 30.000 10.633 20.102 90.027 60.011 30.000 10.000 60.474 90.742 20.133 50.311 80.824 70.242 80.503 90.068 60.828 40.000 30.429 40.000 10.063 30.000 20.781 10.000 10.000 50.000 10.665 10.633 40.450 40.818 20.000 70.000 10.429 20.532 50.226 80.825 60.510 80.377 30.709 10.079 90.000 10.753 30.683 30.102 110.063 30.401 110.620 90.000 10.619 20.000 110.000 50.000 10.595 100.000 20.000 10.345 90.564 30.411 50.603 10.384 40.945 50.266 60.643 40.367 90.304 10.663 70.000 10.010 30.726 100.767 60.898 30.000 10.784 80.435 10.861 50.000 10.447 70.000 100.257 50.656 80.377 8
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
L3DETR-ScanNet_2000.336 50.533 80.279 30.155 50.508 30.073 80.101 120.000 10.058 20.000 10.294 110.233 110.548 30.927 10.788 60.264 10.463 60.000 30.638 70.098 100.014 40.411 80.226 80.525 80.225 70.010 30.397 30.000 10.000 30.192 30.380 90.598 30.000 10.117 30.000 20.883 40.082 70.689 20.000 50.032 120.549 40.417 40.910 30.000 10.000 20.448 60.613 60.000 80.697 50.960 10.759 20.158 20.293 10.883 40.000 10.312 20.583 10.079 40.422 90.068 120.660 50.418 50.298 70.430 90.114 70.526 30.776 10.051 20.679 10.946 40.152 60.000 10.183 40.000 100.211 50.511 70.409 110.565 70.355 50.448 50.512 40.557 20.000 30.000 10.420 60.000 70.007 120.104 30.000 30.125 120.330 20.514 100.146 70.321 80.860 60.174 60.000 10.629 30.075 110.000 100.000 40.000 10.002 50.671 40.712 40.141 40.339 70.856 30.261 70.529 70.067 70.835 10.000 30.369 90.000 10.259 20.000 20.629 30.000 10.487 10.000 10.579 80.646 20.107 120.720 80.122 50.000 10.333 90.505 70.303 60.908 10.503 100.565 10.074 60.324 10.000 10.740 50.661 60.109 90.000 70.427 80.563 120.000 10.579 80.108 50.000 50.000 10.664 30.000 20.000 10.641 50.539 60.416 40.515 20.256 60.940 80.312 30.209 120.620 10.138 100.636 80.000 10.000 80.775 80.861 40.765 80.000 10.801 70.119 100.860 60.000 10.687 10.001 90.192 110.679 60.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
PonderV2 ScanNet2000.346 30.552 50.270 50.175 40.497 50.070 90.239 50.000 10.000 30.000 10.232 120.412 50.584 20.842 30.804 40.212 50.540 50.000 30.433 110.106 70.000 60.590 30.290 70.548 30.243 50.000 50.356 80.000 10.000 30.062 70.398 80.441 50.000 10.104 70.000 20.888 30.076 90.682 50.030 10.094 50.491 70.351 80.869 70.000 10.063 10.403 70.700 20.000 80.660 90.881 40.761 10.050 70.186 50.852 80.000 10.007 60.570 50.100 20.565 20.326 40.641 70.431 40.290 90.621 40.259 20.408 60.622 70.125 10.082 70.950 30.179 40.000 10.263 30.424 30.193 60.558 40.880 20.545 80.375 40.727 20.445 70.499 70.000 30.000 10.475 50.002 50.034 50.083 50.000 30.924 10.290 30.636 40.115 90.400 30.874 30.186 50.000 10.611 50.128 20.113 20.000 40.000 10.000 60.584 70.636 60.103 90.385 60.843 50.283 20.603 40.080 50.825 50.000 30.377 70.000 10.000 40.000 20.457 80.000 10.000 50.000 10.574 90.608 60.481 20.792 30.394 30.000 10.357 70.503 80.261 70.817 80.504 90.304 50.472 30.115 60.000 10.750 40.677 40.202 20.000 70.509 40.729 20.000 10.519 90.000 110.000 50.000 10.620 90.000 20.000 10.660 40.560 40.486 30.384 60.346 50.952 30.247 90.667 30.436 70.269 30.691 40.000 10.010 30.787 50.889 20.880 40.000 10.810 50.336 40.860 60.000 10.606 40.009 60.248 60.681 40.392 7
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.
LGroundpermissive0.272 100.485 100.184 100.106 100.476 70.077 70.218 60.000 10.000 30.000 10.547 10.295 80.540 40.746 90.745 100.058 110.112 110.005 10.658 60.077 120.000 60.322 100.178 110.512 90.190 80.199 10.277 100.000 10.000 30.173 40.399 70.000 60.000 10.039 110.000 20.858 100.085 60.676 70.002 30.103 40.498 60.323 90.703 90.000 10.000 20.296 100.549 70.216 10.702 40.768 90.718 90.028 80.092 110.786 110.000 10.000 80.453 110.022 50.251 120.252 70.572 100.348 100.321 60.514 50.063 100.279 110.552 100.000 40.019 110.932 100.132 110.000 10.000 80.000 100.156 120.457 100.623 80.518 90.265 110.358 80.381 100.395 100.000 30.000 10.127 120.012 40.051 10.000 70.000 30.886 90.014 90.437 120.179 30.244 100.826 100.000 70.000 10.599 70.136 10.085 30.000 40.000 10.000 60.565 80.612 90.143 30.207 100.566 100.232 100.446 100.127 20.708 100.000 30.384 60.000 10.000 40.000 20.402 90.000 10.059 30.000 10.525 120.566 80.229 90.659 100.000 70.000 10.265 100.446 90.147 110.720 120.597 50.066 90.000 70.187 40.000 10.726 80.467 120.134 80.000 70.413 100.629 80.000 10.363 110.055 70.022 20.000 10.626 80.000 20.000 10.323 100.479 120.154 110.117 100.028 110.901 100.243 100.415 110.295 120.143 60.610 110.000 10.000 80.777 70.397 120.324 110.000 10.778 100.179 80.702 110.000 10.274 120.404 10.233 70.622 100.398 6
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
AWCS0.305 90.508 90.225 90.142 60.463 90.063 100.195 70.000 10.000 30.000 10.467 20.551 10.504 60.773 60.764 90.142 90.029 120.000 30.626 80.100 80.000 60.360 90.179 100.507 100.137 100.006 40.300 90.000 10.000 30.172 50.364 100.512 40.000 10.056 90.000 20.865 90.093 40.634 120.000 50.071 90.396 100.296 110.876 60.000 10.000 20.373 90.436 110.063 70.749 10.877 50.721 70.131 30.124 90.804 100.000 10.000 80.515 70.010 60.452 80.252 70.578 90.417 60.179 120.484 70.171 40.337 90.606 90.000 40.115 50.937 90.142 80.000 10.008 70.000 100.157 110.484 90.402 120.501 100.339 60.553 40.529 20.478 90.000 30.000 10.404 70.001 60.022 80.077 60.000 30.894 80.219 40.628 50.093 100.305 90.886 10.233 40.000 10.603 60.112 40.023 70.000 40.000 10.000 60.741 20.664 50.097 100.253 90.782 90.264 60.523 80.154 10.707 110.000 30.411 50.000 10.000 40.000 20.332 110.000 10.000 50.000 10.602 40.595 70.185 100.656 110.159 40.000 10.355 80.424 100.154 100.729 100.516 70.220 70.620 20.084 80.000 10.707 90.651 80.173 30.014 60.381 120.582 100.000 10.619 20.049 90.000 50.000 10.702 20.000 20.000 10.302 110.489 100.317 80.334 70.392 30.922 90.254 80.533 90.394 80.129 120.613 100.000 10.000 80.820 20.649 80.749 90.000 10.782 90.282 60.863 40.000 10.288 110.006 70.220 80.633 90.542 2
CSC-Pretrainpermissive0.249 120.455 120.171 110.079 120.418 110.059 110.186 80.000 10.000 30.000 10.335 70.250 100.316 110.766 70.697 120.142 90.170 90.003 20.553 90.112 60.097 10.201 120.186 90.476 120.081 110.000 50.216 120.000 10.000 30.001 120.314 120.000 60.000 10.055 100.000 20.832 120.094 30.659 100.002 30.076 70.310 120.293 120.664 110.000 10.000 20.175 120.634 40.130 20.552 120.686 120.700 120.076 60.110 100.770 120.000 10.000 80.430 120.000 70.319 100.166 100.542 120.327 110.205 110.332 110.052 110.375 80.444 120.000 40.012 120.930 120.203 20.000 10.000 80.046 70.175 90.413 110.592 90.471 110.299 100.152 120.340 110.247 120.000 30.000 10.225 100.058 30.037 30.000 70.207 10.862 110.014 90.548 80.033 110.233 110.816 110.000 70.000 10.542 100.123 30.121 10.019 20.000 10.000 60.463 110.454 120.045 120.128 120.557 110.235 90.441 110.063 80.484 120.000 30.308 120.000 10.000 40.000 20.318 120.000 10.000 50.000 10.545 110.543 90.164 110.734 60.000 70.000 10.215 120.371 110.198 90.743 90.205 110.062 100.000 70.079 90.000 10.683 110.547 110.142 70.000 70.441 60.579 110.000 10.464 100.098 60.041 10.000 10.590 110.000 20.000 10.373 80.494 90.174 100.105 110.001 120.895 110.222 110.537 80.307 110.180 50.625 90.000 10.000 80.591 120.609 100.398 100.000 10.766 120.014 120.638 120.000 10.377 90.004 80.206 100.609 120.465 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 110.463 110.154 120.102 110.381 120.084 50.134 100.000 10.000 30.000 10.386 40.141 120.279 120.737 110.703 110.014 120.164 100.000 30.663 50.092 110.000 60.224 110.291 60.531 60.056 120.000 50.242 110.000 10.000 30.013 100.331 110.000 60.000 10.035 120.001 10.858 100.059 110.650 110.000 50.056 100.353 110.299 100.670 100.000 10.000 20.284 110.484 100.071 60.594 110.720 110.710 100.027 90.068 120.813 90.000 10.005 70.492 90.164 10.274 110.111 110.571 110.307 120.293 80.307 120.150 50.163 120.531 110.002 30.545 30.932 100.093 120.000 10.000 80.002 90.159 100.368 120.581 100.440 120.228 120.406 60.282 120.294 110.000 30.000 10.189 110.060 20.036 40.000 70.000 30.897 70.000 120.525 90.025 120.205 120.771 120.000 70.000 10.593 80.108 70.044 40.000 40.000 10.000 60.282 120.589 100.094 110.169 110.466 120.227 110.419 120.125 30.757 90.002 10.334 110.000 10.000 40.000 20.357 100.000 10.000 50.000 10.582 70.513 110.337 80.612 120.000 70.000 10.250 110.352 120.136 120.724 110.655 30.280 60.000 70.046 110.000 10.606 120.559 100.159 50.102 10.445 50.655 50.000 10.310 120.117 30.000 50.000 10.581 120.026 10.000 10.265 120.483 110.084 120.097 120.044 100.865 120.142 120.588 70.351 100.272 20.596 120.000 10.003 60.622 110.720 70.096 120.000 10.771 110.016 110.772 100.000 10.302 100.194 40.214 90.621 110.197 12
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019