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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
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 70.753 60.848 10.256 10.717 20.000 30.842 10.192 20.065 20.449 50.346 10.546 30.190 60.000 40.384 30.000 10.000 30.218 10.505 10.791 10.000 10.136 10.000 20.903 10.073 80.687 20.000 40.168 10.551 20.387 40.941 10.000 10.000 20.397 60.654 30.000 70.714 30.759 80.752 30.118 30.264 10.926 10.000 10.048 10.575 10.000 60.597 10.366 10.755 10.469 10.474 10.798 10.140 60.617 10.692 20.000 30.592 10.971 10.188 20.000 10.133 30.593 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 60.641 10.903 10.349 10.616 10.088 40.832 10.000 30.480 10.000 10.428 10.000 20.497 50.000 10.000 40.000 10.662 20.690 10.612 10.828 10.575 10.000 10.404 40.644 10.325 30.887 10.728 10.009 90.134 50.026 100.000 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 30.531 10.978 10.457 10.708 10.583 20.141 70.748 10.000 10.026 10.822 10.871 30.879 50.000 10.851 10.405 20.914 10.000 10.682 10.000 80.281 10.738 10.463 3
OA-CNN-L_ScanNet2000.333 40.558 20.269 40.124 60.448 80.080 50.272 30.000 10.000 20.000 10.342 50.515 20.524 30.713 100.789 40.158 60.384 50.000 30.806 30.125 30.000 50.496 40.332 30.498 90.227 50.024 20.474 10.000 10.003 20.071 50.487 20.000 50.000 10.110 30.000 20.876 30.013 100.703 10.000 40.076 60.473 60.355 50.906 30.000 10.000 20.476 40.706 10.000 70.672 70.835 60.748 40.015 90.223 30.860 40.000 10.000 60.572 30.000 60.509 50.313 40.662 20.398 70.396 20.411 80.276 10.527 20.711 10.000 30.076 70.946 30.166 40.000 10.022 40.160 30.183 60.493 60.699 50.637 30.403 30.330 70.406 60.526 30.024 20.000 10.392 60.000 60.016 100.000 50.196 20.915 40.112 50.557 50.197 20.352 60.877 20.000 50.000 10.592 80.103 80.000 90.067 10.000 10.089 20.735 30.625 50.130 50.568 30.836 40.271 30.534 50.043 80.799 40.001 20.445 20.000 10.000 30.024 10.661 20.000 10.262 10.000 10.591 40.517 90.373 50.788 50.021 40.000 10.455 10.517 50.320 40.823 50.200 100.001 100.150 40.100 50.000 10.736 40.668 40.103 80.052 40.662 10.720 30.000 10.602 50.112 40.002 40.000 10.637 50.000 20.000 10.621 50.569 20.398 40.412 40.234 50.949 30.363 20.492 90.495 40.251 40.665 50.000 10.001 70.805 30.833 40.794 60.000 10.821 20.314 40.843 70.000 10.560 40.245 20.262 30.713 20.370 7
OctFormer ScanNet200permissive0.326 60.539 60.265 50.131 50.499 30.110 10.522 10.000 10.000 20.000 10.318 80.427 40.455 80.743 80.765 60.175 50.842 10.000 30.828 20.204 10.033 30.429 60.335 20.601 10.312 20.000 40.357 50.000 10.000 30.047 70.423 50.000 50.000 10.105 40.000 20.873 50.079 60.670 60.000 40.117 20.471 70.432 20.829 70.000 10.000 20.584 20.417 100.089 30.684 60.837 50.705 90.021 80.178 50.892 20.000 10.028 30.505 70.000 60.457 60.200 80.662 20.412 50.244 80.496 50.000 100.451 30.626 40.000 30.102 50.943 50.138 70.000 10.000 60.149 40.291 30.534 50.722 30.632 40.331 60.253 90.453 40.487 60.000 30.000 10.479 30.000 60.022 70.000 50.000 30.900 60.128 40.684 20.164 50.413 20.854 70.000 50.000 10.512 100.074 100.003 70.000 40.000 10.000 40.469 80.613 60.132 40.529 40.871 20.227 90.582 40.026 100.787 50.000 30.339 80.000 10.000 30.000 20.626 30.000 10.029 30.000 10.587 50.612 40.411 40.724 70.000 50.000 10.407 30.552 20.513 10.849 30.655 30.408 10.000 60.296 10.000 10.686 80.645 70.145 50.022 50.414 70.633 60.000 10.637 10.224 10.000 50.000 10.650 40.000 20.000 10.622 40.535 60.343 50.483 20.230 60.943 50.289 40.618 40.596 10.140 80.679 40.000 10.022 20.783 60.620 80.906 10.000 10.806 50.137 80.865 30.000 10.378 60.000 80.168 100.680 50.227 9
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
PonderV2 ScanNet2000.346 20.552 40.270 30.175 30.497 40.070 70.239 40.000 10.000 20.000 10.232 100.412 50.584 10.842 20.804 30.212 40.540 40.000 30.433 100.106 60.000 50.590 30.290 60.548 20.243 40.000 40.356 60.000 10.000 30.062 60.398 70.441 40.000 10.104 50.000 20.888 20.076 70.682 30.030 10.094 40.491 50.351 60.869 60.000 10.063 10.403 50.700 20.000 70.660 80.881 20.761 10.050 50.186 40.852 60.000 10.007 40.570 40.100 20.565 20.326 30.641 50.431 30.290 70.621 30.259 20.408 40.622 50.125 10.082 60.950 20.179 30.000 10.263 20.424 20.193 40.558 30.880 10.545 60.375 40.727 20.445 50.499 50.000 30.000 10.475 40.002 40.034 40.083 30.000 30.924 10.290 20.636 30.115 70.400 30.874 30.186 40.000 10.611 40.128 20.113 20.000 40.000 10.000 40.584 50.636 40.103 70.385 50.843 30.283 20.603 30.080 50.825 30.000 30.377 60.000 10.000 30.000 20.457 60.000 10.000 40.000 10.574 70.608 50.481 20.792 30.394 20.000 10.357 60.503 60.261 50.817 60.504 80.304 30.472 30.115 40.000 10.750 30.677 30.202 10.000 70.509 30.729 10.000 10.519 70.000 90.000 50.000 10.620 70.000 20.000 10.660 30.560 40.486 20.384 50.346 40.952 20.247 70.667 20.436 50.269 30.691 30.000 10.010 30.787 50.889 20.880 40.000 10.810 40.336 30.860 60.000 10.606 30.009 50.248 50.681 40.392 5
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
PPT-SpUNet-F.T.0.332 50.556 30.270 20.123 70.519 20.091 30.349 20.000 10.000 20.000 10.339 60.383 70.498 60.833 30.807 20.241 20.584 30.000 30.755 40.124 40.000 50.608 20.330 40.530 60.314 10.000 40.374 40.000 10.000 30.197 20.459 40.000 50.000 10.117 20.000 20.876 30.095 10.682 30.000 40.086 50.518 30.433 10.930 20.000 10.000 20.563 30.542 70.077 40.715 20.858 40.756 20.008 100.171 60.874 30.000 10.039 20.550 50.000 60.545 40.256 50.657 40.453 20.351 40.449 70.213 30.392 50.611 60.000 30.037 80.946 30.138 70.000 10.000 60.063 50.308 20.537 40.796 20.673 20.323 70.392 50.400 70.509 40.000 30.000 10.649 10.000 60.023 60.000 50.000 30.914 50.002 90.506 90.163 60.359 50.872 40.000 50.000 10.623 30.112 40.001 80.000 40.000 10.021 30.753 10.565 90.150 10.579 20.806 60.267 40.616 10.042 90.783 60.000 30.374 70.000 10.000 30.000 20.620 40.000 10.000 40.000 10.572 80.634 20.350 60.792 30.000 50.000 10.376 50.535 30.378 20.855 20.672 20.074 60.000 60.185 30.000 10.727 50.660 50.076 100.000 70.432 60.646 50.000 10.594 60.006 80.000 50.000 10.658 30.000 20.000 10.661 10.549 50.300 70.291 70.045 70.942 60.304 30.600 50.572 30.135 90.695 20.000 10.008 50.793 40.942 10.899 20.000 10.816 30.181 60.897 20.000 10.679 20.223 30.264 20.691 30.345 8
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.
CSC-Pretrainpermissive0.249 100.455 100.171 90.079 100.418 90.059 90.186 70.000 10.000 20.000 10.335 70.250 90.316 90.766 50.697 100.142 70.170 70.003 20.553 80.112 50.097 10.201 100.186 70.476 100.081 90.000 40.216 100.000 10.000 30.001 100.314 100.000 50.000 10.055 80.000 20.832 100.094 20.659 80.002 20.076 60.310 100.293 100.664 100.000 10.000 20.175 100.634 40.130 20.552 100.686 100.700 100.076 40.110 80.770 100.000 10.000 60.430 100.000 60.319 80.166 90.542 100.327 90.205 90.332 90.052 90.375 60.444 100.000 30.012 100.930 100.203 10.000 10.000 60.046 60.175 70.413 90.592 80.471 90.299 80.152 100.340 90.247 100.000 30.000 10.225 80.058 20.037 20.000 50.207 10.862 100.014 70.548 70.033 90.233 90.816 90.000 50.000 10.542 90.123 30.121 10.019 20.000 10.000 40.463 90.454 100.045 100.128 100.557 90.235 70.441 90.063 70.484 100.000 30.308 100.000 10.000 30.000 20.318 100.000 10.000 40.000 10.545 90.543 80.164 100.734 60.000 50.000 10.215 100.371 90.198 70.743 70.205 90.062 80.000 60.079 70.000 10.683 90.547 90.142 60.000 70.441 50.579 100.000 10.464 80.098 50.041 10.000 10.590 90.000 20.000 10.373 60.494 70.174 80.105 90.001 100.895 90.222 90.537 70.307 90.180 50.625 70.000 10.000 80.591 100.609 90.398 80.000 10.766 100.014 100.638 100.000 10.377 70.004 70.206 90.609 100.465 2
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
AWCS0.305 70.508 70.225 70.142 40.463 70.063 80.195 60.000 10.000 20.000 10.467 20.551 10.504 40.773 40.764 70.142 70.029 100.000 30.626 70.100 70.000 50.360 70.179 80.507 80.137 80.006 30.300 70.000 10.000 30.172 40.364 80.512 30.000 10.056 70.000 20.865 70.093 30.634 100.000 40.071 80.396 80.296 90.876 50.000 10.000 20.373 70.436 90.063 60.749 10.877 30.721 50.131 20.124 70.804 80.000 10.000 60.515 60.010 50.452 70.252 60.578 70.417 40.179 100.484 60.171 40.337 70.606 70.000 30.115 40.937 70.142 60.000 10.008 50.000 90.157 90.484 70.402 100.501 80.339 50.553 30.529 20.478 70.000 30.000 10.404 50.001 50.022 70.077 40.000 30.894 80.219 30.628 40.093 80.305 70.886 10.233 30.000 10.603 50.112 40.023 60.000 40.000 10.000 40.741 20.664 30.097 80.253 70.782 70.264 50.523 60.154 10.707 90.000 30.411 40.000 10.000 30.000 20.332 90.000 10.000 40.000 10.602 30.595 60.185 90.656 90.159 30.000 10.355 70.424 80.154 80.729 80.516 60.220 50.620 20.084 60.000 10.707 70.651 60.173 20.014 60.381 100.582 90.000 10.619 20.049 70.000 50.000 10.702 20.000 20.000 10.302 90.489 80.317 60.334 60.392 20.922 70.254 60.533 80.394 60.129 100.613 80.000 10.000 80.820 20.649 70.749 70.000 10.782 70.282 50.863 40.000 10.288 90.006 60.220 70.633 70.542 1
CeCo0.340 30.551 50.247 60.181 20.475 60.057 100.142 80.000 10.000 20.000 10.387 30.463 30.499 50.924 10.774 50.213 30.257 60.000 30.546 90.100 70.006 40.615 10.177 100.534 40.246 30.000 40.400 20.000 10.338 10.006 90.484 30.609 20.000 10.083 60.000 20.873 50.089 40.661 70.000 40.048 100.560 10.408 30.892 40.000 10.000 20.586 10.616 50.000 70.692 50.900 10.721 50.162 10.228 20.860 40.000 10.000 60.575 10.083 30.550 30.347 20.624 60.410 60.360 30.740 20.109 70.321 80.660 30.000 30.121 30.939 60.143 50.000 10.400 10.003 70.190 50.564 20.652 60.615 50.421 20.304 80.579 10.547 20.000 30.000 10.296 70.000 60.030 50.096 20.000 30.916 30.037 60.551 60.171 40.376 40.865 50.286 20.000 10.633 20.102 90.027 50.011 30.000 10.000 40.474 70.742 20.133 30.311 60.824 50.242 60.503 70.068 60.828 20.000 30.429 30.000 10.063 20.000 20.781 10.000 10.000 40.000 10.665 10.633 30.450 30.818 20.000 50.000 10.429 20.532 40.226 60.825 40.510 70.377 20.709 10.079 70.000 10.753 20.683 20.102 90.063 30.401 90.620 80.000 10.619 20.000 90.000 50.000 10.595 80.000 20.000 10.345 70.564 30.411 30.603 10.384 30.945 40.266 50.643 30.367 70.304 10.663 60.000 10.010 30.726 80.767 50.898 30.000 10.784 60.435 10.861 50.000 10.447 50.000 80.257 40.656 60.377 6
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
LGroundpermissive0.272 80.485 80.184 80.106 80.476 50.077 60.218 50.000 10.000 20.000 10.547 10.295 80.540 20.746 70.745 80.058 90.112 90.005 10.658 60.077 100.000 50.322 80.178 90.512 70.190 60.199 10.277 80.000 10.000 30.173 30.399 60.000 50.000 10.039 90.000 20.858 80.085 50.676 50.002 20.103 30.498 40.323 70.703 80.000 10.000 20.296 80.549 60.216 10.702 40.768 70.718 70.028 60.092 90.786 90.000 10.000 60.453 90.022 40.251 100.252 60.572 80.348 80.321 50.514 40.063 80.279 90.552 80.000 30.019 90.932 80.132 90.000 10.000 60.000 90.156 100.457 80.623 70.518 70.265 90.358 60.381 80.395 80.000 30.000 10.127 100.012 30.051 10.000 50.000 30.886 90.014 70.437 100.179 30.244 80.826 80.000 50.000 10.599 60.136 10.085 30.000 40.000 10.000 40.565 60.612 70.143 20.207 80.566 80.232 80.446 80.127 20.708 80.000 30.384 50.000 10.000 30.000 20.402 70.000 10.059 20.000 10.525 100.566 70.229 80.659 80.000 50.000 10.265 80.446 70.147 90.720 100.597 50.066 70.000 60.187 20.000 10.726 60.467 100.134 70.000 70.413 80.629 70.000 10.363 90.055 60.022 20.000 10.626 60.000 20.000 10.323 80.479 100.154 90.117 80.028 90.901 80.243 80.415 100.295 100.143 60.610 90.000 10.000 80.777 70.397 100.324 90.000 10.778 80.179 70.702 90.000 10.274 100.404 10.233 60.622 80.398 4
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
Minkowski 34Dpermissive0.253 90.463 90.154 100.102 90.381 100.084 40.134 90.000 10.000 20.000 10.386 40.141 100.279 100.737 90.703 90.014 100.164 80.000 30.663 50.092 90.000 50.224 90.291 50.531 50.056 100.000 40.242 90.000 10.000 30.013 80.331 90.000 50.000 10.035 100.001 10.858 80.059 90.650 90.000 40.056 90.353 90.299 80.670 90.000 10.000 20.284 90.484 80.071 50.594 90.720 90.710 80.027 70.068 100.813 70.000 10.005 50.492 80.164 10.274 90.111 100.571 90.307 100.293 60.307 100.150 50.163 100.531 90.002 20.545 20.932 80.093 100.000 10.000 60.002 80.159 80.368 100.581 90.440 100.228 100.406 40.282 100.294 90.000 30.000 10.189 90.060 10.036 30.000 50.000 30.897 70.000 100.525 80.025 100.205 100.771 100.000 50.000 10.593 70.108 70.044 40.000 40.000 10.000 40.282 100.589 80.094 90.169 90.466 100.227 90.419 100.125 30.757 70.002 10.334 90.000 10.000 30.000 20.357 80.000 10.000 40.000 10.582 60.513 100.337 70.612 100.000 50.000 10.250 90.352 100.136 100.724 90.655 30.280 40.000 60.046 90.000 10.606 100.559 80.159 40.102 10.445 40.655 40.000 10.310 100.117 30.000 50.000 10.581 100.026 10.000 10.265 100.483 90.084 100.097 100.044 80.865 100.142 100.588 60.351 80.272 20.596 100.000 10.003 60.622 90.720 60.096 100.000 10.771 90.016 90.772 80.000 10.302 80.194 40.214 80.621 90.197 10
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 Infoavg aphead apcommon aptail apalarm 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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
TD3D Scannet200permissive0.211 20.332 20.177 20.103 20.337 20.036 20.222 40.000 10.000 10.000 10.031 10.342 10.093 40.852 10.452 40.559 20.000 20.004 20.000 30.039 10.000 20.309 20.047 40.380 20.028 20.000 10.080 20.000 10.000 20.147 10.192 30.000 20.000 10.083 10.000 10.395 20.039 40.662 10.000 10.000 20.074 10.135 10.296 20.000 20.000 10.231 50.646 10.139 30.633 31.000 10.705 10.048 10.088 20.439 20.184 20.039 20.266 20.551 20.260 30.026 50.463 20.046 30.252 20.249 30.083 20.372 10.411 10.000 20.414 10.323 10.000 10.052 20.000 10.157 10.278 20.278 20.237 20.015 20.321 20.253 10.060 40.000 10.000 10.272 20.008 10.169 20.032 20.000 10.404 10.356 20.283 20.073 30.028 50.617 20.038 20.000 10.494 20.037 20.215 10.083 20.000 20.003 20.486 30.694 10.000 20.040 40.083 40.219 50.209 20.007 10.483 10.000 20.125 40.000 10.150 20.014 10.544 10.000 10.000 20.000 10.260 50.143 50.200 10.610 30.028 20.032 10.145 10.059 20.046 40.740 20.806 10.543 20.000 20.108 20.008 10.222 50.669 20.456 10.074 10.224 10.586 10.006 20.451 20.000 10.002 10.889 10.282 20.000 10.000 10.252 20.413 20.111 20.074 20.240 10.893 10.266 20.144 30.293 20.281 20.604 20.000 10.000 20.379 50.963 10.250 40.000 10.160 10.420 20.000 10.343 30.207 20.079 50.315 20.052 2
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
Mask3D Scannet2000.278 10.383 10.263 10.168 10.506 10.068 10.083 50.000 10.000 10.000 10.023 20.149 40.302 10.778 30.647 10.569 10.500 10.031 10.014 20.027 20.173 10.311 10.195 10.351 30.258 10.000 10.082 10.000 10.003 10.037 20.391 11.000 10.000 10.014 20.000 10.572 10.573 10.661 20.000 10.003 10.005 40.082 40.349 10.028 10.000 10.605 10.515 30.509 10.711 11.000 10.665 30.015 20.107 10.402 40.201 10.083 10.304 10.759 10.491 10.378 10.572 10.119 10.277 10.013 50.089 10.283 20.411 20.267 10.006 30.156 20.000 10.116 10.000 10.105 30.556 10.514 10.396 10.275 10.323 10.215 20.380 10.000 10.000 10.356 10.005 20.208 10.325 10.000 10.050 40.400 10.561 10.258 10.179 10.722 10.147 10.000 10.586 10.063 10.015 20.139 10.016 10.028 10.708 10.418 20.016 10.048 30.500 10.489 10.349 10.001 20.475 20.086 10.365 10.000 10.500 10.000 20.323 30.000 10.222 10.000 10.497 10.626 10.044 30.795 10.556 10.008 20.121 40.265 10.667 10.789 10.568 20.579 10.444 10.176 10.004 20.474 10.752 10.233 20.014 20.002 40.570 20.007 10.377 50.000 10.000 20.000 20.337 10.000 10.000 10.384 10.465 10.287 10.085 10.048 20.816 50.467 10.810 10.377 10.415 10.744 10.000 10.004 10.724 10.778 20.590 10.000 10.032 20.441 10.000 10.377 20.391 10.427 10.321 10.192 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
CSC-Pretrain Inst.permissive0.123 50.223 50.082 50.046 40.308 30.004 30.278 10.000 10.000 10.000 10.000 50.032 50.105 30.537 40.348 50.378 40.000 20.000 30.000 30.000 50.000 20.000 50.037 50.323 40.000 40.000 10.013 50.000 10.000 20.000 30.235 20.000 20.000 10.000 30.000 10.231 30.045 30.564 40.000 10.000 20.006 30.078 50.065 30.000 20.000 10.259 30.516 20.000 40.600 41.000 10.578 50.000 30.000 50.184 50.000 30.000 30.034 50.000 30.211 40.089 30.394 50.018 50.064 40.171 40.001 50.144 30.172 40.000 20.000 40.044 40.000 10.000 30.000 10.064 50.126 40.278 20.093 50.000 40.094 40.214 30.011 50.000 10.000 10.000 30.000 30.022 50.000 30.000 10.275 30.000 40.275 40.000 50.098 40.407 40.000 30.000 10.250 50.007 50.000 30.000 30.000 20.000 30.333 40.376 40.000 20.000 50.042 50.285 30.119 40.000 30.224 50.000 20.184 30.000 10.000 30.000 20.244 40.000 10.000 20.000 10.377 30.378 20.051 20.424 50.000 30.000 30.116 50.030 40.125 20.441 40.444 50.063 50.000 20.042 30.000 30.297 20.483 30.096 50.000 30.028 20.338 40.000 30.444 30.000 10.000 20.000 20.189 40.000 10.000 10.141 40.152 50.017 40.000 50.000 30.838 40.193 30.111 50.105 50.198 30.588 30.000 10.000 20.542 30.343 50.267 30.000 10.000 30.108 50.000 10.333 40.000 50.228 20.202 50.022 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.154 30.275 30.108 30.060 30.295 50.002 40.278 10.000 10.000 10.000 10.006 40.272 20.064 50.815 20.503 30.333 50.000 20.000 30.556 10.001 40.000 20.148 30.078 20.448 10.007 30.000 10.024 30.000 10.000 20.000 30.190 40.000 20.000 10.000 30.000 10.209 50.031 50.573 30.000 10.000 20.041 20.099 30.037 40.000 20.000 10.327 20.364 50.181 20.642 21.000 10.654 40.000 30.023 30.429 30.000 30.000 30.097 30.000 30.278 20.267 20.434 30.048 20.092 30.257 20.030 30.097 40.189 30.000 20.089 20.000 50.000 10.000 30.000 10.115 20.166 30.222 50.222 30.003 30.127 30.213 40.169 20.000 10.000 10.000 30.000 30.044 30.000 30.000 10.000 50.000 40.268 50.222 20.130 20.494 30.000 30.000 10.363 30.015 30.000 30.000 30.000 20.000 30.611 20.400 30.000 20.056 20.278 30.242 40.180 30.000 30.383 40.000 20.209 20.000 10.000 30.000 20.364 20.000 10.000 20.000 10.323 40.302 30.019 40.654 20.000 30.000 30.141 20.045 30.000 50.427 50.514 30.143 30.000 20.028 40.000 30.252 30.402 40.156 40.000 30.028 20.470 30.000 30.444 30.000 10.000 20.000 20.205 30.000 10.000 10.203 30.381 30.026 30.037 30.000 30.881 30.099 40.135 40.239 30.000 40.585 40.000 10.000 20.616 20.778 20.322 20.000 10.000 30.407 30.000 10.333 40.148 30.177 30.242 30.028 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.permissive0.130 40.246 40.083 40.043 50.299 40.000 50.278 10.000 10.000 10.000 10.022 30.175 30.122 20.537 40.521 20.400 30.000 20.000 30.000 30.008 30.000 20.048 40.076 30.182 50.000 40.000 10.022 40.000 10.000 20.000 30.141 50.000 20.000 10.000 30.000 10.210 40.063 20.547 50.000 10.000 20.000 50.100 20.026 50.000 20.000 10.241 40.488 40.000 40.564 51.000 10.672 20.000 30.021 40.486 10.000 30.000 30.067 40.000 30.194 50.033 40.415 40.026 40.025 50.271 10.004 40.094 50.142 50.000 20.000 40.111 30.000 10.000 30.000 10.088 40.083 50.278 20.110 40.000 40.082 50.199 50.137 30.000 10.000 10.000 30.000 30.041 40.000 30.000 10.308 20.067 30.280 30.016 40.101 30.373 50.000 30.000 10.319 40.007 40.000 30.000 30.000 20.000 30.028 50.355 50.000 20.101 10.444 20.289 20.114 50.000 30.394 30.000 20.032 50.000 10.000 30.000 20.201 50.000 10.000 20.000 10.384 20.248 40.000 50.529 40.000 30.000 30.133 30.020 50.089 30.720 30.500 40.099 40.000 20.000 50.000 30.238 40.334 50.190 30.000 30.000 50.317 50.000 30.472 10.000 10.000 20.000 20.094 50.000 10.000 10.082 50.236 40.004 50.019 40.000 30.883 20.061 50.262 20.217 40.000 40.557 50.000 10.000 20.460 40.761 40.156 50.000 10.000 30.259 40.000 10.394 10.019 40.084 40.232 40.000 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


ScanNet Benchmark

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PTv3 ScanNet0.794 10.941 30.813 150.851 60.782 50.890 20.597 10.916 10.696 70.713 30.979 10.635 10.384 20.793 20.907 60.821 30.790 280.696 100.967 30.903 10.805 1
PonderV20.785 20.978 10.800 230.833 200.788 30.853 140.545 140.910 40.713 10.705 40.979 10.596 50.390 10.769 100.832 380.821 30.792 270.730 10.975 10.897 30.785 3
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.
Mix3Dpermissive0.781 30.964 20.855 10.843 140.781 60.858 100.575 50.831 280.685 110.714 20.979 10.594 60.310 230.801 10.892 130.841 20.819 30.723 40.940 110.887 50.725 20
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 40.861 190.818 120.836 170.790 20.875 30.576 40.905 50.704 40.739 10.969 90.611 20.349 90.756 180.958 10.702 400.805 120.708 70.916 280.898 20.801 2
PPT-SpUNet-Joint0.766 50.932 40.794 290.829 220.751 190.854 120.540 170.903 60.630 300.672 120.963 120.565 190.357 70.788 30.900 90.737 220.802 130.685 140.950 50.887 50.780 4
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.
OctFormerpermissive0.766 50.925 60.808 190.849 80.786 40.846 240.566 80.876 120.690 90.674 110.960 140.576 150.226 610.753 200.904 70.777 100.815 50.722 50.923 240.877 110.776 6
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
OccuSeg+Semantic0.764 70.758 550.796 270.839 160.746 210.907 10.562 90.850 200.680 130.672 120.978 40.610 30.335 140.777 60.819 410.847 10.830 10.691 120.972 20.885 70.727 18
CU-Hybrid Net0.764 70.924 70.819 100.840 150.757 140.853 140.580 20.848 210.709 30.643 200.958 170.587 100.295 290.753 200.884 170.758 160.815 50.725 30.927 210.867 180.743 12
O-CNNpermissive0.762 90.924 70.823 60.844 130.770 80.852 160.577 30.847 230.711 20.640 240.958 170.592 70.217 670.762 140.888 140.758 160.813 80.726 20.932 190.868 170.744 11
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
OA-CNN-L_ScanNet200.756 100.783 410.826 50.858 40.776 70.837 300.548 130.896 90.649 220.675 100.962 130.586 110.335 140.771 90.802 450.770 120.787 300.691 120.936 140.880 100.761 8
ConDaFormer0.755 110.927 50.822 70.836 170.801 10.849 190.516 270.864 170.651 210.680 90.958 170.584 130.282 360.759 160.855 280.728 240.802 130.678 160.880 540.873 160.756 9
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
PNE0.755 110.786 390.835 40.834 190.758 120.849 190.570 70.836 270.648 230.668 140.978 40.581 140.367 50.683 300.856 260.804 50.801 170.678 160.961 40.889 40.716 25
P. Hermosilla: Point Neighborhood Embeddings.
DMF-Net0.752 130.906 110.793 310.802 370.689 350.825 410.556 100.867 140.681 120.602 390.960 140.555 240.365 60.779 50.859 230.747 190.795 240.717 60.917 270.856 260.764 7
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
PointTransformerV20.752 130.742 620.809 180.872 10.758 120.860 90.552 110.891 100.610 370.687 50.960 140.559 220.304 260.766 120.926 30.767 130.797 200.644 290.942 90.876 140.722 22
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer0.749 150.793 370.790 320.807 330.750 200.856 110.524 230.881 110.588 490.642 230.977 70.591 80.274 410.781 40.929 20.804 50.796 210.642 300.947 70.885 70.715 26
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 150.909 90.818 120.811 300.752 170.839 290.485 420.842 240.673 140.644 190.957 210.528 330.305 250.773 80.859 230.788 70.818 40.693 110.916 280.856 260.723 21
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 170.623 880.804 210.859 30.745 220.824 430.501 320.912 30.690 90.685 70.956 220.567 180.320 200.768 110.918 40.720 290.802 130.676 190.921 250.881 90.779 5
StratifiedFormerpermissive0.747 180.901 120.803 220.845 120.757 140.846 240.512 280.825 310.696 70.645 180.956 220.576 150.262 520.744 250.861 220.742 200.770 390.705 80.899 400.860 230.734 13
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
Virtual MVFusion0.746 190.771 490.819 100.848 100.702 330.865 80.397 790.899 70.699 50.664 150.948 500.588 90.330 160.746 240.851 320.764 140.796 210.704 90.935 150.866 190.728 16
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNetpermissive0.746 190.870 170.838 20.858 40.729 270.850 180.501 320.874 130.587 500.658 160.956 220.564 200.299 270.765 130.900 90.716 320.812 90.631 350.939 120.858 240.709 27
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)
Retro-FPN0.744 210.842 250.800 230.767 510.740 230.836 320.541 160.914 20.672 150.626 280.958 170.552 250.272 430.777 60.886 160.696 410.801 170.674 210.941 100.858 240.717 23
Peng Xiang*, Xin Wen*, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
EQ-Net0.743 220.620 890.799 260.849 80.730 260.822 450.493 390.897 80.664 160.681 80.955 250.562 210.378 30.760 150.903 80.738 210.801 170.673 220.907 320.877 110.745 10
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT0.742 230.860 200.765 440.819 250.769 90.848 210.533 190.829 290.663 170.631 270.955 250.586 110.274 410.753 200.896 110.729 230.760 460.666 240.921 250.855 280.733 14
LRPNet0.742 230.816 320.806 200.807 330.752 170.828 390.575 50.839 260.699 50.637 250.954 310.520 350.320 200.755 190.834 360.760 150.772 360.676 190.915 300.862 210.717 23
LargeKernel3D0.739 250.909 90.820 90.806 350.740 230.852 160.545 140.826 300.594 480.643 200.955 250.541 270.263 510.723 280.858 250.775 110.767 400.678 160.933 170.848 330.694 32
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN0.736 260.776 450.790 320.851 60.754 160.854 120.491 410.866 150.596 470.686 60.955 250.536 280.342 110.624 450.869 190.787 80.802 130.628 360.927 210.875 150.704 29
MinkowskiNetpermissive0.736 260.859 210.818 120.832 210.709 310.840 280.521 250.853 190.660 190.643 200.951 400.544 260.286 340.731 260.893 120.675 490.772 360.683 150.874 600.852 310.727 18
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 280.890 130.837 30.864 20.726 280.873 40.530 220.824 320.489 810.647 170.978 40.609 40.336 130.624 450.733 540.758 160.776 340.570 600.949 60.877 110.728 16
PointTransformer++0.725 290.727 700.811 170.819 250.765 100.841 270.502 310.814 370.621 330.623 300.955 250.556 230.284 350.620 470.866 200.781 90.757 500.648 270.932 190.862 210.709 27
SparseConvNet0.725 290.647 850.821 80.846 110.721 290.869 50.533 190.754 520.603 430.614 320.955 250.572 170.325 180.710 290.870 180.724 270.823 20.628 360.934 160.865 200.683 35
MatchingNet0.724 310.812 340.812 160.810 310.735 250.834 340.495 380.860 180.572 560.602 390.954 310.512 370.280 380.757 170.845 340.725 260.780 320.606 460.937 130.851 320.700 31
INS-Conv-semantic0.717 320.751 580.759 470.812 290.704 320.868 60.537 180.842 240.609 390.608 350.953 340.534 300.293 300.616 480.864 210.719 310.793 250.640 310.933 170.845 370.663 40
PointMetaBase0.714 330.835 260.785 340.821 230.684 370.846 240.531 210.865 160.614 340.596 430.953 340.500 400.246 570.674 310.888 140.692 420.764 420.624 380.849 750.844 380.675 37
contrastBoundarypermissive0.705 340.769 520.775 390.809 320.687 360.820 480.439 670.812 380.661 180.591 450.945 580.515 360.171 850.633 420.856 260.720 290.796 210.668 230.889 470.847 340.689 33
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 350.774 470.800 230.793 420.760 110.847 230.471 460.802 410.463 880.634 260.968 110.491 430.271 450.726 270.910 50.706 360.815 50.551 710.878 550.833 390.570 71
RFCR0.702 360.889 140.745 570.813 280.672 400.818 520.493 390.815 360.623 310.610 330.947 520.470 510.249 560.594 510.848 330.705 370.779 330.646 280.892 450.823 450.611 54
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
One Thing One Click0.701 370.825 300.796 270.723 580.716 300.832 350.433 690.816 340.634 280.609 340.969 90.418 770.344 100.559 630.833 370.715 330.808 110.560 650.902 370.847 340.680 36
JSENetpermissive0.699 380.881 160.762 450.821 230.667 410.800 640.522 240.792 440.613 350.607 360.935 780.492 420.205 720.576 560.853 300.691 430.758 480.652 260.872 630.828 420.649 44
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
One-Thing-One-Click0.693 390.743 610.794 290.655 810.684 370.822 450.497 370.719 620.622 320.617 310.977 70.447 640.339 120.750 230.664 700.703 390.790 280.596 500.946 80.855 280.647 45
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 400.732 660.772 400.786 430.677 390.866 70.517 260.848 210.509 740.626 280.952 380.536 280.225 630.545 690.704 610.689 460.810 100.564 640.903 360.854 300.729 15
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 410.884 150.754 510.795 400.647 470.818 520.422 710.802 410.612 360.604 370.945 580.462 540.189 800.563 620.853 300.726 250.765 410.632 340.904 340.821 480.606 58
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 420.704 750.741 610.754 550.656 430.829 370.501 320.741 570.609 390.548 520.950 440.522 340.371 40.633 420.756 490.715 330.771 380.623 390.861 710.814 500.658 41
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 430.866 180.748 540.819 250.645 490.794 670.450 570.802 410.587 500.604 370.945 580.464 530.201 750.554 650.840 350.723 280.732 590.602 480.907 320.822 470.603 61
VACNN++0.684 440.728 690.757 500.776 480.690 340.804 620.464 510.816 340.577 550.587 460.945 580.508 390.276 400.671 320.710 590.663 540.750 530.589 550.881 520.832 410.653 43
KP-FCNN0.684 440.847 240.758 490.784 450.647 470.814 550.473 450.772 470.605 410.594 440.935 780.450 620.181 830.587 520.805 440.690 440.785 310.614 420.882 510.819 490.632 50
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DGNet0.684 440.712 740.784 350.782 470.658 420.835 330.499 360.823 330.641 250.597 420.950 440.487 440.281 370.575 570.619 740.647 620.764 420.620 410.871 660.846 360.688 34
Superpoint Network0.683 470.851 230.728 650.800 390.653 450.806 600.468 480.804 390.572 560.602 390.946 550.453 610.239 600.519 740.822 390.689 460.762 450.595 520.895 430.827 430.630 51
PointContrast_LA_SEM0.683 470.757 560.784 350.786 430.639 510.824 430.408 740.775 460.604 420.541 540.934 820.532 310.269 470.552 660.777 470.645 650.793 250.640 310.913 310.824 440.671 38
VI-PointConv0.676 490.770 510.754 510.783 460.621 550.814 550.552 110.758 500.571 580.557 500.954 310.529 320.268 490.530 720.682 650.675 490.719 620.603 470.888 480.833 390.665 39
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 500.789 380.748 540.763 530.635 530.814 550.407 760.747 540.581 540.573 470.950 440.484 450.271 450.607 490.754 500.649 590.774 350.596 500.883 500.823 450.606 58
SALANet0.670 510.816 320.770 420.768 500.652 460.807 590.451 540.747 540.659 200.545 530.924 880.473 500.149 950.571 590.811 430.635 680.746 540.623 390.892 450.794 620.570 71
PointConvpermissive0.666 520.781 420.759 470.699 660.644 500.822 450.475 440.779 450.564 610.504 700.953 340.428 710.203 740.586 540.754 500.661 550.753 510.588 560.902 370.813 520.642 46
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 520.703 760.781 370.751 570.655 440.830 360.471 460.769 480.474 840.537 560.951 400.475 490.279 390.635 400.698 640.675 490.751 520.553 700.816 820.806 540.703 30
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PPCNN++permissive0.663 540.746 590.708 680.722 590.638 520.820 480.451 540.566 890.599 450.541 540.950 440.510 380.313 220.648 370.819 410.616 730.682 770.590 540.869 670.810 530.656 42
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 550.778 430.702 710.806 350.619 560.813 580.468 480.693 700.494 770.524 620.941 700.449 630.298 280.510 760.821 400.675 490.727 610.568 620.826 800.803 560.637 48
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 560.698 780.743 590.650 820.564 730.820 480.505 300.758 500.631 290.479 740.945 580.480 470.226 610.572 580.774 480.690 440.735 570.614 420.853 740.776 770.597 64
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 570.752 570.734 630.664 790.583 680.815 540.399 780.754 520.639 260.535 580.942 680.470 510.309 240.665 330.539 790.650 580.708 670.635 330.857 730.793 640.642 46
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 580.778 430.731 640.699 660.577 690.829 370.446 590.736 580.477 830.523 640.945 580.454 580.269 470.484 830.749 530.618 710.738 550.599 490.827 790.792 670.621 53
PointConv-SFPN0.641 590.776 450.703 700.721 600.557 760.826 400.451 540.672 750.563 620.483 730.943 670.425 740.162 900.644 380.726 550.659 560.709 660.572 590.875 580.786 720.559 77
MVPNetpermissive0.641 590.831 270.715 660.671 760.590 640.781 730.394 800.679 720.642 240.553 510.937 750.462 540.256 530.649 360.406 920.626 690.691 740.666 240.877 560.792 670.608 57
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 610.717 730.701 720.692 690.576 700.801 630.467 500.716 630.563 620.459 800.953 340.429 700.169 870.581 550.854 290.605 740.710 640.550 720.894 440.793 640.575 69
FPConvpermissive0.639 620.785 400.760 460.713 640.603 590.798 650.392 810.534 940.603 430.524 620.948 500.457 560.250 550.538 700.723 570.598 780.696 720.614 420.872 630.799 570.567 74
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 630.797 360.769 430.641 870.590 640.820 480.461 520.537 930.637 270.536 570.947 520.388 840.206 710.656 340.668 680.647 620.732 590.585 570.868 680.793 640.473 96
PointSPNet0.637 640.734 650.692 790.714 630.576 700.797 660.446 590.743 560.598 460.437 850.942 680.403 800.150 940.626 440.800 460.649 590.697 710.557 680.846 760.777 760.563 75
SConv0.636 650.830 280.697 750.752 560.572 720.780 750.445 610.716 630.529 670.530 590.951 400.446 650.170 860.507 780.666 690.636 670.682 770.541 780.886 490.799 570.594 65
Supervoxel-CNN0.635 660.656 830.711 670.719 610.613 570.757 840.444 640.765 490.534 660.566 480.928 860.478 480.272 430.636 390.531 810.664 530.645 870.508 850.864 700.792 670.611 54
joint point-basedpermissive0.634 670.614 900.778 380.667 780.633 540.825 410.420 720.804 390.467 860.561 490.951 400.494 410.291 310.566 600.458 870.579 840.764 420.559 670.838 770.814 500.598 63
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 680.731 670.688 820.675 730.591 630.784 720.444 640.565 900.610 370.492 710.949 480.456 570.254 540.587 520.706 600.599 770.665 830.612 450.868 680.791 700.579 68
APCF-Net0.631 690.742 620.687 840.672 740.557 760.792 700.408 740.665 760.545 640.508 670.952 380.428 710.186 810.634 410.702 620.620 700.706 680.555 690.873 610.798 590.581 67
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN0.631 690.771 490.692 790.672 740.524 810.837 300.440 660.706 680.538 650.446 820.944 640.421 760.219 660.552 660.751 520.591 800.737 560.543 770.901 390.768 790.557 78
3DSM_DMMF0.631 690.626 870.745 570.801 380.607 580.751 850.506 290.729 610.565 600.491 720.866 1020.434 660.197 780.595 500.630 730.709 350.705 690.560 650.875 580.740 870.491 91
FusionAwareConv0.630 720.604 920.741 610.766 520.590 640.747 860.501 320.734 590.503 760.527 600.919 920.454 580.323 190.550 680.420 910.678 480.688 750.544 750.896 420.795 610.627 52
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 730.800 350.625 940.719 610.545 780.806 600.445 610.597 840.448 910.519 650.938 740.481 460.328 170.489 820.499 860.657 570.759 470.592 530.881 520.797 600.634 49
SegGroup_sempermissive0.627 740.818 310.747 560.701 650.602 600.764 810.385 850.629 810.490 790.508 670.931 850.409 790.201 750.564 610.725 560.618 710.692 730.539 790.873 610.794 620.548 81
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 750.830 280.694 770.757 540.563 740.772 790.448 580.647 790.520 700.509 660.949 480.431 690.191 790.496 800.614 750.647 620.672 810.535 810.876 570.783 730.571 70
dtc_net0.625 750.703 760.751 530.794 410.535 790.848 210.480 430.676 740.528 680.469 770.944 640.454 580.004 1070.464 850.636 720.704 380.758 480.548 740.924 230.787 710.492 90
HPEIN0.618 770.729 680.668 850.647 840.597 620.766 800.414 730.680 710.520 700.525 610.946 550.432 670.215 680.493 810.599 760.638 660.617 920.570 600.897 410.806 540.605 60
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
SPH3D-GCNpermissive0.610 780.858 220.772 400.489 990.532 800.792 700.404 770.643 800.570 590.507 690.935 780.414 780.046 1040.510 760.702 620.602 760.705 690.549 730.859 720.773 780.534 84
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 790.760 540.667 860.649 830.521 820.793 680.457 530.648 780.528 680.434 870.947 520.401 810.153 930.454 860.721 580.648 610.717 630.536 800.904 340.765 800.485 92
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 800.634 860.743 590.697 680.601 610.781 730.437 680.585 870.493 780.446 820.933 830.394 820.011 1060.654 350.661 710.603 750.733 580.526 820.832 780.761 820.480 93
LAP-D0.594 810.720 710.692 790.637 880.456 910.773 780.391 830.730 600.587 500.445 840.940 720.381 850.288 320.434 890.453 890.591 800.649 850.581 580.777 860.749 860.610 56
DPC0.592 820.720 710.700 730.602 920.480 870.762 830.380 860.713 660.585 530.437 850.940 720.369 870.288 320.434 890.509 850.590 820.639 900.567 630.772 870.755 840.592 66
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 830.766 530.659 890.683 710.470 900.740 880.387 840.620 830.490 790.476 750.922 900.355 900.245 580.511 750.511 840.571 850.643 880.493 890.872 630.762 810.600 62
ROSMRF0.580 840.772 480.707 690.681 720.563 740.764 810.362 880.515 950.465 870.465 790.936 770.427 730.207 700.438 870.577 770.536 880.675 800.486 900.723 930.779 740.524 86
SD-DETR0.576 850.746 590.609 980.445 1030.517 830.643 990.366 870.714 650.456 890.468 780.870 1010.432 670.264 500.558 640.674 660.586 830.688 750.482 910.739 910.733 890.537 83
SQN_0.1%0.569 860.676 800.696 760.657 800.497 840.779 760.424 700.548 910.515 720.376 920.902 990.422 750.357 70.379 930.456 880.596 790.659 840.544 750.685 960.665 1000.556 79
TextureNetpermissive0.566 870.672 820.664 870.671 760.494 850.719 890.445 610.678 730.411 970.396 900.935 780.356 890.225 630.412 910.535 800.565 860.636 910.464 930.794 850.680 970.568 73
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
DVVNet0.562 880.648 840.700 730.770 490.586 670.687 930.333 920.650 770.514 730.475 760.906 960.359 880.223 650.340 950.442 900.422 990.668 820.501 860.708 940.779 740.534 84
Pointnet++ & Featurepermissive0.557 890.735 640.661 880.686 700.491 860.744 870.392 810.539 920.451 900.375 930.946 550.376 860.205 720.403 920.356 950.553 870.643 880.497 870.824 810.756 830.515 87
GMLPs0.538 900.495 1000.693 780.647 840.471 890.793 680.300 950.477 960.505 750.358 940.903 980.327 930.081 1010.472 840.529 820.448 970.710 640.509 830.746 890.737 880.554 80
PanopticFusion-label0.529 910.491 1010.688 820.604 910.386 960.632 1000.225 1050.705 690.434 940.293 1000.815 1030.348 910.241 590.499 790.669 670.507 900.649 850.442 990.796 840.602 1030.561 76
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
subcloud_weak0.516 920.676 800.591 1010.609 890.442 920.774 770.335 910.597 840.422 960.357 950.932 840.341 920.094 1000.298 970.528 830.473 950.676 790.495 880.602 1020.721 920.349 103
Online SegFusion0.515 930.607 910.644 920.579 940.434 930.630 1010.353 890.628 820.440 920.410 880.762 1060.307 950.167 880.520 730.403 930.516 890.565 950.447 970.678 970.701 940.514 88
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
3DMV, FTSDF0.501 940.558 960.608 990.424 1050.478 880.690 920.246 1010.586 860.468 850.450 810.911 940.394 820.160 910.438 870.212 1020.432 980.541 1000.475 920.742 900.727 900.477 94
PCNN0.498 950.559 950.644 920.560 960.420 950.711 910.229 1030.414 970.436 930.352 960.941 700.324 940.155 920.238 1020.387 940.493 910.529 1010.509 830.813 830.751 850.504 89
3DMV0.484 960.484 1020.538 1030.643 860.424 940.606 1040.310 930.574 880.433 950.378 910.796 1040.301 960.214 690.537 710.208 1030.472 960.507 1040.413 1020.693 950.602 1030.539 82
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 970.577 940.611 970.356 1070.321 1040.715 900.299 970.376 1010.328 1040.319 980.944 640.285 980.164 890.216 1050.229 1000.484 930.545 990.456 950.755 880.709 930.475 95
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 980.679 790.604 1000.578 950.380 970.682 940.291 980.106 1070.483 820.258 1050.920 910.258 1020.025 1050.231 1040.325 960.480 940.560 970.463 940.725 920.666 990.231 107
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 990.474 1030.623 950.463 1010.366 990.651 970.310 930.389 1000.349 1020.330 970.937 750.271 1000.126 970.285 980.224 1010.350 1040.577 940.445 980.625 1000.723 910.394 99
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
SurfaceConvPF0.442 1000.505 990.622 960.380 1060.342 1020.654 960.227 1040.397 990.367 1000.276 1020.924 880.240 1030.198 770.359 940.262 980.366 1010.581 930.435 1000.640 990.668 980.398 98
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET20.442 1000.548 970.548 1020.597 930.363 1000.628 1020.300 950.292 1020.374 990.307 990.881 1000.268 1010.186 810.238 1020.204 1040.407 1000.506 1050.449 960.667 980.620 1020.462 97
Tangent Convolutionspermissive0.438 1020.437 1050.646 910.474 1000.369 980.645 980.353 890.258 1040.282 1060.279 1010.918 930.298 970.147 960.283 990.294 970.487 920.562 960.427 1010.619 1010.633 1010.352 102
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1030.525 980.647 900.522 970.324 1030.488 1070.077 1080.712 670.353 1010.401 890.636 1080.281 990.176 840.340 950.565 780.175 1080.551 980.398 1030.370 1080.602 1030.361 101
SPLAT Netcopyleft0.393 1040.472 1040.511 1040.606 900.311 1050.656 950.245 1020.405 980.328 1040.197 1060.927 870.227 1050.000 1090.001 1090.249 990.271 1070.510 1020.383 1050.593 1030.699 950.267 105
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
ScanNet+FTSDF0.383 1050.297 1070.491 1050.432 1040.358 1010.612 1030.274 990.116 1060.411 970.265 1030.904 970.229 1040.079 1020.250 1000.185 1050.320 1050.510 1020.385 1040.548 1040.597 1060.394 99
PointNet++permissive0.339 1060.584 930.478 1060.458 1020.256 1070.360 1080.250 1000.247 1050.278 1070.261 1040.677 1070.183 1060.117 980.212 1060.145 1070.364 1020.346 1080.232 1080.548 1040.523 1070.252 106
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 1070.353 1060.290 1080.278 1080.166 1080.553 1050.169 1070.286 1030.147 1080.148 1080.908 950.182 1070.064 1030.023 1080.018 1090.354 1030.363 1060.345 1060.546 1060.685 960.278 104
ScanNetpermissive0.306 1080.203 1080.366 1070.501 980.311 1050.524 1060.211 1060.002 1090.342 1030.189 1070.786 1050.145 1080.102 990.245 1010.152 1060.318 1060.348 1070.300 1070.460 1070.437 1080.182 108
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 1090.000 1090.041 1090.172 1090.030 1090.062 1090.001 1090.035 1080.004 1090.051 1090.143 1090.019 1090.003 1080.041 1070.050 1080.003 1090.054 1090.018 1090.005 1090.264 1090.082 109


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




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
ExtMask3D0.598 10.852 110.692 40.433 200.461 40.791 10.264 50.488 280.493 10.508 30.528 80.594 50.706 20.791 50.483 30.734 40.595 20.911 90.437 2
MAFT0.596 20.889 80.721 10.448 140.460 50.768 30.251 60.558 150.408 30.504 40.539 40.616 30.618 60.858 20.482 40.684 110.551 90.931 60.450 1
UniPerception0.588 30.963 20.667 60.493 70.472 30.750 60.229 90.528 210.468 20.498 60.542 20.643 10.530 140.661 280.463 90.695 100.599 10.972 10.420 4
Queryformer0.583 40.926 40.702 20.393 260.504 10.733 120.276 40.527 220.373 80.479 70.534 60.533 130.697 30.720 200.436 120.745 30.592 30.958 30.363 13
SIM3D0.575 50.889 80.675 50.284 410.401 100.762 50.329 20.531 200.408 40.521 20.541 30.587 60.646 40.744 160.467 70.665 130.579 50.886 190.425 3
PBNetpermissive0.573 60.926 40.575 160.619 10.472 20.736 100.239 80.487 290.383 70.459 90.506 110.533 120.585 80.767 90.404 140.717 50.559 80.969 20.381 9
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
OneFormer3D0.566 70.781 170.697 30.562 20.431 60.770 20.331 10.400 360.373 90.529 10.504 120.568 90.475 190.732 180.470 60.762 10.550 100.871 250.379 10
Mask3D0.566 70.926 40.597 110.408 230.420 80.737 90.239 70.598 80.386 60.458 100.549 10.568 100.716 10.601 330.480 50.646 160.575 60.922 70.364 12
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
ISBNetpermissive0.559 90.939 30.655 70.383 280.426 70.763 40.180 110.534 190.386 50.499 50.509 100.621 20.427 280.704 230.467 80.649 150.571 70.948 40.401 5
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
GraphCut0.552 101.000 10.611 100.438 170.392 120.714 130.139 140.598 90.327 120.389 130.510 90.598 40.427 290.754 120.463 100.761 20.588 40.903 120.329 19
SPFormerpermissive0.549 110.745 200.640 80.484 80.395 110.739 80.311 30.566 130.335 110.468 80.492 130.555 110.478 180.747 140.436 110.712 60.540 110.893 160.343 18
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
DKNet0.532 120.815 140.624 90.517 40.377 140.749 70.107 160.509 250.304 140.437 110.475 140.581 70.539 120.775 80.339 190.640 180.506 140.901 130.385 8
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
IPCA-Inst0.520 130.889 80.551 200.548 30.418 90.665 230.064 250.585 100.260 220.277 260.471 160.500 140.644 50.785 60.369 150.591 240.511 120.878 220.362 14
SoftGroup++0.513 140.704 260.578 150.398 250.363 200.704 140.061 260.647 40.297 190.378 160.537 50.343 170.614 70.828 40.295 240.710 80.505 160.875 240.394 6
SSTNetpermissive0.506 150.738 230.549 210.497 60.316 250.693 170.178 120.377 390.198 280.330 180.463 180.576 80.515 150.857 30.494 10.637 190.457 200.943 50.290 28
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SoftGrouppermissive0.504 160.667 330.579 130.372 300.381 130.694 160.072 220.677 20.303 150.387 140.531 70.319 210.582 90.754 110.318 200.643 170.492 170.907 110.388 7
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
DANCENET0.504 160.926 40.579 120.472 100.367 170.626 330.165 130.432 310.221 240.408 120.449 200.411 150.564 100.746 150.421 130.707 90.438 230.846 330.288 29
TD3Dpermissive0.489 180.852 110.511 290.434 180.322 240.735 110.101 190.512 240.355 100.349 170.468 170.283 250.514 160.676 270.268 290.671 120.510 130.908 100.329 20
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
OccuSeg+instance0.486 190.802 160.536 230.428 210.369 160.702 150.205 100.331 440.301 160.379 150.474 150.327 180.437 240.862 10.485 20.601 220.394 310.846 350.273 31
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
TopoSeg0.479 200.704 260.564 170.467 120.366 180.633 310.068 230.554 160.262 210.328 190.447 210.323 190.534 130.722 190.288 260.614 200.482 180.912 80.358 16
DualGroup0.469 210.815 140.552 190.398 240.374 150.683 190.130 150.539 180.310 130.327 200.407 240.276 260.447 230.535 370.342 180.659 140.455 210.900 150.301 24
SSEC0.465 220.667 330.578 140.502 50.362 210.641 300.035 350.605 60.291 200.323 210.451 190.296 230.417 320.677 260.245 330.501 410.506 150.900 140.366 11
HAISpermissive0.457 230.704 260.561 180.457 130.364 190.673 200.046 340.547 170.194 290.308 220.426 220.288 240.454 220.711 210.262 300.563 310.434 250.889 180.344 17
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
DD-UNet+Group0.436 240.630 410.508 320.480 90.310 260.624 350.065 240.638 50.174 300.256 300.384 270.194 380.428 260.759 100.289 250.574 280.400 290.849 320.291 27
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
INS-Conv-instance0.435 250.716 250.495 340.355 320.331 220.689 180.102 180.394 380.208 270.280 240.395 260.250 290.544 110.741 170.309 220.536 370.391 320.842 380.258 35
Mask-Group0.434 260.778 180.516 270.471 110.330 230.658 240.029 370.526 230.249 230.256 290.400 250.309 220.384 360.296 530.368 160.575 270.425 260.877 230.362 15
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
Box2Mask0.433 270.741 210.463 390.433 190.283 290.625 340.103 170.298 490.125 380.260 280.424 230.322 200.472 200.701 240.363 170.711 70.309 470.882 200.272 33
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
RPGN0.428 280.630 410.508 310.367 310.249 360.658 250.016 440.673 30.131 360.234 330.383 280.270 270.434 250.748 130.274 280.609 210.406 280.842 370.267 34
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
DENet0.413 290.741 210.520 250.237 440.284 280.523 430.097 200.691 10.138 330.209 430.229 450.238 320.390 340.707 220.310 210.448 480.470 190.892 170.310 22
PointGroup0.407 300.639 400.496 330.415 220.243 380.645 290.021 420.570 120.114 390.211 410.359 300.217 360.428 270.660 290.256 310.562 320.341 390.860 280.291 26
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]
CSC-Pretrained0.405 310.738 230.465 380.331 360.205 420.655 260.051 300.601 70.092 430.211 420.329 330.198 370.459 210.775 70.195 400.524 390.400 300.878 210.184 44
PE0.396 320.667 330.467 370.446 160.243 370.624 360.022 410.577 110.106 400.219 360.340 310.239 310.487 170.475 440.225 350.541 360.350 370.818 400.273 32
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
Dyco3Dcopyleft0.395 330.642 390.518 260.447 150.259 350.666 220.050 310.251 530.166 310.231 340.362 290.232 330.331 390.535 360.229 340.587 250.438 240.850 300.317 21
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OSIS0.392 340.778 180.530 240.220 460.278 300.567 400.083 210.330 450.299 170.270 270.310 360.143 430.260 430.624 310.277 270.568 300.361 350.865 270.301 23
AOIA0.387 350.704 260.515 280.385 270.225 410.669 210.005 510.482 300.126 370.181 460.269 420.221 350.426 300.478 430.218 360.592 230.371 330.851 290.242 37
SSEN0.384 360.852 110.494 350.192 470.226 400.648 280.022 400.398 370.299 180.277 250.317 350.231 340.194 500.514 400.196 380.586 260.444 220.843 360.184 43
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
PCJC0.375 370.704 260.542 220.284 400.197 440.649 270.006 480.426 320.138 340.242 310.304 370.183 410.388 350.629 300.141 500.546 350.344 380.738 460.283 30
ClickSeg_Instance0.366 380.654 370.375 430.184 480.302 270.592 380.050 320.300 480.093 420.283 230.277 390.249 300.426 310.615 320.299 230.504 400.367 340.832 390.191 42
SphereSeg0.357 390.651 380.411 410.345 330.264 340.630 320.059 270.289 510.212 250.240 320.336 320.158 420.305 400.557 340.159 460.455 470.341 400.726 480.294 25
3D-MPA0.355 400.457 520.484 360.299 380.277 310.591 390.047 330.332 420.212 260.217 370.278 380.193 390.413 330.410 470.195 390.574 290.352 360.849 310.213 40
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
NeuralBF0.353 410.593 430.511 300.375 290.264 330.597 370.008 460.332 430.160 320.229 350.274 410.000 640.206 470.678 250.155 470.485 430.422 270.816 410.254 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
RWSeg0.348 420.475 490.456 400.320 370.275 320.476 450.020 430.491 270.056 500.212 400.320 340.261 280.302 410.520 380.182 420.557 330.285 490.867 260.197 41
GICN0.341 430.580 440.371 440.344 340.198 430.469 460.052 290.564 140.093 410.212 390.212 470.127 450.347 380.537 350.206 370.525 380.329 420.729 470.241 38
One_Thing_One_Clickpermissive0.326 440.472 500.361 450.232 450.183 450.555 410.000 570.498 260.038 520.195 440.226 460.362 160.168 510.469 450.251 320.553 340.335 410.846 340.117 52
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Occipital-SCS0.320 450.679 320.352 460.334 350.229 390.436 470.025 380.412 350.058 480.161 510.240 440.085 470.262 420.496 420.187 410.467 450.328 430.775 420.231 39
Sparse R-CNN0.292 460.704 260.213 560.153 500.154 470.551 420.053 280.212 540.132 350.174 480.274 400.070 490.363 370.441 460.176 430.424 500.234 510.758 440.161 48
MTML0.282 470.577 450.380 420.182 490.107 530.430 480.001 540.422 330.057 490.179 470.162 500.070 500.229 450.511 410.161 440.491 420.313 440.650 530.162 46
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
SALoss-ResNet0.262 480.667 330.335 470.067 570.123 510.427 490.022 390.280 520.058 470.216 380.211 480.039 530.142 530.519 390.106 540.338 540.310 460.721 490.138 49
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)
MASCpermissive0.254 490.463 510.249 550.113 510.167 460.412 510.000 560.374 400.073 440.173 490.243 430.130 440.228 460.368 490.160 450.356 520.208 520.711 500.136 50
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
3D-BoNet0.253 500.519 470.324 500.251 430.137 500.345 560.031 360.419 340.069 450.162 500.131 520.052 510.202 490.338 510.147 490.301 570.303 480.651 520.178 45
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
SPG_WSIS0.251 510.380 540.274 530.289 390.144 480.413 500.000 570.311 460.065 460.113 530.130 530.029 560.204 480.388 480.108 530.459 460.311 450.769 430.127 51
SegGroup_inspermissive0.246 520.556 460.335 480.062 590.115 520.490 440.000 570.297 500.018 560.186 450.142 510.083 480.233 440.216 550.153 480.469 440.251 500.744 450.083 55
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
PanopticFusion-inst0.214 530.250 590.330 490.275 420.103 540.228 620.000 570.345 410.024 540.088 550.203 490.186 400.167 520.367 500.125 510.221 600.112 620.666 510.162 47
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
UNet-backbone0.161 540.519 470.259 540.084 530.059 560.325 580.002 520.093 590.009 580.077 570.064 560.045 520.044 600.161 570.045 560.331 550.180 540.566 540.033 64
3D-SISpermissive0.161 540.407 530.155 610.068 560.043 600.346 550.001 530.134 560.005 590.088 540.106 550.037 540.135 550.321 520.028 600.339 530.116 610.466 570.093 54
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.158 560.356 550.173 590.113 520.140 490.359 520.012 450.023 620.039 510.134 520.123 540.008 600.089 560.149 580.117 520.221 590.128 590.563 550.094 53
Region-18class0.146 570.175 630.321 510.080 540.062 550.357 530.000 570.307 470.002 610.066 580.044 580.000 640.018 620.036 630.054 550.447 490.133 570.472 560.060 59
SemRegionNet-20cls0.121 580.296 570.203 570.071 550.058 570.349 540.000 570.150 550.019 550.054 600.034 610.017 590.052 580.042 620.013 630.209 610.183 530.371 580.057 60
Hier3Dcopyleft0.117 590.222 610.161 600.054 610.027 620.289 590.000 570.124 570.001 630.079 560.061 570.027 570.141 540.240 540.005 640.310 560.129 580.153 640.081 56
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
3D-BEVIS0.117 590.250 590.308 520.020 630.009 650.269 610.006 490.008 630.029 530.037 630.014 640.003 620.036 610.147 590.042 580.381 510.118 600.362 590.069 58
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
tmp0.113 610.333 560.151 620.056 600.053 580.344 570.000 570.105 580.016 570.049 610.035 600.020 580.053 570.048 610.013 620.183 630.173 550.344 610.054 61
Sem_Recon_ins0.098 620.295 580.187 580.015 640.036 610.213 630.005 500.038 610.003 600.056 590.037 590.036 550.015 630.051 600.044 570.209 620.098 630.354 600.071 57
ASIS0.085 630.037 640.080 640.066 580.047 590.282 600.000 570.052 600.002 620.047 620.026 620.001 630.046 590.194 560.031 590.264 580.140 560.167 630.047 63
Sgpn_scannet0.049 640.023 650.134 630.031 620.013 640.144 640.006 470.008 640.000 640.028 640.017 630.003 610.009 650.000 640.021 610.122 640.095 640.175 620.054 62
MaskRCNN 2d->3d Proj0.022 650.185 620.000 650.000 650.015 630.000 650.000 550.006 650.000 640.010 650.006 650.107 460.012 640.000 640.002 650.027 650.004 650.022 650.001 65


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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Virtual MVFusion (R)0.745 10.861 10.839 10.881 10.672 10.512 10.422 150.898 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
BPNet_2Dcopyleft0.670 20.822 30.795 30.836 20.659 20.481 20.451 110.769 30.656 30.567 30.931 30.395 40.390 40.700 30.534 30.689 90.770 20.574 30.865 60.831 30.675 4
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
CU-Hybrid-2D Net0.636 30.825 20.820 20.179 200.648 30.463 30.549 20.742 60.676 20.628 20.961 10.420 20.379 50.684 60.381 150.732 20.723 30.599 20.827 130.851 20.634 6
CMX0.613 40.681 70.725 90.502 120.634 50.297 150.478 90.830 20.651 40.537 60.924 40.375 50.315 120.686 50.451 120.714 40.543 180.504 50.894 40.823 40.688 3
DMMF_3d0.605 50.651 80.744 70.782 30.637 40.387 40.536 30.732 70.590 60.540 50.856 180.359 90.306 130.596 110.539 20.627 180.706 40.497 70.785 180.757 160.476 19
MCA-Net0.595 60.533 170.756 60.746 40.590 80.334 70.506 60.670 120.587 70.500 100.905 80.366 80.352 80.601 100.506 60.669 150.648 70.501 60.839 120.769 120.516 18
RFBNet0.592 70.616 90.758 50.659 50.581 90.330 80.469 100.655 150.543 120.524 70.924 40.355 100.336 100.572 140.479 80.671 130.648 70.480 90.814 160.814 50.614 9
FAN_NV_RVC0.586 80.510 180.764 40.079 230.620 70.330 80.494 70.753 40.573 80.556 40.884 130.405 30.303 140.718 20.452 110.672 120.658 50.509 40.898 30.813 60.727 2
DCRedNet0.583 90.682 60.723 100.542 110.510 170.310 120.451 110.668 130.549 110.520 80.920 60.375 50.446 20.528 170.417 130.670 140.577 150.478 100.862 70.806 70.628 8
MIX6D_RVC0.582 100.695 40.687 140.225 180.632 60.328 100.550 10.748 50.623 50.494 130.890 110.350 120.254 200.688 40.454 100.716 30.597 140.489 80.881 50.768 130.575 12
SSMAcopyleft0.577 110.695 40.716 120.439 140.563 110.314 110.444 130.719 80.551 100.503 90.887 120.346 130.348 90.603 90.353 170.709 50.600 120.457 120.901 20.786 80.599 11
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
UNIV_CNP_RVC_UE0.566 120.569 160.686 160.435 150.524 140.294 160.421 160.712 90.543 120.463 150.872 140.320 140.363 70.611 80.477 90.686 100.627 90.443 150.862 70.775 110.639 5
EMSAFormer0.564 130.581 130.736 80.564 100.546 130.219 200.517 40.675 110.486 170.427 190.904 90.352 110.320 110.589 120.528 40.708 60.464 210.413 190.847 110.786 80.611 10
SN_RN152pyrx8_RVCcopyleft0.546 140.572 140.663 180.638 70.518 150.298 140.366 210.633