Presenting the ScanNet200 Benchmark

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

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

ScanNet200 Benchmark

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 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 by
CeCo0.340 30.551 50.247 70.181 20.475 70.057 110.142 80.000 10.000 30.000 10.387 30.463 30.499 60.924 20.774 60.213 40.257 70.000 30.546 100.100 70.006 50.615 10.177 110.534 40.246 30.000 50.400 20.000 10.338 10.006 100.484 30.609 20.000 10.083 70.000 20.873 60.089 40.661 80.000 40.048 100.560 10.408 40.892 50.000 10.000 20.586 10.616 50.000 70.692 60.900 20.721 60.162 10.228 30.860 50.000 10.000 70.575 20.083 30.550 30.347 20.624 70.410 70.360 30.740 20.109 80.321 90.660 40.000 40.121 40.939 70.143 60.000 10.400 10.003 70.190 60.564 20.652 60.615 50.421 20.304 90.579 10.547 30.000 30.000 10.296 80.000 60.030 50.096 30.000 30.916 30.037 70.551 60.171 40.376 40.865 50.286 20.000 10.633 20.102 90.027 50.011 30.000 10.000 50.474 80.742 20.133 40.311 70.824 60.242 70.503 80.068 60.828 30.000 30.429 30.000 10.063 30.000 20.781 10.000 10.000 50.000 10.665 10.633 40.450 30.818 20.000 60.000 10.429 20.532 40.226 70.825 50.510 70.377 30.709 10.079 80.000 10.753 20.683 20.102 100.063 30.401 100.620 80.000 10.619 20.000 100.000 50.000 10.595 90.000 20.000 10.345 80.564 30.411 40.603 10.384 30.945 40.266 60.643 30.367 80.304 10.663 60.000 10.010 30.726 90.767 60.898 30.000 10.784 70.435 10.861 50.000 10.447 60.000 90.257 40.656 70.377 7
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
AWCS0.305 80.508 80.225 80.142 50.463 80.063 90.195 60.000 10.000 30.000 10.467 20.551 10.504 50.773 50.764 80.142 80.029 110.000 30.626 80.100 70.000 60.360 80.179 90.507 90.137 90.006 40.300 80.000 10.000 30.172 50.364 90.512 40.000 10.056 80.000 20.865 80.093 30.634 110.000 40.071 80.396 90.296 100.876 60.000 10.000 20.373 80.436 100.063 60.749 10.877 40.721 60.131 30.124 80.804 90.000 10.000 70.515 70.010 60.452 70.252 60.578 80.417 50.179 110.484 60.171 40.337 80.606 80.000 40.115 50.937 80.142 70.000 10.008 60.000 90.157 100.484 80.402 110.501 90.339 60.553 30.529 20.478 80.000 30.000 10.404 60.001 50.022 70.077 50.000 30.894 80.219 40.628 40.093 90.305 80.886 10.233 30.000 10.603 60.112 40.023 60.000 40.000 10.000 50.741 20.664 40.097 90.253 80.782 80.264 50.523 70.154 10.707 100.000 30.411 40.000 10.000 40.000 20.332 100.000 10.000 50.000 10.602 30.595 70.185 90.656 100.159 30.000 10.355 70.424 90.154 90.729 90.516 60.220 60.620 20.084 70.000 10.707 80.651 70.173 20.014 60.381 110.582 90.000 10.619 20.049 80.000 50.000 10.702 20.000 20.000 10.302 100.489 90.317 70.334 70.392 20.922 80.254 70.533 80.394 70.129 110.613 90.000 10.000 80.820 20.649 80.749 80.000 10.782 80.282 50.863 40.000 10.288 100.006 60.220 70.633 80.542 2
PTv3 ScanNet2000.393 10.592 10.330 10.216 10.520 10.109 20.108 100.000 10.337 10.000 10.310 90.394 60.494 80.753 70.848 10.256 20.717 20.000 30.842 10.192 20.065 20.449 50.346 10.546 30.190 70.000 50.384 40.000 10.000 30.218 10.505 10.791 10.000 10.136 10.000 20.903 10.073 90.687 30.000 40.168 10.551 20.387 50.941 10.000 10.000 20.397 70.654 30.000 70.714 30.759 90.752 40.118 40.264 20.926 10.000 10.048 20.575 20.000 70.597 10.366 10.755 10.469 10.474 10.798 10.140 60.617 10.692 30.000 40.592 20.971 10.188 20.000 10.133 40.593 10.349 10.650 10.717 40.699 10.455 10.790 10.523 30.636 10.301 10.000 10.622 20.000 60.017 90.259 10.000 30.921 20.337 10.733 10.210 10.514 10.860 60.407 10.000 10.688 10.109 60.000 90.000 40.000 10.151 10.671 40.782 10.115 70.641 10.903 10.349 10.616 10.088 40.832 20.000 30.480 10.000 10.428 10.000 20.497 60.000 10.000 50.000 10.662 20.690 10.612 10.828 10.575 10.000 10.404 40.644 10.325 30.887 20.728 10.009 100.134 50.026 110.000 10.761 10.731 10.172 30.077 20.528 20.727 20.000 10.603 40.220 20.022 20.000 10.740 10.000 20.000 10.661 10.586 10.566 10.436 40.531 10.978 10.457 10.708 10.583 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 90.281 10.738 10.463 4
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
L3DETR-ScanNet_2000.336 40.533 70.279 20.155 40.508 30.073 70.101 110.000 10.058 20.000 10.294 100.233 100.548 20.927 10.788 50.264 10.463 50.000 30.638 70.098 90.014 40.411 70.226 70.525 70.225 60.010 30.397 30.000 10.000 30.192 30.380 80.598 30.000 10.117 20.000 20.883 30.082 60.689 20.000 40.032 110.549 30.417 30.910 30.000 10.000 20.448 50.613 60.000 70.697 50.960 10.759 20.158 20.293 10.883 30.000 10.312 10.583 10.079 40.422 80.068 110.660 40.418 40.298 60.430 80.114 70.526 30.776 10.051 20.679 10.946 30.152 50.000 10.183 30.000 90.211 40.511 60.409 100.565 60.355 50.448 40.512 40.557 20.000 30.000 10.420 50.000 60.007 110.104 20.000 30.125 110.330 20.514 90.146 70.321 70.860 60.174 50.000 10.629 30.075 100.000 90.000 40.000 10.002 40.671 40.712 30.141 30.339 60.856 30.261 60.529 60.067 70.835 10.000 30.369 80.000 10.259 20.000 20.629 30.000 10.487 10.000 10.579 70.646 20.107 110.720 80.122 40.000 10.333 80.505 60.303 50.908 10.503 90.565 10.074 60.324 10.000 10.740 40.661 50.109 80.000 70.427 70.563 110.000 10.579 70.108 50.000 50.000 10.664 30.000 20.000 10.641 40.539 60.416 30.515 20.256 50.940 70.312 30.209 110.620 10.138 90.636 70.000 10.000 80.775 80.861 40.765 70.000 10.801 60.119 90.860 60.000 10.687 10.001 80.192 100.679 60.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
OctFormer ScanNet200permissive0.326 70.539 60.265 60.131 60.499 40.110 10.522 10.000 10.000 30.000 10.318 80.427 40.455 90.743 90.765 70.175 60.842 10.000 30.828 20.204 10.033 30.429 60.335 20.601 10.312 20.000 50.357 60.000 10.000 30.047 80.423 50.000 60.000 10.105 50.000 20.873 60.079 70.670 70.000 40.117 20.471 80.432 20.829 80.000 10.000 20.584 20.417 110.089 30.684 70.837 60.705 100.021 90.178 60.892 20.000 10.028 40.505 80.000 70.457 60.200 80.662 20.412 60.244 90.496 50.000 110.451 40.626 50.000 40.102 60.943 60.138 80.000 10.000 70.149 40.291 30.534 50.722 30.632 40.331 70.253 100.453 50.487 70.000 30.000 10.479 30.000 60.022 70.000 60.000 30.900 60.128 50.684 20.164 50.413 20.854 80.000 60.000 10.512 110.074 110.003 70.000 40.000 10.000 50.469 90.613 70.132 50.529 40.871 20.227 100.582 40.026 110.787 60.000 30.339 90.000 10.000 40.000 20.626 40.000 10.029 40.000 10.587 50.612 50.411 40.724 70.000 60.000 10.407 30.552 20.513 10.849 40.655 30.408 20.000 70.296 20.000 10.686 90.645 80.145 50.022 50.414 80.633 60.000 10.637 10.224 10.000 50.000 10.650 50.000 20.000 10.622 50.535 70.343 60.483 30.230 70.943 50.289 50.618 40.596 20.140 80.679 40.000 10.022 20.783 60.620 90.906 10.000 10.806 50.137 80.865 30.000 10.378 70.000 90.168 110.680 50.227 10
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
PonderV2 ScanNet2000.346 20.552 40.270 40.175 30.497 50.070 80.239 40.000 10.000 30.000 10.232 110.412 50.584 10.842 30.804 30.212 50.540 40.000 30.433 110.106 60.000 60.590 30.290 60.548 20.243 40.000 50.356 70.000 10.000 30.062 70.398 70.441 50.000 10.104 60.000 20.888 20.076 80.682 40.030 10.094 40.491 60.351 70.869 70.000 10.063 10.403 60.700 20.000 70.660 90.881 30.761 10.050 60.186 50.852 70.000 10.007 50.570 50.100 20.565 20.326 30.641 60.431 30.290 80.621 30.259 20.408 50.622 60.125 10.082 70.950 20.179 30.000 10.263 20.424 20.193 50.558 30.880 10.545 70.375 40.727 20.445 60.499 60.000 30.000 10.475 40.002 40.034 40.083 40.000 30.924 10.290 30.636 30.115 80.400 30.874 30.186 40.000 10.611 50.128 20.113 20.000 40.000 10.000 50.584 60.636 50.103 80.385 50.843 40.283 20.603 30.080 50.825 40.000 30.377 60.000 10.000 40.000 20.457 70.000 10.000 50.000 10.574 80.608 60.481 20.792 30.394 20.000 10.357 60.503 70.261 60.817 70.504 80.304 40.472 30.115 50.000 10.750 30.677 30.202 10.000 70.509 30.729 10.000 10.519 80.000 100.000 50.000 10.620 80.000 20.000 10.660 30.560 40.486 20.384 60.346 40.952 20.247 80.667 20.436 60.269 30.691 30.000 10.010 30.787 50.889 20.880 40.000 10.810 40.336 30.860 60.000 10.606 40.009 50.248 50.681 40.392 6
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
OA-CNN-L_ScanNet2000.333 50.558 20.269 50.124 70.448 90.080 50.272 30.000 10.000 30.000 10.342 50.515 20.524 40.713 110.789 40.158 70.384 60.000 30.806 30.125 30.000 60.496 40.332 30.498 100.227 50.024 20.474 10.000 10.003 20.071 60.487 20.000 60.000 10.110 40.000 20.876 40.013 110.703 10.000 40.076 60.473 70.355 60.906 40.000 10.000 20.476 40.706 10.000 70.672 80.835 70.748 50.015 100.223 40.860 50.000 10.000 70.572 40.000 70.509 50.313 40.662 20.398 80.396 20.411 90.276 10.527 20.711 20.000 40.076 80.946 30.166 40.000 10.022 50.160 30.183 70.493 70.699 50.637 30.403 30.330 80.406 70.526 40.024 20.000 10.392 70.000 60.016 100.000 60.196 20.915 40.112 60.557 50.197 20.352 60.877 20.000 60.000 10.592 90.103 80.000 90.067 10.000 10.089 20.735 30.625 60.130 60.568 30.836 50.271 30.534 50.043 90.799 50.001 20.445 20.000 10.000 40.024 10.661 20.000 10.262 20.000 10.591 40.517 100.373 50.788 50.021 50.000 10.455 10.517 50.320 40.823 60.200 110.001 110.150 40.100 60.000 10.736 50.668 40.103 90.052 40.662 10.720 30.000 10.602 50.112 40.002 40.000 10.637 60.000 20.000 10.621 60.569 20.398 50.412 50.234 60.949 30.363 20.492 90.495 50.251 40.665 50.000 10.001 70.805 30.833 50.794 60.000 10.821 20.314 40.843 80.000 10.560 50.245 20.262 30.713 20.370 8
PPT-SpUNet-F.T.0.332 60.556 30.270 30.123 80.519 20.091 30.349 20.000 10.000 30.000 10.339 60.383 70.498 70.833 40.807 20.241 30.584 30.000 30.755 40.124 40.000 60.608 20.330 40.530 60.314 10.000 50.374 50.000 10.000 30.197 20.459 40.000 60.000 10.117 20.000 20.876 40.095 10.682 40.000 40.086 50.518 40.433 10.930 20.000 10.000 20.563 30.542 80.077 40.715 20.858 50.756 30.008 110.171 70.874 40.000 10.039 30.550 60.000 70.545 40.256 50.657 50.453 20.351 40.449 70.213 30.392 60.611 70.000 40.037 90.946 30.138 80.000 10.000 70.063 50.308 20.537 40.796 20.673 20.323 80.392 60.400 80.509 50.000 30.000 10.649 10.000 60.023 60.000 60.000 30.914 50.002 100.506 100.163 60.359 50.872 40.000 60.000 10.623 40.112 40.001 80.000 40.000 10.021 30.753 10.565 100.150 10.579 20.806 70.267 40.616 10.042 100.783 70.000 30.374 70.000 10.000 40.000 20.620 50.000 10.000 50.000 10.572 90.634 30.350 60.792 30.000 60.000 10.376 50.535 30.378 20.855 30.672 20.074 70.000 70.185 40.000 10.727 60.660 60.076 110.000 70.432 60.646 50.000 10.594 60.006 90.000 50.000 10.658 40.000 20.000 10.661 10.549 50.300 80.291 80.045 80.942 60.304 40.600 50.572 40.135 100.695 20.000 10.008 50.793 40.942 10.899 20.000 10.816 30.181 60.897 20.000 10.679 30.223 30.264 20.691 30.345 9
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
LGroundpermissive0.272 90.485 90.184 90.106 90.476 60.077 60.218 50.000 10.000 30.000 10.547 10.295 80.540 30.746 80.745 90.058 100.112 100.005 10.658 60.077 110.000 60.322 90.178 100.512 80.190 70.199 10.277 90.000 10.000 30.173 40.399 60.000 60.000 10.039 100.000 20.858 90.085 50.676 60.002 20.103 30.498 50.323 80.703 90.000 10.000 20.296 90.549 70.216 10.702 40.768 80.718 80.028 70.092 100.786 100.000 10.000 70.453 100.022 50.251 110.252 60.572 90.348 90.321 50.514 40.063 90.279 100.552 90.000 40.019 100.932 90.132 100.000 10.000 70.000 90.156 110.457 90.623 70.518 80.265 100.358 70.381 90.395 90.000 30.000 10.127 110.012 30.051 10.000 60.000 30.886 90.014 80.437 110.179 30.244 90.826 90.000 60.000 10.599 70.136 10.085 30.000 40.000 10.000 50.565 70.612 80.143 20.207 90.566 90.232 90.446 90.127 20.708 90.000 30.384 50.000 10.000 40.000 20.402 80.000 10.059 30.000 10.525 110.566 80.229 80.659 90.000 60.000 10.265 90.446 80.147 100.720 110.597 50.066 80.000 70.187 30.000 10.726 70.467 110.134 70.000 70.413 90.629 70.000 10.363 100.055 70.022 20.000 10.626 70.000 20.000 10.323 90.479 110.154 100.117 90.028 100.901 90.243 90.415 100.295 110.143 60.610 100.000 10.000 80.777 70.397 110.324 100.000 10.778 90.179 70.702 100.000 10.274 110.404 10.233 60.622 90.398 5
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrainpermissive0.249 110.455 110.171 100.079 110.418 100.059 100.186 70.000 10.000 30.000 10.335 70.250 90.316 100.766 60.697 110.142 80.170 80.003 20.553 90.112 50.097 10.201 110.186 80.476 110.081 100.000 50.216 110.000 10.000 30.001 110.314 110.000 60.000 10.055 90.000 20.832 110.094 20.659 90.002 20.076 60.310 110.293 110.664 110.000 10.000 20.175 110.634 40.130 20.552 110.686 110.700 110.076 50.110 90.770 110.000 10.000 70.430 110.000 70.319 90.166 90.542 110.327 100.205 100.332 100.052 100.375 70.444 110.000 40.012 110.930 110.203 10.000 10.000 70.046 60.175 80.413 100.592 80.471 100.299 90.152 110.340 100.247 110.000 30.000 10.225 90.058 20.037 20.000 60.207 10.862 100.014 80.548 70.033 100.233 100.816 100.000 60.000 10.542 100.123 30.121 10.019 20.000 10.000 50.463 100.454 110.045 110.128 110.557 100.235 80.441 100.063 80.484 110.000 30.308 110.000 10.000 40.000 20.318 110.000 10.000 50.000 10.545 100.543 90.164 100.734 60.000 60.000 10.215 110.371 100.198 80.743 80.205 100.062 90.000 70.079 80.000 10.683 100.547 100.142 60.000 70.441 50.579 100.000 10.464 90.098 60.041 10.000 10.590 100.000 20.000 10.373 70.494 80.174 90.105 100.001 110.895 100.222 100.537 70.307 100.180 50.625 80.000 10.000 80.591 110.609 100.398 90.000 10.766 110.014 110.638 110.000 10.377 80.004 70.206 90.609 110.465 3
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 100.463 100.154 110.102 100.381 110.084 40.134 90.000 10.000 30.000 10.386 40.141 110.279 110.737 100.703 100.014 110.164 90.000 30.663 50.092 100.000 60.224 100.291 50.531 50.056 110.000 50.242 100.000 10.000 30.013 90.331 100.000 60.000 10.035 110.001 10.858 90.059 100.650 100.000 40.056 90.353 100.299 90.670 100.000 10.000 20.284 100.484 90.071 50.594 100.720 100.710 90.027 80.068 110.813 80.000 10.005 60.492 90.164 10.274 100.111 100.571 100.307 110.293 70.307 110.150 50.163 110.531 100.002 30.545 30.932 90.093 110.000 10.000 70.002 80.159 90.368 110.581 90.440 110.228 110.406 50.282 110.294 100.000 30.000 10.189 100.060 10.036 30.000 60.000 30.897 70.000 110.525 80.025 110.205 110.771 110.000 60.000 10.593 80.108 70.044 40.000 40.000 10.000 50.282 110.589 90.094 100.169 100.466 110.227 100.419 110.125 30.757 80.002 10.334 100.000 10.000 40.000 20.357 90.000 10.000 50.000 10.582 60.513 110.337 70.612 110.000 60.000 10.250 100.352 110.136 110.724 100.655 30.280 50.000 70.046 100.000 10.606 110.559 90.159 40.102 10.445 40.655 40.000 10.310 110.117 30.000 50.000 10.581 110.026 10.000 10.265 110.483 100.084 110.097 110.044 90.865 110.142 110.588 60.351 90.272 20.596 110.000 10.003 60.622 100.720 70.096 110.000 10.771 100.016 100.772 90.000 10.302 90.194 40.214 80.621 100.197 11
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


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




Method Infoavgalarm clockarmchairbackpackbagballbarbasketbathroom cabinetbathroom counterbathroom stallbathroom stall doorbathroom vanitybathtubbedbenchbicyclebinblackboardblanketblindsboardbookbookshelfbottlebowlboxbroombucketbulletin boardcabinetcalendarcandlecartcase of water bottlescd caseceilingceiling lightchairclockclosetcloset doorcloset rodcloset wallclothesclothes dryercoat rackcoffee kettlecoffee makercoffee tablecolumncomputer towercontainercopiercouchcountercratecupcurtaincushiondecorationdeskdining tabledish rackdishwasherdividerdoordoorframedresserdumbbelldustpanend tablefanfile cabinetfire alarmfire extinguisherfireplacefolded chairfurnitureguitarguitar casehair dryerhandicap barhatheadphonesironing boardjacketkeyboardkeyboard pianokitchen cabinetkitchen counterladderlamplaptoplaundry basketlaundry detergentlaundry hamperledgelightlight switchluggagemachinemailboxmatmattressmicrowavemini fridgemirrormonitormousemusic standnightstandobjectoffice chairottomanovenpaperpaper bagpaper cutterpaper towel dispenserpaper towel rollpersonpianopicturepillarpillowpipeplantplateplungerposterpotted plantpower outletpower stripprinterprojectorprojector screenpurserackradiatorrailrange hoodrecycling binrefrigeratorscaleseatshelfshoeshowershower curtainshower curtain rodshower doorshower floorshower headshower wallsignsinksoap dishsoap dispensersofa chairspeakerstair railstairsstandstoolstorage binstorage containerstorage organizerstovestructurestuffed animalsuitcasetabletelephonetissue boxtoastertoaster oventoilettoilet papertoilet paper dispensertoilet paper holdertoilet seat cover dispensertoweltrash bintrash cantraytubetvtv standvacuum cleanerventwardrobewashing machinewater bottlewater coolerwater pitcherwhiteboardwindowwindowsill
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 by
TD3D Scannet200permissive0.320 20.501 20.264 20.164 20.506 30.062 20.500 10.000 10.000 10.000 10.208 10.431 20.252 31.000 10.733 30.587 20.000 20.008 20.000 30.106 10.000 20.356 10.123 40.686 10.101 20.000 10.152 20.000 10.000 20.226 10.280 30.000 20.000 10.250 10.000 10.619 20.061 30.841 10.000 10.000 20.167 10.194 10.333 20.000 20.000 10.667 20.820 10.250 30.790 41.000 10.879 20.077 10.094 30.708 10.217 20.049 20.634 10.792 10.331 40.033 50.716 20.159 20.396 20.331 40.099 20.415 10.842 10.000 20.458 10.542 10.000 10.101 20.000 10.218 10.513 20.500 20.458 20.104 20.516 10.456 10.268 40.000 10.000 10.400 10.022 10.233 20.143 20.000 10.677 10.400 10.504 50.095 30.083 50.890 20.061 20.000 10.906 10.076 20.231 10.125 20.000 20.003 20.792 30.881 10.000 20.098 30.125 40.498 50.459 20.063 10.715 10.000 20.241 40.000 10.396 20.063 10.605 10.000 10.000 20.000 10.448 50.629 30.202 20.967 10.250 20.038 10.192 10.185 20.083 41.000 11.000 10.857 20.000 20.470 20.012 10.565 30.798 10.621 10.111 10.500 11.000 10.017 20.509 10.000 10.008 11.000 10.525 20.000 10.000 10.332 30.679 10.264 20.333 20.267 11.000 10.549 10.299 50.387 20.328 30.744 40.000 10.000 20.435 51.000 10.283 40.000 10.196 10.817 10.000 10.472 10.222 30.123 40.560 20.156 2
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
CSC-Pretrain Inst.permissive0.209 40.361 50.157 40.085 40.506 20.007 30.500 10.000 10.000 10.000 10.000 50.093 50.221 40.667 40.524 50.400 30.000 20.000 30.000 30.004 40.000 20.000 50.109 50.589 40.000 40.000 10.059 50.000 10.000 20.000 30.322 20.000 20.000 10.000 30.000 10.405 30.055 40.700 50.000 10.000 20.028 40.091 50.083 30.000 20.000 10.667 20.768 20.000 40.807 31.000 10.776 50.000 30.000 50.340 50.000 30.000 30.103 50.000 30.750 10.200 30.634 50.053 50.246 30.677 20.006 50.198 30.432 40.000 20.000 40.050 40.000 10.000 30.000 10.111 50.356 40.500 20.188 50.000 40.220 40.448 20.050 50.000 10.000 10.000 30.000 30.032 50.000 30.000 10.396 20.000 40.573 40.000 50.228 30.747 40.000 30.000 10.573 50.021 50.000 30.000 30.000 20.000 30.500 40.573 30.000 20.000 50.125 40.592 30.364 50.000 30.450 50.000 20.364 20.000 10.000 30.000 20.340 30.000 10.000 20.000 10.610 30.833 10.221 10.702 50.000 30.000 30.135 50.094 40.125 20.571 40.500 40.143 50.000 20.125 30.000 30.618 20.667 40.115 50.000 30.125 21.000 10.000 30.500 20.000 10.000 20.000 20.502 40.000 10.000 10.312 40.248 50.050 40.000 50.000 30.997 30.420 30.500 40.149 50.451 20.748 20.000 10.000 20.636 30.667 50.600 20.000 10.000 30.278 50.000 10.333 40.000 50.294 20.381 50.110 3
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.246 30.413 30.170 30.130 30.455 50.003 50.500 10.000 10.000 10.000 10.017 40.333 40.111 51.000 10.681 40.400 30.000 20.000 31.000 10.003 50.000 20.167 30.190 20.637 20.067 30.000 10.081 30.000 10.000 20.000 30.264 40.000 20.000 10.000 30.000 10.387 40.031 50.754 30.000 10.000 20.151 20.135 20.056 40.000 20.000 10.582 40.589 50.500 20.815 21.000 10.903 10.000 30.097 20.588 40.000 30.000 30.234 30.000 30.500 30.400 10.682 40.156 30.159 40.750 10.046 30.125 40.660 30.000 20.200 20.000 50.000 10.000 30.000 10.164 30.402 30.500 20.373 30.025 30.143 50.426 30.317 20.000 10.000 10.000 30.000 30.063 30.000 30.000 10.000 50.000 40.575 30.250 20.241 20.772 30.000 30.000 10.653 40.034 30.000 30.000 30.000 20.000 31.000 10.561 40.000 20.100 20.500 10.541 40.452 30.000 30.581 30.000 20.364 20.000 10.000 30.000 20.571 20.000 10.000 20.000 10.568 40.511 40.167 30.857 30.000 30.000 30.164 20.112 30.000 50.530 51.000 10.286 30.000 20.125 30.000 30.464 50.706 30.208 40.000 30.125 20.744 40.000 30.500 20.000 10.000 20.000 20.511 30.000 10.000 10.344 20.541 30.068 30.333 20.000 31.000 10.196 40.533 30.318 30.000 40.748 30.000 10.000 20.690 21.000 10.400 30.000 10.000 30.667 30.000 10.333 40.333 20.270 30.399 30.083 4
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.permissive0.203 50.369 40.134 50.078 50.479 40.003 40.500 10.000 10.000 10.000 10.100 20.371 30.300 20.667 40.746 20.400 30.000 20.000 30.000 30.031 30.000 20.074 40.165 30.413 50.000 40.000 10.070 40.000 10.000 20.000 30.221 50.000 20.000 10.000 30.000 10.372 50.070 20.706 40.000 10.000 20.000 50.123 40.033 50.000 20.000 10.422 50.732 30.000 40.778 51.000 10.845 30.000 30.090 40.636 20.000 30.000 30.158 40.000 30.250 50.050 40.693 30.123 40.051 50.385 30.009 40.118 50.406 50.000 20.000 40.200 20.000 10.000 30.000 10.133 40.307 50.500 20.251 40.000 40.281 30.402 40.317 20.000 10.000 10.000 30.000 30.060 40.000 30.000 10.396 20.200 30.669 20.021 40.218 40.720 50.000 30.000 10.696 30.025 40.000 30.000 30.000 20.000 30.125 50.596 20.000 20.191 10.500 10.595 20.369 40.000 30.500 40.000 20.143 50.000 10.000 30.000 20.226 50.000 10.000 20.000 10.701 20.511 40.000 50.851 40.000 30.000 30.150 40.052 50.100 30.981 30.500 40.286 30.000 20.000 50.000 30.545 40.522 50.250 30.000 30.000 50.522 50.000 30.500 20.000 10.000 20.000 20.282 50.000 10.000 10.178 50.382 40.018 50.056 40.000 30.997 30.107 50.677 20.313 40.000 40.726 50.000 10.000 20.583 40.903 40.200 50.000 10.000 30.333 40.000 10.442 20.083 40.109 50.387 40.000 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
Mask3D Scannet2000.388 10.542 10.357 10.237 10.610 10.091 10.125 50.000 10.000 10.000 10.065 30.668 10.451 11.000 10.955 10.640 10.500 10.039 10.125 20.063 20.409 10.311 20.291 10.609 30.266 10.000 10.163 10.000 10.008 10.044 20.496 11.000 10.000 10.018 20.000 10.756 10.573 10.808 20.000 10.010 10.042 30.130 30.552 10.042 10.000 11.000 10.725 40.750 10.883 11.000 10.832 40.024 20.107 10.614 30.226 10.250 10.628 20.792 10.677 20.400 10.741 10.278 10.511 10.077 50.111 10.313 20.715 20.302 10.017 30.200 20.000 10.188 10.000 10.178 20.736 11.000 10.615 10.514 10.409 20.380 50.600 10.000 10.000 10.400 10.013 20.254 10.381 10.000 10.123 40.400 10.839 10.258 10.463 10.926 10.265 10.000 10.857 20.099 10.021 20.500 10.027 10.028 11.000 10.502 50.016 10.076 40.500 10.612 10.578 10.005 20.597 20.194 10.497 10.000 10.500 10.000 20.323 40.000 11.000 10.000 10.748 10.708 20.050 40.890 21.000 10.008 20.151 30.301 11.000 11.000 10.792 30.945 11.000 10.511 10.004 20.753 10.776 20.287 20.020 20.003 40.974 30.033 10.412 50.000 10.000 20.000 20.667 10.000 10.000 10.491 10.676 20.352 10.335 10.060 20.822 50.527 21.000 10.517 10.606 10.853 10.000 10.004 10.806 11.000 10.727 10.000 10.042 20.739 20.000 10.399 30.391 10.504 10.591 10.571 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023


ScanNet Benchmark

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort by
Swin3Dpermissive0.779 40.861 200.818 130.836 180.790 20.875 40.576 50.905 60.704 40.739 10.969 100.611 20.349 100.756 200.958 10.702 430.805 140.708 70.916 310.898 30.801 2
PointConvFormer0.749 170.793 390.790 340.807 350.750 220.856 120.524 260.881 130.588 510.642 250.977 80.591 90.274 450.781 40.929 20.804 60.796 230.642 320.947 90.885 80.715 28
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
PointTransformerV20.752 150.742 650.809 200.872 10.758 140.860 100.552 130.891 120.610 390.687 60.960 170.559 230.304 290.766 140.926 30.767 160.797 220.644 310.942 110.876 160.722 24
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
MSP0.748 190.623 920.804 230.859 30.745 240.824 460.501 350.912 40.690 90.685 80.956 250.567 190.320 230.768 130.918 40.720 320.802 150.676 200.921 280.881 100.779 6
TTT-KD0.773 50.646 890.818 130.809 330.774 80.878 30.581 20.943 10.687 110.704 50.978 40.607 50.336 150.775 80.912 50.838 30.823 20.694 110.967 30.899 20.794 3
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ClickSeg_Semantic0.703 370.774 490.800 250.793 440.760 130.847 240.471 490.802 440.463 920.634 280.968 120.491 460.271 490.726 300.910 60.706 390.815 60.551 750.878 580.833 410.570 75
PTv3 ScanNet0.794 10.941 30.813 170.851 70.782 50.890 20.597 10.916 20.696 70.713 30.979 10.635 10.384 20.793 20.907 70.821 40.790 300.696 100.967 30.903 10.805 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
OctFormerpermissive0.766 70.925 70.808 210.849 90.786 40.846 250.566 90.876 140.690 90.674 130.960 170.576 160.226 650.753 220.904 80.777 120.815 60.722 50.923 270.877 130.776 7
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
ResLFE_HDS0.772 60.939 40.824 60.854 60.771 90.840 290.564 100.900 80.686 120.677 110.961 160.537 290.348 110.769 110.903 90.785 100.815 60.676 200.939 140.880 110.772 8
EQ-Net0.743 240.620 930.799 280.849 90.730 280.822 480.493 420.897 100.664 180.681 90.955 280.562 220.378 30.760 170.903 90.738 240.801 190.673 240.907 350.877 130.745 12
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
PPT-SpUNet-Joint0.766 70.932 50.794 310.829 230.751 210.854 130.540 200.903 70.630 320.672 140.963 140.565 200.357 80.788 30.900 110.737 250.802 150.685 150.950 70.887 60.780 5
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
VMNetpermissive0.746 210.870 180.838 20.858 40.729 290.850 190.501 350.874 150.587 520.658 180.956 250.564 210.299 300.765 150.900 110.716 350.812 110.631 370.939 140.858 260.709 29
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
SAT0.742 250.860 210.765 470.819 260.769 110.848 220.533 220.829 320.663 190.631 290.955 280.586 120.274 450.753 220.896 130.729 260.760 480.666 260.921 280.855 300.733 16
MinkowskiNetpermissive0.736 280.859 220.818 130.832 220.709 330.840 290.521 280.853 220.660 210.643 220.951 430.544 270.286 380.731 290.893 140.675 530.772 380.683 160.874 640.852 330.727 20
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
Mix3Dpermissive0.781 30.964 20.855 10.843 150.781 60.858 110.575 60.831 310.685 130.714 20.979 10.594 70.310 260.801 10.892 150.841 20.819 40.723 40.940 130.887 60.725 22
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
PointMetaBase0.714 350.835 270.785 360.821 240.684 400.846 250.531 240.865 190.614 360.596 460.953 370.500 430.246 610.674 340.888 160.692 450.764 440.624 400.849 790.844 400.675 39
O-CNNpermissive0.762 110.924 80.823 70.844 140.770 100.852 170.577 40.847 260.711 20.640 260.958 200.592 80.217 710.762 160.888 160.758 190.813 100.726 20.932 220.868 190.744 13
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
Retro-FPN0.744 230.842 260.800 250.767 530.740 250.836 340.541 180.914 30.672 170.626 300.958 200.552 260.272 470.777 60.886 180.696 440.801 190.674 230.941 120.858 260.717 25
Peng Xiang*, Xin Wen*, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
CU-Hybrid Net0.764 90.924 80.819 110.840 160.757 160.853 150.580 30.848 240.709 30.643 220.958 200.587 110.295 320.753 220.884 190.758 190.815 60.725 30.927 240.867 200.743 14
SparseConvNet0.725 310.647 880.821 90.846 120.721 310.869 60.533 220.754 560.603 450.614 340.955 280.572 180.325 210.710 320.870 200.724 300.823 20.628 380.934 190.865 220.683 37
RPN0.736 280.776 470.790 340.851 70.754 180.854 130.491 440.866 180.596 490.686 70.955 280.536 300.342 130.624 480.869 210.787 90.802 150.628 380.927 240.875 170.704 31
PointTransformer++0.725 310.727 730.811 190.819 260.765 120.841 280.502 340.814 400.621 350.623 320.955 280.556 240.284 390.620 500.866 220.781 110.757 520.648 290.932 220.862 230.709 29
INS-Conv-semantic0.717 340.751 600.759 500.812 300.704 340.868 70.537 210.842 270.609 410.608 380.953 370.534 320.293 330.616 510.864 230.719 340.793 270.640 330.933 200.845 390.663 43
StratifiedFormerpermissive0.747 200.901 130.803 240.845 130.757 160.846 250.512 310.825 340.696 70.645 200.956 250.576 160.262 560.744 270.861 240.742 230.770 410.705 80.899 430.860 250.734 15
Xin Lai*, Jianhui Liu*, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
BPNetcopyleft0.749 170.909 100.818 130.811 310.752 190.839 310.485 450.842 270.673 160.644 210.957 240.528 350.305 280.773 90.859 250.788 80.818 50.693 120.916 310.856 280.723 23
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
DMF-Net0.752 150.906 120.793 330.802 390.689 380.825 440.556 120.867 160.681 140.602 420.960 170.555 250.365 70.779 50.859 250.747 220.795 260.717 60.917 300.856 280.764 9
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
LargeKernel3D0.739 270.909 100.820 100.806 370.740 250.852 170.545 160.826 330.594 500.643 220.955 280.541 280.263 550.723 310.858 270.775 140.767 420.678 170.933 200.848 350.694 34
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
PNE0.755 130.786 410.835 40.834 200.758 140.849 200.570 80.836 300.648 250.668 160.978 40.581 150.367 60.683 330.856 280.804 60.801 190.678 170.961 50.889 50.716 27
P. Hermosilla: Point Neighborhood Embeddings.
contrastBoundarypermissive0.705 360.769 540.775 410.809 330.687 390.820 510.439 710.812 410.661 200.591 480.945 610.515 390.171 890.633 450.856 280.720 320.796 230.668 250.889 500.847 360.689 35
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ConDaFormer0.755 130.927 60.822 80.836 180.801 10.849 200.516 300.864 200.651 230.680 100.958 200.584 140.282 400.759 180.855 300.728 270.802 150.678 170.880 570.873 180.756 11
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
PointMRNet0.640 650.717 760.701 760.692 710.576 740.801 660.467 530.716 670.563 650.459 840.953 370.429 740.169 910.581 580.854 310.605 780.710 670.550 760.894 470.793 680.575 73
Feature_GeometricNetpermissive0.690 430.884 160.754 540.795 420.647 510.818 550.422 750.802 440.612 380.604 400.945 610.462 580.189 840.563 650.853 320.726 280.765 430.632 360.904 370.821 500.606 62
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
JSENetpermissive0.699 400.881 170.762 480.821 240.667 440.800 670.522 270.792 470.613 370.607 390.935 810.492 450.205 760.576 590.853 320.691 470.758 500.652 280.872 670.828 440.649 47
Zeyu HU, Mingmin Zhen, Xuyang BAI, Hongbo Fu, Chiew-lan Tai: JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. ECCV 2020
Virtual MVFusion0.746 210.771 510.819 110.848 110.702 350.865 90.397 830.899 90.699 50.664 170.948 530.588 100.330 190.746 260.851 340.764 170.796 230.704 90.935 180.866 210.728 18
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
RFCR0.702 380.889 150.745 610.813 290.672 430.818 550.493 420.815 390.623 330.610 360.947 550.470 550.249 600.594 540.848 350.705 400.779 350.646 300.892 480.823 470.611 58
Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma: Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning. CVPR2021
MatchingNet0.724 330.812 360.812 180.810 320.735 270.834 360.495 410.860 210.572 590.602 420.954 340.512 400.280 420.757 190.845 360.725 290.780 340.606 480.937 160.851 340.700 33
Feature-Geometry Netpermissive0.685 450.866 190.748 580.819 260.645 530.794 700.450 610.802 440.587 520.604 400.945 610.464 570.201 790.554 680.840 370.723 310.732 620.602 510.907 350.822 490.603 65
LRPNet0.742 250.816 340.806 220.807 350.752 190.828 420.575 60.839 290.699 50.637 270.954 340.520 380.320 230.755 210.834 380.760 180.772 380.676 200.915 330.862 230.717 25
One Thing One Click0.701 390.825 310.796 290.723 600.716 320.832 380.433 730.816 370.634 300.609 370.969 100.418 810.344 120.559 660.833 390.715 360.808 130.560 690.902 400.847 360.680 38
PonderV20.785 20.978 10.800 250.833 210.788 30.853 150.545 160.910 50.713 10.705 40.979 10.596 60.390 10.769 110.832 400.821 40.792 290.730 10.975 10.897 40.785 4
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.
Superpoint Network0.683 490.851 240.728 690.800 410.653 480.806 630.468 510.804 420.572 590.602 420.946 580.453 650.239 640.519 770.822 410.689 500.762 470.595 550.895 460.827 450.630 55
DCM-Net0.658 580.778 450.702 750.806 370.619 600.813 610.468 510.693 740.494 810.524 660.941 730.449 670.298 310.510 790.821 420.675 530.727 640.568 660.826 840.803 600.637 52
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
OccuSeg+Semantic0.764 90.758 570.796 290.839 170.746 230.907 10.562 110.850 230.680 150.672 140.978 40.610 30.335 170.777 60.819 430.847 10.830 10.691 130.972 20.885 80.727 20
PPCNN++permissive0.663 570.746 620.708 720.722 610.638 560.820 510.451 580.566 940.599 470.541 580.950 470.510 410.313 250.648 400.819 430.616 770.682 800.590 570.869 710.810 560.656 45
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
SALANet0.670 530.816 340.770 450.768 520.652 490.807 620.451 580.747 580.659 220.545 570.924 910.473 540.149 990.571 620.811 450.635 720.746 570.623 410.892 480.794 660.570 75
KP-FCNN0.684 460.847 250.758 520.784 470.647 510.814 580.473 480.772 500.605 430.594 470.935 810.450 660.181 870.587 550.805 460.690 480.785 330.614 440.882 540.819 510.632 54
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
OA-CNN-L_ScanNet200.756 120.783 430.826 50.858 40.776 70.837 320.548 150.896 110.649 240.675 120.962 150.586 120.335 170.771 100.802 470.770 150.787 320.691 130.936 170.880 110.761 10
PointSPNet0.637 680.734 680.692 830.714 650.576 740.797 690.446 630.743 600.598 480.437 890.942 710.403 840.150 980.626 470.800 480.649 630.697 740.557 720.846 800.777 800.563 79
PointContrast_LA_SEM0.683 490.757 580.784 370.786 450.639 550.824 460.408 780.775 490.604 440.541 580.934 850.532 330.269 510.552 690.777 490.645 690.793 270.640 330.913 340.824 460.671 40
HPGCNN0.656 600.698 810.743 630.650 850.564 770.820 510.505 330.758 540.631 310.479 780.945 610.480 510.226 650.572 610.774 500.690 480.735 600.614 440.853 780.776 810.597 68
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
FusionNet0.688 440.704 780.741 650.754 570.656 460.829 400.501 350.741 610.609 410.548 560.950 470.522 370.371 40.633 450.756 510.715 360.771 400.623 410.861 750.814 530.658 44
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
ROSMRF3D0.673 520.789 400.748 580.763 550.635 570.814 580.407 800.747 580.581 560.573 510.950 470.484 490.271 490.607 520.754 520.649 630.774 370.596 530.883 530.823 470.606 62
PointConvpermissive0.666 550.781 440.759 500.699 680.644 540.822 480.475 470.779 480.564 640.504 740.953 370.428 750.203 780.586 570.754 520.661 590.753 530.588 590.902 400.813 550.642 50
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointNet2-SFPN0.631 730.771 510.692 830.672 760.524 850.837 320.440 700.706 720.538 690.446 860.944 670.421 800.219 700.552 690.751 540.591 840.737 590.543 810.901 420.768 830.557 82
RandLA-Netpermissive0.645 620.778 450.731 680.699 680.577 730.829 400.446 630.736 620.477 870.523 680.945 610.454 620.269 510.484 870.749 550.618 750.738 580.599 520.827 830.792 710.621 57
IPCA0.731 300.890 140.837 30.864 20.726 300.873 50.530 250.824 350.489 850.647 190.978 40.609 40.336 150.624 480.733 560.758 190.776 360.570 630.949 80.877 130.728 18
PointConv-SFPN0.641 630.776 470.703 740.721 620.557 800.826 430.451 580.672 790.563 650.483 770.943 700.425 780.162 940.644 410.726 570.659 600.709 690.572 620.875 610.786 760.559 81
SegGroup_sempermissive0.627 780.818 330.747 600.701 670.602 640.764 840.385 890.629 850.490 830.508 710.931 880.409 830.201 790.564 640.725 580.618 750.692 760.539 830.873 650.794 660.548 85
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
FPConvpermissive0.639 660.785 420.760 490.713 660.603 630.798 680.392 850.534 990.603 450.524 660.948 530.457 600.250 590.538 730.723 590.598 820.696 750.614 440.872 670.799 610.567 78
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
AttAN0.609 830.760 560.667 900.649 860.521 860.793 710.457 560.648 820.528 720.434 910.947 550.401 850.153 970.454 900.721 600.648 650.717 660.536 840.904 370.765 840.485 97
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
VACNN++0.684 460.728 720.757 530.776 500.690 360.804 650.464 540.816 370.577 580.587 490.945 610.508 420.276 440.671 350.710 610.663 580.750 560.589 580.881 550.832 430.653 46
PointMTL0.632 720.731 700.688 860.675 750.591 670.784 750.444 680.565 950.610 390.492 750.949 510.456 610.254 580.587 550.706 620.599 810.665 860.612 470.868 720.791 740.579 72
PicassoNet-IIpermissive0.692 420.732 690.772 420.786 450.677 420.866 80.517 290.848 240.509 780.626 300.952 410.536 300.225 670.545 720.704 630.689 500.810 120.564 680.903 390.854 320.729 17
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
APCF-Net0.631 730.742 650.687 880.672 760.557 800.792 730.408 780.665 800.545 680.508 710.952 410.428 750.186 850.634 440.702 640.620 740.706 710.555 730.873 650.798 630.581 71
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
SPH3D-GCNpermissive0.610 820.858 230.772 420.489 1040.532 840.792 730.404 810.643 840.570 620.507 730.935 810.414 820.046 1090.510 790.702 640.602 800.705 720.549 770.859 760.773 820.534 88
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
PointASNLpermissive0.666 550.703 790.781 390.751 590.655 470.830 390.471 490.769 510.474 880.537 600.951 430.475 530.279 430.635 430.698 660.675 530.751 540.553 740.816 860.806 570.703 32
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
VI-PointConv0.676 510.770 530.754 540.783 480.621 590.814 580.552 130.758 540.571 610.557 540.954 340.529 340.268 530.530 750.682 670.675 530.719 650.603 500.888 510.833 410.665 42
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
SD-DETR0.576 890.746 620.609 1030.445 1080.517 870.643 1030.366 910.714 690.456 930.468 820.870 1050.432 710.264 540.558 670.674 680.586 870.688 780.482 950.739 960.733 930.537 87
PanopticFusion-label0.529 950.491 1060.688 860.604 950.386 1010.632 1040.225 1090.705 730.434 980.293 1050.815 1070.348 950.241 630.499 830.669 690.507 940.649 890.442 1030.796 880.602 1080.561 80
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
PD-Net0.638 670.797 380.769 460.641 910.590 680.820 510.461 550.537 980.637 290.536 610.947 550.388 880.206 750.656 370.668 700.647 660.732 620.585 600.868 720.793 680.473 101
SConv0.636 690.830 290.697 790.752 580.572 760.780 780.445 650.716 670.529 710.530 630.951 430.446 690.170 900.507 820.666 710.636 710.682 800.541 820.886 520.799 610.594 69
One-Thing-One-Click0.693 410.743 640.794 310.655 830.684 400.822 480.497 400.719 660.622 340.617 330.977 80.447 680.339 140.750 250.664 720.703 420.790 300.596 530.946 100.855 300.647 48
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
wsss-transformer0.600 840.634 900.743 630.697 700.601 650.781 760.437 720.585 910.493 820.446 860.933 860.394 860.011 1110.654 380.661 730.603 790.733 610.526 860.832 820.761 860.480 98
dtc_net0.625 790.703 790.751 560.794 430.535 830.848 220.480 460.676 780.528 720.469 810.944 670.454 620.004 1120.464 890.636 740.704 410.758 500.548 780.924 260.787 750.492 95
3DSM_DMMF0.631 730.626 910.745 610.801 400.607 620.751 880.506 320.729 650.565 630.491 760.866 1060.434 700.197 820.595 530.630 750.709 380.705 720.560 690.875 610.740 910.491 96
DGNet0.684 460.712 770.784 370.782 490.658 450.835 350.499 390.823 360.641 270.597 450.950 470.487 480.281 410.575 600.619 760.647 660.764 440.620 430.871 700.846 380.688 36
SIConv0.625 790.830 290.694 810.757 560.563 780.772 820.448 620.647 830.520 740.509 700.949 510.431 730.191 830.496 840.614 770.647 660.672 840.535 850.876 600.783 770.571 74
HPEIN0.618 810.729 710.668 890.647 870.597 660.766 830.414 770.680 750.520 740.525 650.946 580.432 710.215 720.493 850.599 780.638 700.617 960.570 630.897 440.806 570.605 64
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia: Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. ICCV 2019
O3DSeg0.668 540.822 320.771 440.496 1030.651 500.833 370.541 180.761 530.555 670.611 350.966 130.489 470.370 50.388 970.580 790.776 130.751 540.570 630.956 60.817 520.646 49
ROSMRF0.580 880.772 500.707 730.681 740.563 780.764 840.362 920.515 1000.465 910.465 830.936 800.427 770.207 740.438 910.577 800.536 920.675 830.486 940.723 980.779 780.524 91
MVF-GNN0.658 580.558 1000.751 560.655 830.690 360.722 920.453 570.867 160.579 570.576 500.893 1030.523 360.293 330.733 280.571 810.692 450.659 870.606 480.875 610.804 590.668 41
3DWSSS0.425 1080.525 1030.647 950.522 1010.324 1080.488 1120.077 1130.712 710.353 1050.401 930.636 1130.281 1030.176 880.340 1000.565 820.175 1130.551 1030.398 1070.370 1130.602 1080.361 106
SAFNet-segpermissive0.654 610.752 590.734 670.664 810.583 720.815 570.399 820.754 560.639 280.535 620.942 710.470 550.309 270.665 360.539 830.650 620.708 700.635 350.857 770.793 680.642 50
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
TextureNetpermissive0.566 910.672 850.664 910.671 780.494 900.719 930.445 650.678 770.411 1010.396 940.935 810.356 930.225 670.412 950.535 840.565 900.636 950.464 970.794 890.680 1010.568 77
Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkerhouser, Matthias Niessner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. CVPR
Supervoxel-CNN0.635 700.656 860.711 710.719 630.613 610.757 870.444 680.765 520.534 700.566 520.928 890.478 520.272 470.636 420.531 850.664 570.645 910.508 890.864 740.792 710.611 58
GMLPs0.538 940.495 1050.693 820.647 870.471 940.793 710.300 990.477 1010.505 790.358 990.903 1010.327 970.081 1060.472 880.529 860.448 1010.710 670.509 870.746 940.737 920.554 84
subcloud_weak0.516 960.676 830.591 1060.609 930.442 970.774 800.335 950.597 880.422 1000.357 1000.932 870.341 960.094 1050.298 1020.528 870.473 990.676 820.495 920.602 1070.721 960.349 108
CCRFNet0.589 870.766 550.659 940.683 730.470 950.740 910.387 880.620 870.490 830.476 790.922 930.355 940.245 620.511 780.511 880.571 890.643 920.493 930.872 670.762 850.600 66
DPC0.592 860.720 740.700 770.602 960.480 920.762 860.380 900.713 700.585 550.437 890.940 750.369 910.288 360.434 930.509 890.590 860.639 940.567 670.772 920.755 880.592 70
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
DenSeR0.628 770.800 370.625 990.719 630.545 820.806 630.445 650.597 880.448 950.519 690.938 770.481 500.328 200.489 860.499 900.657 610.759 490.592 560.881 550.797 640.634 53
Weakly-Openseg v30.489 1000.749 610.664 910.646 890.496 890.559 1090.122 1120.577 920.257 1120.364 980.805 1080.198 1100.096 1040.510 790.496 910.361 1070.563 1000.359 1100.777 900.644 1050.532 90
joint point-basedpermissive0.634 710.614 940.778 400.667 800.633 580.825 440.420 760.804 420.467 900.561 530.951 430.494 440.291 350.566 630.458 920.579 880.764 440.559 710.838 810.814 530.598 67
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
SQN_0.1%0.569 900.676 830.696 800.657 820.497 880.779 790.424 740.548 960.515 760.376 960.902 1020.422 790.357 80.379 980.456 930.596 830.659 870.544 790.685 1010.665 1040.556 83
LAP-D0.594 850.720 740.692 830.637 920.456 960.773 810.391 870.730 640.587 520.445 880.940 750.381 890.288 360.434 930.453 940.591 840.649 890.581 610.777 900.749 900.610 60
DVVNet0.562 920.648 870.700 770.770 510.586 710.687 970.333 960.650 810.514 770.475 800.906 990.359 920.223 690.340 1000.442 950.422 1030.668 850.501 900.708 990.779 780.534 88
FusionAwareConv0.630 760.604 960.741 650.766 540.590 680.747 890.501 350.734 630.503 800.527 640.919 950.454 620.323 220.550 710.420 960.678 520.688 780.544 790.896 450.795 650.627 56
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
MVPNetpermissive0.641 630.831 280.715 700.671 780.590 680.781 760.394 840.679 760.642 260.553 550.937 780.462 580.256 570.649 390.406 970.626 730.691 770.666 260.877 590.792 710.608 61
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
Online SegFusion0.515 970.607 950.644 970.579 980.434 980.630 1050.353 930.628 860.440 960.410 920.762 1110.307 990.167 920.520 760.403 980.516 930.565 990.447 1010.678 1020.701 980.514 93
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
PCNN0.498 990.559 990.644 970.560 1000.420 1000.711 950.229 1070.414 1020.436 970.352 1010.941 730.324 980.155 960.238 1070.387 990.493 950.529 1060.509 870.813 870.751 890.504 94
Pointnet++ & Featurepermissive0.557 930.735 670.661 930.686 720.491 910.744 900.392 850.539 970.451 940.375 970.946 580.376 900.205 760.403 960.356 1000.553 910.643 920.497 910.824 850.756 870.515 92
FCPNpermissive0.447 1030.679 820.604 1050.578 990.380 1020.682 980.291 1020.106 1120.483 860.258 1100.920 940.258 1060.025 1100.231 1090.325 1010.480 980.560 1020.463 980.725 970.666 1030.231 112
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
Tangent Convolutionspermissive0.438 1070.437 1100.646 960.474 1050.369 1030.645 1020.353 930.258 1090.282 1100.279 1060.918 960.298 1010.147 1000.283 1040.294 1020.487 960.562 1010.427 1050.619 1060.633 1060.352 107
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
SurfaceConvPF0.442 1050.505 1040.622 1010.380 1110.342 1070.654 1000.227 1080.397 1040.367 1040.276 1070.924 910.240 1070.198 810.359 990.262 1030.366 1050.581 970.435 1040.640 1040.668 1020.398 103
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
SPLAT Netcopyleft0.393 1090.472 1090.511 1090.606 940.311 1100.656 990.245 1060.405 1030.328 1080.197 1110.927 900.227 1090.000 1140.001 1140.249 1040.271 1120.510 1070.383 1090.593 1080.699 990.267 110
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
PointCNN with RGBpermissive0.458 1020.577 980.611 1020.356 1120.321 1090.715 940.299 1010.376 1060.328 1080.319 1030.944 670.285 1020.164 930.216 1100.229 1050.484 970.545 1040.456 990.755 930.709 970.475 100
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
DGCNN_reproducecopyleft0.446 1040.474 1080.623 1000.463 1060.366 1040.651 1010.310 970.389 1050.349 1060.330 1020.937 780.271 1040.126 1010.285 1030.224 1060.350 1090.577 980.445 1020.625 1050.723 950.394 104
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
3DMV, FTSDF0.501 980.558 1000.608 1040.424 1100.478 930.690 960.246 1050.586 900.468 890.450 850.911 970.394 860.160 950.438 910.212 1070.432 1020.541 1050.475 960.742 950.727 940.477 99
3DMV0.484 1010.484 1070.538 1080.643 900.424 990.606 1080.310 970.574 930.433 990.378 950.796 1090.301 1000.214 730.537 740.208 1080.472 1000.507 1090.413 1060.693 1000.602 1080.539 86
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PNET20.442 1050.548 1020.548 1070.597 970.363 1050.628 1060.300 990.292 1070.374 1030.307 1040.881 1040.268 1050.186 850.238 1070.204 1090.407 1040.506 1100.449 1000.667 1030.620 1070.462 102
ScanNet+FTSDF0.383 1100.297 1120.491 1100.432 1090.358 1060.612 1070.274 1030.116 1110.411 1010.265 1080.904 1000.229 1080.079 1070.250 1050.185 1100.320 1100.510 1070.385 1080.548 1090.597 1110.394 104
ScanNetpermissive0.306 1130.203 1130.366 1120.501 1020.311 1100.524 1110.211 1100.002 1140.342 1070.189 1120.786 1100.145 1130.102 1030.245 1060.152 1110.318 1110.348 1120.300 1120.460 1120.437 1130.182 113
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
PointNet++permissive0.339 1110.584 970.478 1110.458 1070.256 1120.360 1130.250 1040.247 1100.278 1110.261 1090.677 1120.183 1110.117 1020.212 1110.145 1120.364 1060.346 1130.232 1130.548 1090.523 1120.252 111
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
ERROR0.054 1140.000 1140.041 1140.172 1140.030 1140.062 1140.001 1140.035 1130.004 1140.051 1140.143 1140.019 1140.003 1130.041 1120.050 1130.003 1140.054 1140.018 1140.005 1140.264 1140.082 114
SSC-UNetpermissive0.308 1120.353 1110.290 1130.278 1130.166 1130.553 1100.169 1110.286 1080.147 1130.148 1130.908 980.182 1120.064 1080.023 1130.018 1140.354 1080.363 1110.345 1110.546 1110.685 1000.278 109


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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort by
Mask3D_evaluation0.631 371.000 10.829 190.606 410.646 170.836 210.068 440.511 490.462 320.507 270.619 200.389 420.610 331.000 10.432 460.828 160.673 250.788 600.552 24
DENet0.629 381.000 10.797 320.608 400.589 270.627 510.219 270.882 10.310 450.402 480.383 510.396 410.650 191.000 10.663 210.543 590.691 231.000 10.568 21
SSEC0.707 201.000 10.850 140.924 30.648 160.747 420.162 300.862 30.572 240.520 240.624 180.549 230.649 281.000 10.560 350.706 420.768 141.000 10.591 17
Box2Mask0.677 261.000 10.847 160.771 230.509 410.816 250.277 210.558 440.482 280.562 200.640 150.448 330.700 131.000 10.666 190.852 90.578 400.997 340.488 35
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
PBNetpermissive0.747 151.000 10.818 210.837 140.713 50.844 190.457 110.647 330.711 100.614 140.617 210.657 160.650 191.000 10.692 180.822 170.765 151.000 10.595 15
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
RWSeg0.567 440.528 610.708 520.626 380.580 290.745 430.063 460.627 360.240 490.400 490.497 370.464 310.515 441.000 10.475 420.745 350.571 411.000 10.429 43
IPCA-Inst0.731 171.000 10.788 350.884 80.698 80.788 350.252 230.760 140.646 180.511 260.637 160.665 150.804 51.000 10.644 250.778 260.747 191.000 10.561 22
INS-Conv-instance0.657 291.000 10.760 430.667 370.581 280.863 150.323 180.655 310.477 290.473 320.549 320.432 360.650 191.000 10.655 220.738 370.585 390.944 480.472 38
Spherical Mask(CtoF)0.812 11.000 10.973 30.852 110.718 30.917 30.574 30.677 250.748 70.729 70.715 40.795 10.809 11.000 10.831 30.854 70.787 71.000 10.638 3
SphereSeg0.680 241.000 10.856 130.744 280.618 220.893 60.151 310.651 320.713 90.537 230.579 280.430 370.651 181.000 10.389 510.744 360.697 210.991 430.601 14
SPFormerpermissive0.770 90.903 490.903 90.806 180.609 240.886 80.568 40.815 60.705 110.711 80.655 110.652 170.685 171.000 10.789 90.809 220.776 121.000 10.583 18
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
RPGN0.643 321.000 10.758 440.582 490.539 330.826 230.046 480.765 120.372 410.436 400.588 240.539 260.650 191.000 10.577 320.750 340.653 290.997 340.495 34
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
SSTNetpermissive0.698 221.000 10.697 530.888 70.556 320.803 300.387 150.626 370.417 360.556 210.585 260.702 70.600 341.000 10.824 50.720 410.692 221.000 10.509 30
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
HAISpermissive0.699 211.000 10.849 150.820 150.675 140.808 290.279 200.757 150.465 310.517 250.596 230.559 220.600 341.000 10.654 230.767 280.676 240.994 410.560 23
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
GICN0.638 341.000 10.895 110.800 190.480 450.676 470.144 330.737 170.354 420.447 350.400 490.365 440.700 131.000 10.569 330.836 130.599 351.000 10.473 37
PointGroup0.636 351.000 10.765 400.624 390.505 430.797 320.116 390.696 230.384 400.441 360.559 310.476 300.596 371.000 10.666 190.756 330.556 470.997 340.513 29
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
OccuSeg+instance0.672 271.000 10.758 450.682 350.576 300.842 200.477 90.504 510.524 270.567 190.585 270.451 320.557 421.000 10.751 130.797 230.563 431.000 10.467 39
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
CSC-Pretrained0.648 301.000 10.810 230.768 240.523 390.813 270.143 340.819 50.389 390.422 430.511 360.443 340.650 191.000 10.624 280.732 380.634 321.000 10.375 47
MTML0.549 461.000 10.807 270.588 460.327 530.647 490.004 570.815 70.180 520.418 440.364 530.182 510.445 491.000 10.442 450.688 490.571 421.000 10.396 45
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
Mask3D0.780 81.000 10.786 360.716 320.696 100.885 100.500 70.714 190.810 30.672 110.715 40.679 140.809 11.000 10.831 30.833 140.787 71.000 10.602 13
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
DD-UNet+Group0.635 360.667 510.797 330.714 330.562 310.774 370.146 320.810 80.429 350.476 310.546 340.399 400.633 301.000 10.632 270.722 400.609 341.000 10.514 28
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
SoftGroup++0.769 101.000 10.803 290.937 10.684 120.865 140.213 280.870 20.664 150.571 180.758 10.702 80.807 41.000 10.653 240.902 10.792 61.000 10.626 5
TD3Dpermissive0.751 141.000 10.774 370.867 100.621 200.934 10.404 140.706 200.812 20.605 160.633 170.626 190.690 161.000 10.640 260.820 180.777 111.000 10.612 11
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
ExtMask3D0.789 51.000 10.988 10.756 270.706 70.912 40.429 130.647 330.806 40.755 40.673 100.689 120.772 91.000 10.789 80.852 80.811 31.000 10.617 9
SIM3D0.766 111.000 10.948 40.582 480.599 260.882 120.510 60.701 220.632 190.772 30.685 90.687 130.782 71.000 10.833 20.756 320.798 51.000 10.622 7
Queryformer0.787 61.000 10.933 50.601 420.754 10.886 90.558 50.661 300.767 60.665 120.716 30.639 180.808 31.000 10.844 10.897 30.804 41.000 10.624 6
MAFT0.786 71.000 10.894 120.807 170.694 110.893 70.486 80.674 260.740 80.786 10.704 70.727 40.739 111.000 10.707 170.849 100.756 171.000 10.685 1
ISBNetpermissive0.757 131.000 10.904 80.731 300.678 130.895 50.458 100.644 350.670 140.710 90.620 190.732 30.650 191.000 10.756 120.778 250.779 101.000 10.614 10
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
OneFormer3Dcopyleft0.801 21.000 10.973 20.909 50.698 90.928 20.582 20.668 280.685 120.780 20.687 80.698 110.702 121.000 10.794 70.900 20.784 90.986 450.635 4
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
TST3D0.795 41.000 10.929 70.918 40.709 60.884 110.596 10.704 210.769 50.734 60.644 140.699 100.751 101.000 10.794 60.876 40.757 160.997 340.550 25
GraphCut0.732 161.000 10.788 340.724 310.642 180.859 180.248 240.787 110.618 210.596 170.653 130.722 60.583 401.000 10.766 100.861 50.825 21.000 10.504 31
DKNet0.718 191.000 10.814 220.782 210.619 210.872 130.224 260.751 160.569 250.677 100.585 250.724 50.633 300.981 320.515 400.819 190.736 201.000 10.617 8
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
DANCENET0.680 241.000 10.807 260.733 290.600 250.768 380.375 170.543 450.538 260.610 150.599 220.498 280.632 320.981 320.739 140.856 60.633 330.882 560.454 40
SoftGrouppermissive0.761 121.000 10.808 250.845 120.716 40.862 160.243 250.824 40.655 170.620 130.734 20.699 90.791 60.981 320.716 150.844 110.769 131.000 10.594 16
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
TopoSeg0.725 181.000 10.806 280.933 20.668 150.758 390.272 220.734 180.630 200.549 220.654 120.606 200.697 150.966 350.612 300.839 120.754 181.000 10.573 19
ClickSeg_Instance0.539 471.000 10.621 560.300 540.530 370.698 450.127 380.533 460.222 500.430 420.400 480.365 440.574 410.938 360.472 430.659 510.543 490.944 480.347 50
PE0.645 311.000 10.773 390.798 200.538 340.786 360.088 430.799 100.350 430.435 410.547 330.545 240.646 290.933 370.562 340.761 310.556 480.997 340.501 33
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
UniPerception0.800 31.000 10.930 60.872 90.727 20.862 170.454 120.764 130.820 10.746 50.706 60.750 20.772 80.926 380.764 110.818 210.826 10.997 340.660 2
SSEN0.575 431.000 10.761 410.473 510.477 460.795 330.066 450.529 470.658 160.460 330.461 410.380 430.331 570.859 390.401 500.692 480.653 281.000 10.348 49
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
3D-SISpermissive0.382 571.000 10.432 640.245 570.190 590.577 550.013 540.263 590.033 620.320 550.240 580.075 580.422 530.857 400.117 620.699 440.271 630.883 550.235 57
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
3D-MPA0.611 391.000 10.833 180.765 250.526 380.756 400.136 370.588 420.470 300.438 390.432 450.358 460.650 190.857 400.429 470.765 290.557 461.000 10.430 42
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
PanopticFusion-inst0.478 520.667 510.712 510.595 440.259 580.550 580.000 600.613 390.175 540.250 590.434 420.437 350.411 540.857 400.485 410.591 580.267 640.944 480.359 48
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
OSIS0.605 401.000 10.801 300.599 430.535 350.728 440.286 190.436 550.679 130.491 280.433 430.256 480.404 550.857 400.620 290.724 390.510 531.000 10.539 26
SPG_WSIS0.470 530.667 510.685 540.677 360.372 510.562 560.000 600.482 520.244 480.316 560.298 540.052 620.442 510.857 400.267 560.702 430.559 451.000 10.287 53
Dyco3Dcopyleft0.641 331.000 10.841 170.893 60.531 360.802 310.115 400.588 420.448 330.438 380.537 350.430 380.550 430.857 400.534 380.764 300.657 260.987 440.568 20
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
NeuralBF0.555 450.667 510.896 100.843 130.517 400.751 410.029 500.519 480.414 370.439 370.465 390.000 670.484 460.857 400.287 550.693 470.651 301.000 10.485 36
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Occipital-SCS0.512 501.000 10.716 490.509 500.506 420.611 520.092 420.602 410.177 530.346 530.383 500.165 530.442 500.850 470.386 520.618 550.543 500.889 530.389 46
PCJC0.578 421.000 10.810 240.583 470.449 480.813 280.042 490.603 400.341 440.490 290.465 400.410 390.650 190.835 480.264 570.694 460.561 440.889 530.504 32
DualGroup0.694 231.000 10.799 310.811 160.622 190.817 240.376 160.805 90.590 230.487 300.568 290.525 270.650 190.835 480.600 310.829 150.655 271.000 10.526 27
3D-BoNet0.488 511.000 10.672 550.590 450.301 550.484 620.098 410.620 380.306 460.341 540.259 570.125 550.434 520.796 500.402 490.499 610.513 520.909 520.439 41
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
AOIA0.601 411.000 10.761 420.687 340.485 440.828 220.008 550.663 290.405 380.405 470.425 460.490 290.596 370.714 510.553 370.779 240.597 360.992 420.424 44
SegGroup_inspermissive0.445 560.667 510.773 380.185 620.317 540.656 480.000 600.407 560.134 560.381 510.267 560.217 500.476 470.714 510.452 440.629 540.514 511.000 10.222 58
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SALoss-ResNet0.459 541.000 10.737 470.159 650.259 570.587 540.138 360.475 530.217 510.416 450.408 470.128 540.315 580.714 510.411 480.536 600.590 380.873 570.304 52
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
Hier3Dcopyleft0.323 580.667 510.542 600.264 560.157 620.550 570.000 600.205 620.009 640.270 580.218 590.075 580.500 450.688 540.007 680.698 450.301 600.459 650.200 59
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
One_Thing_One_Clickpermissive0.529 480.667 510.718 480.777 220.399 490.683 460.000 600.669 270.138 550.391 500.374 520.539 250.360 560.641 550.556 360.774 270.593 370.997 340.251 55
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Sparse R-CNN0.515 491.000 10.538 610.282 550.468 470.790 340.173 290.345 570.429 340.413 460.484 380.176 520.595 390.591 560.522 390.668 500.476 540.986 460.327 51
MASCpermissive0.447 550.528 610.555 590.381 520.382 500.633 500.002 580.509 500.260 470.361 520.432 440.327 470.451 480.571 570.367 530.639 530.386 550.980 470.276 54
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
Mask-Group0.664 281.000 10.822 200.764 260.616 230.815 260.139 350.694 240.597 220.459 340.566 300.599 210.600 340.516 580.715 160.819 200.635 311.000 10.603 12
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
UNet-backbone0.319 590.667 510.715 500.233 580.189 600.479 630.008 550.218 600.067 610.201 610.173 600.107 560.123 630.438 590.150 590.615 560.355 560.916 510.093 67
ASIS0.199 660.333 640.253 670.167 640.140 640.438 640.000 600.177 630.008 650.121 650.069 650.004 660.231 600.429 600.036 660.445 640.273 620.333 670.119 66
3D-BEVIS0.248 630.667 510.566 580.076 660.035 680.394 660.027 520.035 670.098 590.099 660.030 670.025 640.098 640.375 610.126 610.604 570.181 660.854 580.171 61
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
R-PointNet0.306 600.500 630.405 650.311 530.348 520.589 530.054 470.068 650.126 570.283 570.290 550.028 630.219 610.214 620.331 540.396 650.275 610.821 590.245 56
Sem_Recon_ins0.227 650.764 500.486 620.069 670.098 650.426 650.017 530.067 660.015 630.172 620.100 620.096 570.054 670.183 630.135 600.366 660.260 650.614 640.168 62
tmp0.248 630.667 510.437 630.188 610.153 630.491 610.000 600.208 610.094 600.153 630.099 640.057 600.217 620.119 640.039 640.466 620.302 590.640 630.140 64
SemRegionNet-20cls0.250 620.333 640.613 570.229 590.163 610.493 600.000 600.304 580.107 580.147 640.100 630.052 610.231 590.119 640.039 640.445 630.325 570.654 620.141 63
Region-18class0.284 610.250 670.751 460.228 600.270 560.521 590.000 600.468 540.008 660.205 600.127 610.000 670.068 650.070 660.262 580.652 520.323 580.740 610.173 60
Sgpn_scannet0.143 670.208 680.390 660.169 630.065 660.275 670.029 510.069 640.000 670.087 670.043 660.014 650.027 680.000 670.112 630.351 670.168 670.438 660.138 65
MaskRCNN 2d->3d Proj0.058 680.333 640.002 680.000 680.053 670.002 680.002 590.021 680.000 670.045 680.024 680.238 490.065 660.000 670.014 670.107 680.020 680.110 680.006 68


This table lists the benchmark results for the 2D semantic label scenario.


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort by
Virtual MVFusion (R)0.745 10.861 10.839 10.881 10.672 20.512 10.422 170.898 10.723 10.714 10.954 20.454 10.509 10.773 10.895 10.756 10.820 10.653 10.935 10.891 10.728 1
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
MVF-GNN(2D)0.636 30.606 140.794 40.434 160.688 10.337 80.464 120.798 30.632 50.589 30.908 80.420 20.329 120.743 20.594 20.738 20.676 50.527 40.906 20.818 60.715 3
DMMF_3d0.605 60.651 90.744 100.782 30.637 50.387 40.536 30.732 80.590 70.540 60.856 210.359 110.306 150.596 140.539 30.627 200.706 40.497 80.785 210.757 190.476 22
BPNet_2Dcopyleft0.670 20.822 30.795 30.836 20.659 30.481 20.451 130.769 40.656 30.567 40.931 30.395 60.390 50.700 40.534 4