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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
OA-CNN-L_ScanNet2000.333 20.558 10.269 20.124 40.448 60.080 40.272 30.000 10.000 10.000 10.342 50.515 20.524 20.713 80.789 20.158 40.384 30.000 30.806 20.125 20.000 40.496 30.332 20.498 70.227 40.024 20.474 10.000 10.003 20.071 40.487 10.000 30.000 10.110 20.000 20.876 10.013 80.703 10.000 30.076 40.473 40.355 40.906 20.000 10.000 10.476 40.706 10.000 70.672 60.835 50.748 20.015 70.223 20.860 30.000 10.000 40.572 20.000 50.509 30.313 20.662 10.398 50.396 10.411 60.276 10.527 10.711 10.000 20.076 50.946 10.166 20.000 10.022 20.160 10.183 40.493 40.699 30.637 20.403 20.330 50.406 40.526 20.024 10.000 10.392 40.000 50.016 80.000 30.196 20.915 20.112 30.557 30.197 10.352 40.877 20.000 30.000 10.592 60.103 60.000 80.067 10.000 10.089 10.735 30.625 30.130 50.568 20.836 20.271 10.534 30.043 60.799 20.001 20.445 10.000 10.000 20.024 10.661 20.000 10.262 10.000 10.591 30.517 70.373 30.788 30.021 20.000 10.455 10.517 40.320 30.823 40.200 80.001 80.150 30.100 40.000 10.736 20.668 20.103 60.052 30.662 10.720 10.000 10.602 40.112 30.002 30.000 10.637 40.000 20.000 10.621 30.569 10.398 20.412 30.234 30.949 10.363 10.492 70.495 30.251 30.665 30.000 10.001 50.805 20.833 20.794 40.000 10.821 10.314 20.843 50.000 10.560 20.245 20.262 20.713 10.370 5
PPT-SpUNet-F.T.0.332 30.556 20.270 10.123 50.519 10.091 20.349 20.000 10.000 10.000 10.339 60.383 50.498 50.833 20.807 10.241 10.584 20.000 30.755 30.124 30.000 40.608 20.330 30.530 40.314 10.000 40.374 30.000 10.000 30.197 10.459 30.000 30.000 10.117 10.000 20.876 10.095 10.682 20.000 30.086 30.518 20.433 10.930 10.000 10.000 10.563 30.542 50.077 40.715 20.858 30.756 10.008 80.171 40.874 20.000 10.039 10.550 30.000 50.545 20.256 30.657 30.453 10.351 30.449 50.213 20.392 30.611 40.000 20.037 60.946 10.138 50.000 10.000 40.063 30.308 10.537 20.796 10.673 10.323 50.392 30.400 50.509 30.000 20.000 10.649 10.000 50.023 50.000 30.000 30.914 30.002 70.506 70.163 50.359 30.872 30.000 30.000 10.623 20.112 30.001 70.000 40.000 10.021 20.753 10.565 70.150 10.579 10.806 40.267 20.616 10.042 70.783 40.000 30.374 50.000 10.000 20.000 20.620 40.000 10.000 40.000 10.572 60.634 10.350 40.792 20.000 30.000 10.376 40.535 20.378 20.855 10.672 10.074 50.000 40.185 30.000 10.727 30.660 30.076 80.000 60.432 40.646 30.000 10.594 50.006 70.000 40.000 10.658 20.000 20.000 10.661 10.549 30.300 50.291 50.045 50.942 40.304 20.600 30.572 20.135 70.695 10.000 10.008 30.793 30.942 10.899 20.000 10.816 20.181 40.897 10.000 10.679 10.223 30.264 10.691 20.345 6
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.
AWCS0.305 50.508 50.225 50.142 20.463 50.063 60.195 50.000 10.000 10.000 10.467 20.551 10.504 30.773 30.764 50.142 50.029 80.000 30.626 60.100 50.000 40.360 50.179 60.507 60.137 60.006 30.300 50.000 10.000 30.172 30.364 60.512 20.000 10.056 50.000 20.865 50.093 30.634 80.000 30.071 60.396 60.296 70.876 40.000 10.000 10.373 50.436 70.063 60.749 10.877 20.721 30.131 20.124 50.804 60.000 10.000 40.515 40.010 40.452 50.252 40.578 50.417 20.179 80.484 40.171 30.337 50.606 50.000 20.115 30.937 50.142 40.000 10.008 30.000 70.157 70.484 50.402 80.501 60.339 30.553 10.529 20.478 50.000 20.000 10.404 30.001 40.022 60.077 20.000 30.894 60.219 10.628 20.093 60.305 50.886 10.233 20.000 10.603 30.112 30.023 50.000 40.000 10.000 30.741 20.664 20.097 60.253 50.782 50.264 30.523 40.154 10.707 70.000 30.411 30.000 10.000 20.000 20.332 70.000 10.000 40.000 10.602 20.595 40.185 70.656 70.159 10.000 10.355 50.424 60.154 60.729 60.516 50.220 40.620 20.084 50.000 10.707 50.651 40.173 10.014 50.381 80.582 70.000 10.619 20.049 60.000 40.000 10.702 10.000 20.000 10.302 70.489 60.317 40.334 40.392 10.922 50.254 50.533 60.394 40.129 80.613 60.000 10.000 60.820 10.649 50.749 50.000 10.782 50.282 30.863 30.000 10.288 70.006 50.220 50.633 50.542 1
Minkowski 34Dpermissive0.253 70.463 70.154 80.102 70.381 80.084 30.134 80.000 10.000 10.000 10.386 40.141 80.279 80.737 70.703 70.014 80.164 60.000 30.663 40.092 70.000 40.224 70.291 40.531 30.056 80.000 40.242 70.000 10.000 30.013 60.331 70.000 30.000 10.035 80.001 10.858 60.059 70.650 70.000 30.056 70.353 70.299 60.670 70.000 10.000 10.284 70.484 60.071 50.594 70.720 70.710 60.027 50.068 80.813 50.000 10.005 30.492 60.164 10.274 70.111 80.571 70.307 80.293 50.307 80.150 40.163 80.531 70.002 10.545 10.932 60.093 80.000 10.000 40.002 60.159 60.368 80.581 70.440 80.228 80.406 20.282 80.294 70.000 20.000 10.189 70.060 10.036 30.000 30.000 30.897 50.000 80.525 60.025 80.205 80.771 80.000 30.000 10.593 50.108 50.044 30.000 40.000 10.000 30.282 80.589 60.094 70.169 70.466 80.227 70.419 80.125 30.757 50.002 10.334 70.000 10.000 20.000 20.357 60.000 10.000 40.000 10.582 50.513 80.337 50.612 80.000 30.000 10.250 70.352 80.136 80.724 70.655 20.280 30.000 40.046 80.000 10.606 80.559 60.159 20.102 10.445 20.655 20.000 10.310 80.117 20.000 40.000 10.581 80.026 10.000 10.265 80.483 70.084 80.097 80.044 60.865 80.142 80.588 40.351 60.272 20.596 80.000 10.003 40.622 70.720 40.096 80.000 10.771 70.016 70.772 60.000 10.302 60.194 40.214 60.621 70.197 8
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CeCo0.340 10.551 30.247 40.181 10.475 40.057 80.142 70.000 10.000 10.000 10.387 30.463 30.499 40.924 10.774 30.213 20.257 40.000 30.546 80.100 50.006 30.615 10.177 80.534 20.246 30.000 40.400 20.000 10.338 10.006 70.484 20.609 10.000 10.083 40.000 20.873 30.089 40.661 50.000 30.048 80.560 10.408 30.892 30.000 10.000 10.586 10.616 30.000 70.692 40.900 10.721 30.162 10.228 10.860 30.000 10.000 40.575 10.083 20.550 10.347 10.624 40.410 40.360 20.740 10.109 50.321 60.660 20.000 20.121 20.939 40.143 30.000 10.400 10.003 50.190 30.564 10.652 40.615 40.421 10.304 60.579 10.547 10.000 20.000 10.296 50.000 50.030 40.096 10.000 30.916 10.037 40.551 40.171 30.376 20.865 40.286 10.000 10.633 10.102 70.027 40.011 30.000 10.000 30.474 50.742 10.133 30.311 40.824 30.242 40.503 50.068 40.828 10.000 30.429 20.000 10.063 10.000 20.781 10.000 10.000 40.000 10.665 10.633 20.450 10.818 10.000 30.000 10.429 20.532 30.226 40.825 30.510 60.377 20.709 10.079 60.000 10.753 10.683 10.102 70.063 20.401 70.620 60.000 10.619 20.000 80.000 40.000 10.595 60.000 20.000 10.345 50.564 20.411 10.603 10.384 20.945 20.266 40.643 10.367 50.304 10.663 40.000 10.010 20.726 60.767 30.898 30.000 10.784 40.435 10.861 40.000 10.447 30.000 70.257 30.656 40.377 4
: Understanding Imbalanced Semantic Segmentation Through Neural Collapse.
LGroundpermissive0.272 60.485 60.184 60.106 60.476 30.077 50.218 40.000 10.000 10.000 10.547 10.295 60.540 10.746 50.745 60.058 70.112 70.005 10.658 50.077 80.000 40.322 60.178 70.512 50.190 50.199 10.277 60.000 10.000 30.173 20.399 50.000 30.000 10.039 70.000 20.858 60.085 50.676 30.002 10.103 20.498 30.323 50.703 60.000 10.000 10.296 60.549 40.216 10.702 30.768 60.718 50.028 40.092 70.786 70.000 10.000 40.453 70.022 30.251 80.252 40.572 60.348 60.321 40.514 20.063 60.279 70.552 60.000 20.019 70.932 60.132 70.000 10.000 40.000 70.156 80.457 60.623 50.518 50.265 70.358 40.381 60.395 60.000 20.000 10.127 80.012 30.051 10.000 30.000 30.886 70.014 50.437 80.179 20.244 60.826 60.000 30.000 10.599 40.136 10.085 20.000 40.000 10.000 30.565 40.612 50.143 20.207 60.566 60.232 60.446 60.127 20.708 60.000 30.384 40.000 10.000 20.000 20.402 50.000 10.059 20.000 10.525 80.566 50.229 60.659 60.000 30.000 10.265 60.446 50.147 70.720 80.597 40.066 60.000 40.187 20.000 10.726 40.467 80.134 50.000 60.413 60.629 50.000 10.363 70.055 50.022 20.000 10.626 50.000 20.000 10.323 60.479 80.154 70.117 60.028 70.901 60.243 60.415 80.295 80.143 50.610 70.000 10.000 60.777 50.397 80.324 70.000 10.778 60.179 50.702 70.000 10.274 80.404 10.233 40.622 60.398 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrainpermissive0.249 80.455 80.171 70.079 80.418 70.059 70.186 60.000 10.000 10.000 10.335 70.250 70.316 70.766 40.697 80.142 50.170 50.003 20.553 70.112 40.097 10.201 80.186 50.476 80.081 70.000 40.216 80.000 10.000 30.001 80.314 80.000 30.000 10.055 60.000 20.832 80.094 20.659 60.002 10.076 40.310 80.293 80.664 80.000 10.000 10.175 80.634 20.130 20.552 80.686 80.700 80.076 30.110 60.770 80.000 10.000 40.430 80.000 50.319 60.166 70.542 80.327 70.205 70.332 70.052 70.375 40.444 80.000 20.012 80.930 80.203 10.000 10.000 40.046 40.175 50.413 70.592 60.471 70.299 60.152 80.340 70.247 80.000 20.000 10.225 60.058 20.037 20.000 30.207 10.862 80.014 50.548 50.033 70.233 70.816 70.000 30.000 10.542 70.123 20.121 10.019 20.000 10.000 30.463 70.454 80.045 80.128 80.557 70.235 50.441 70.063 50.484 80.000 30.308 80.000 10.000 20.000 20.318 80.000 10.000 40.000 10.545 70.543 60.164 80.734 40.000 30.000 10.215 80.371 70.198 50.743 50.205 70.062 70.000 40.079 60.000 10.683 70.547 70.142 40.000 60.441 30.579 80.000 10.464 60.098 40.041 10.000 10.590 70.000 20.000 10.373 40.494 50.174 60.105 70.001 80.895 70.222 70.537 50.307 70.180 40.625 50.000 10.000 60.591 80.609 70.398 60.000 10.766 80.014 80.638 80.000 10.377 50.004 60.206 70.609 80.465 2
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
OctFormer ScanNet200permissive0.326 40.539 40.265 30.131 30.499 20.110 10.522 10.000 10.000 10.000 10.318 80.427 40.455 60.743 60.765 40.175 30.842 10.000 30.828 10.204 10.033 20.429 40.335 10.601 10.312 20.000 40.357 40.000 10.000 30.047 50.423 40.000 30.000 10.105 30.000 20.873 30.079 60.670 40.000 30.117 10.471 50.432 20.829 50.000 10.000 10.584 20.417 80.089 30.684 50.837 40.705 70.021 60.178 30.892 10.000 10.028 20.505 50.000 50.457 40.200 60.662 10.412 30.244 60.496 30.000 80.451 20.626 30.000 20.102 40.943 30.138 50.000 10.000 40.149 20.291 20.534 30.722 20.632 30.331 40.253 70.453 30.487 40.000 20.000 10.479 20.000 50.022 60.000 30.000 30.900 40.128 20.684 10.164 40.413 10.854 50.000 30.000 10.512 80.074 80.003 60.000 40.000 10.000 30.469 60.613 40.132 40.529 30.871 10.227 70.582 20.026 80.787 30.000 30.339 60.000 10.000 20.000 20.626 30.000 10.029 30.000 10.587 40.612 30.411 20.724 50.000 30.000 10.407 30.552 10.513 10.849 20.655 20.408 10.000 40.296 10.000 10.686 60.645 50.145 30.022 40.414 50.633 40.000 10.637 10.224 10.000 40.000 10.650 30.000 20.000 10.622 20.535 40.343 30.483 20.230 40.943 30.289 30.618 20.596 10.140 60.679 20.000 10.022 10.783 40.620 60.906 10.000 10.806 30.137 60.865 20.000 10.378 40.000 70.168 80.680 30.227 7
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023


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




Method Infoavg ap 25%head ap 25%common ap 25%tail ap 25%alarm 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 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 by
Mask3D Scannet2000.445 10.653 10.392 10.254 10.648 10.097 10.125 50.000 10.000 10.000 10.657 10.971 10.451 21.000 11.000 10.640 10.500 10.045 11.000 10.241 20.409 10.363 10.440 10.686 30.300 10.000 10.201 10.000 10.009 10.290 10.556 11.000 10.000 10.063 30.000 10.830 10.573 10.844 20.333 10.204 10.058 50.158 50.552 20.056 10.000 11.000 10.725 40.750 10.927 11.000 10.888 40.042 30.120 20.615 40.226 10.250 10.890 10.792 10.677 20.510 20.818 10.699 10.512 20.167 50.125 10.315 20.943 10.309 10.017 30.200 30.000 10.188 10.000 10.183 30.815 11.000 10.827 10.741 10.442 30.414 40.600 10.000 10.000 10.458 10.049 30.321 10.381 10.000 10.908 20.400 10.841 10.260 10.710 10.966 10.265 10.000 10.924 10.152 10.025 20.500 10.027 10.028 11.000 10.556 50.016 10.080 50.500 10.694 30.608 10.084 10.604 30.194 10.538 30.000 10.500 10.000 20.354 40.000 11.000 10.000 10.761 20.930 10.053 40.890 31.000 10.008 20.262 10.358 21.000 11.000 10.792 40.966 11.000 10.765 20.004 20.930 10.780 20.330 20.027 20.625 10.974 40.050 10.412 50.021 20.000 30.000 20.778 10.000 10.000 10.493 20.746 20.454 10.335 20.396 10.930 50.551 21.000 10.552 10.606 10.853 10.000 10.004 10.806 11.000 10.727 20.000 10.042 30.745 20.000 10.399 40.391 10.630 10.721 10.619 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TD3D Scannet2000.379 20.603 20.306 20.190 20.635 20.073 20.500 10.000 10.000 10.000 10.495 30.735 20.275 51.000 10.979 20.590 20.000 40.021 20.000 30.146 30.000 20.356 20.173 50.795 10.226 20.000 10.173 20.000 10.000 20.226 20.390 20.000 20.000 10.250 10.000 10.706 20.061 30.885 10.093 20.186 20.259 40.200 10.667 10.000 20.000 10.667 20.825 10.250 40.834 41.000 10.958 10.553 10.111 30.748 10.220 20.051 20.866 20.792 10.390 50.045 50.800 20.302 50.517 10.533 30.113 20.427 10.843 20.000 20.458 10.600 10.000 10.101 20.000 10.259 10.717 20.500 20.615 20.520 20.526 20.457 10.270 40.000 10.000 10.400 20.088 20.294 20.181 20.000 11.000 10.400 10.710 50.103 30.477 50.905 20.061 20.000 10.906 20.102 20.232 10.125 20.000 20.003 20.792 31.000 10.000 20.102 30.125 40.559 50.523 30.075 20.715 10.000 20.424 50.000 10.396 20.250 10.638 10.000 10.000 20.000 10.622 50.833 20.221 10.970 10.250 20.038 10.260 20.415 10.125 21.000 11.000 10.857 20.000 20.908 10.012 10.869 30.836 10.635 10.111 10.625 11.000 10.020 20.510 10.003 30.009 21.000 10.778 10.000 10.000 10.370 30.755 10.288 20.333 30.274 21.000 10.557 10.731 20.456 20.433 30.769 50.000 10.000 20.621 41.000 10.458 40.000 10.196 20.817 10.000 10.472 10.222 30.205 50.689 20.274 3
LGround Inst.permissive0.314 30.529 30.225 30.155 30.578 50.010 30.500 10.000 10.000 10.000 10.515 20.556 30.696 11.000 10.927 30.400 30.083 30.000 31.000 10.252 10.000 20.167 30.350 20.731 20.067 30.000 10.123 40.000 10.000 20.036 30.372 30.000 20.000 10.250 10.000 10.569 40.031 50.810 30.000 30.000 40.630 10.183 20.278 30.000 20.000 10.582 40.589 50.500 20.863 31.000 10.940 20.000 40.144 10.716 30.000 30.000 30.484 30.000 30.500 30.400 30.798 30.500 20.278 40.750 10.093 30.166 40.783 30.000 20.200 20.400 20.000 10.000 30.000 10.219 20.539 30.500 20.578 30.413 30.181 50.457 20.375 20.000 10.000 10.050 50.000 40.077 40.000 30.000 10.500 50.000 50.743 30.250 20.488 40.846 30.000 30.000 10.800 30.069 30.000 30.000 30.000 20.000 31.000 10.607 40.000 20.200 10.500 10.694 20.528 20.063 30.659 20.000 20.594 20.000 10.000 30.000 20.571 20.000 10.000 20.000 10.716 40.647 50.221 20.857 40.000 30.000 30.217 30.346 30.071 50.530 51.000 10.429 30.000 20.286 30.000 30.826 50.706 30.208 40.000 30.250 40.744 50.000 30.500 20.042 10.000 30.000 20.746 30.000 10.000 10.517 10.625 30.085 50.333 30.000 41.000 10.378 40.533 50.376 40.042 50.814 30.000 10.000 20.765 31.000 10.600 30.000 10.000 40.667 30.000 10.472 10.333 20.337 30.605 30.305 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.permissive0.280 40.488 40.192 50.124 40.593 40.010 40.500 10.000 10.000 10.000 10.447 40.535 40.445 31.000 10.861 40.400 30.225 20.000 30.000 30.142 40.000 20.074 40.342 30.467 50.067 30.000 10.119 50.000 10.000 20.000 40.337 50.000 20.000 10.000 40.000 10.506 50.070 20.804 40.000 30.000 40.333 30.172 30.150 50.000 20.000 10.479 50.745 30.000 50.830 51.000 10.904 30.167 20.090 40.732 20.000 30.000 30.443 40.000 30.500 30.542 10.772 50.396 40.077 50.385 40.044 40.118 50.777 40.000 20.000 40.200 30.000 10.000 30.000 10.148 40.502 40.500 20.419 40.159 50.281 40.404 50.317 30.000 10.000 10.200 30.000 40.077 30.000 30.000 10.750 30.200 30.715 40.021 40.551 20.828 50.000 30.000 10.743 40.059 50.000 30.000 30.000 20.000 30.125 50.648 30.000 20.191 20.500 10.669 40.502 40.000 50.568 40.000 20.516 40.000 10.000 30.000 20.305 50.000 10.000 20.000 10.825 10.833 20.021 50.918 20.000 30.000 30.191 40.346 40.100 40.981 31.000 10.286 40.000 20.000 50.000 30.868 40.648 50.292 30.000 30.375 31.000 10.000 30.500 20.000 40.333 10.000 20.538 50.000 10.000 10.213 50.518 40.098 40.528 10.250 30.997 30.284 50.677 30.398 30.167 40.790 40.000 10.000 20.618 50.903 50.200 50.000 10.333 10.333 40.000 10.442 30.083 40.213 40.587 40.131 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.275 50.466 50.218 40.110 50.625 30.007 50.500 10.000 10.000 10.000 10.000 50.222 50.377 41.000 10.661 50.400 30.000 40.000 30.000 30.119 50.000 20.000 50.277 40.685 40.067 30.000 10.132 30.000 10.000 20.000 40.367 40.000 20.000 10.000 40.000 10.591 30.055 40.783 50.000 30.014 30.500 20.161 40.278 30.000 20.000 10.667 20.768 20.500 20.866 21.000 10.829 50.000 40.019 50.555 50.000 30.000 30.305 50.000 30.750 10.200 40.783 40.429 30.395 30.677 20.020 50.286 30.584 50.000 20.000 40.115 50.000 10.000 30.000 10.145 50.423 50.500 20.364 50.369 40.571 10.448 30.206 50.000 10.000 10.200 30.106 10.065 50.000 30.000 10.750 30.200 30.774 20.000 50.501 30.841 40.000 30.000 10.692 50.063 40.000 30.000 30.000 20.000 30.500 40.649 20.000 20.084 40.125 40.719 10.413 50.004 40.450 50.000 20.638 10.000 10.000 30.000 20.505 30.000 10.000 20.000 10.727 30.833 20.221 20.779 50.000 30.000 30.168 50.311 50.125 20.571 40.500 50.143 50.000 20.250 40.000 30.869 20.667 40.162 50.000 30.250 41.000 10.000 30.500 20.000 40.000 30.000 20.689 40.000 10.000 10.312 40.383 50.114 30.333 30.000 40.997 30.420 30.613 40.212 50.500 20.819 20.000 10.000 20.768 21.000 10.918 10.000 10.000 40.278 50.000 10.333 50.000 50.353 20.546 50.258 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021


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
Mix3Dpermissive0.781 10.964 10.855 10.843 130.781 40.858 90.575 40.831 260.685 90.714 20.979 10.594 40.310 210.801 10.892 120.841 20.819 30.723 30.940 90.887 30.725 18
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 20.861 170.818 120.836 160.790 20.875 20.576 30.905 30.704 30.739 10.969 70.611 10.349 70.756 160.958 10.702 370.805 120.708 60.916 250.898 10.801 1
PPT-SpUNet-Joint0.766 30.932 20.794 270.829 200.751 170.854 110.540 150.903 40.630 280.672 100.963 100.565 170.357 50.788 20.900 80.737 200.802 130.685 120.950 30.887 30.780 2
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 30.925 40.808 180.849 70.786 30.846 210.566 70.876 100.690 70.674 90.960 120.576 130.226 590.753 180.904 60.777 80.815 50.722 40.923 210.877 90.776 4
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net0.764 50.924 50.819 100.840 140.757 120.853 130.580 10.848 190.709 20.643 180.958 150.587 80.295 270.753 180.884 160.758 140.815 50.725 20.927 190.867 160.743 10
OccuSeg+Semantic0.764 50.758 530.796 250.839 150.746 190.907 10.562 80.850 180.680 110.672 100.978 20.610 20.335 120.777 50.819 390.847 10.830 10.691 100.972 10.885 50.727 16
O-CNNpermissive0.762 70.924 50.823 60.844 120.770 60.852 140.577 20.847 210.711 10.640 220.958 150.592 50.217 650.762 120.888 130.758 140.813 80.726 10.932 170.868 150.744 9
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 80.783 390.826 50.858 40.776 50.837 270.548 120.896 70.649 200.675 80.962 110.586 90.335 120.771 80.802 430.770 100.787 280.691 100.936 120.880 80.761 6
PNE0.755 90.786 370.835 40.834 180.758 100.849 170.570 60.836 250.648 210.668 120.978 20.581 120.367 30.683 280.856 250.804 30.801 170.678 140.961 20.889 20.716 23
ConDaFormer0.755 90.927 30.822 70.836 160.801 10.849 170.516 250.864 150.651 190.680 70.958 150.584 110.282 340.759 140.855 270.728 220.802 130.678 140.880 520.873 140.756 7
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
PointTransformerV20.752 110.742 600.809 170.872 10.758 100.860 80.552 100.891 80.610 350.687 30.960 120.559 200.304 240.766 100.926 30.767 110.797 200.644 270.942 70.876 120.722 20
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net0.752 110.906 90.793 290.802 350.689 330.825 380.556 90.867 120.681 100.602 370.960 120.555 220.365 40.779 40.859 220.747 170.795 240.717 50.917 240.856 240.764 5
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
PointConvFormer0.749 130.793 350.790 300.807 310.750 180.856 100.524 210.881 90.588 470.642 210.977 50.591 60.274 390.781 30.929 20.804 30.796 210.642 280.947 50.885 50.715 24
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 130.909 70.818 120.811 280.752 150.839 260.485 400.842 220.673 120.644 170.957 190.528 310.305 230.773 70.859 220.788 50.818 40.693 90.916 250.856 240.723 19
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 150.623 860.804 200.859 30.745 200.824 400.501 300.912 20.690 70.685 50.956 200.567 160.320 180.768 90.918 40.720 270.802 130.676 170.921 220.881 70.779 3
StratifiedFormerpermissive0.747 160.901 100.803 210.845 110.757 120.846 210.512 260.825 290.696 60.645 160.956 200.576 130.262 500.744 230.861 210.742 180.770 370.705 70.899 380.860 210.734 11
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
VMNetpermissive0.746 170.870 150.838 20.858 40.729 250.850 160.501 300.874 110.587 480.658 140.956 200.564 180.299 250.765 110.900 80.716 300.812 90.631 330.939 100.858 220.709 25
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)
Virtual MVFusion0.746 170.771 470.819 100.848 90.702 310.865 70.397 770.899 50.699 40.664 130.948 480.588 70.330 140.746 220.851 310.764 120.796 210.704 80.935 130.866 170.728 14
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
Retro-FPN0.744 190.842 230.800 220.767 480.740 210.836 290.541 140.914 10.672 130.626 260.958 150.552 230.272 410.777 50.886 150.696 380.801 170.674 190.941 80.858 220.717 21
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-Net0.743 200.620 870.799 240.849 70.730 240.822 420.493 370.897 60.664 140.681 60.955 230.562 190.378 10.760 130.903 70.738 190.801 170.673 200.907 300.877 90.745 8
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet0.742 210.816 300.806 190.807 310.752 150.828 360.575 40.839 240.699 40.637 230.954 290.520 330.320 180.755 170.834 350.760 130.772 340.676 170.915 270.862 190.717 21
SAT0.742 210.860 180.765 420.819 230.769 70.848 190.533 170.829 270.663 150.631 250.955 230.586 90.274 390.753 180.896 100.729 210.760 440.666 220.921 220.855 260.733 12
LargeKernel3D0.739 230.909 70.820 90.806 330.740 210.852 140.545 130.826 280.594 460.643 180.955 230.541 250.263 490.723 260.858 240.775 90.767 380.678 140.933 150.848 310.694 30
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN0.736 240.776 430.790 300.851 60.754 140.854 110.491 390.866 130.596 450.686 40.955 230.536 260.342 90.624 430.869 180.787 60.802 130.628 340.927 190.875 130.704 27
MinkowskiNetpermissive0.736 240.859 190.818 120.832 190.709 290.840 250.521 230.853 170.660 170.643 180.951 380.544 240.286 320.731 240.893 110.675 460.772 340.683 130.874 580.852 290.727 16
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 260.890 110.837 30.864 20.726 260.873 30.530 200.824 300.489 790.647 150.978 20.609 30.336 110.624 430.733 520.758 140.776 320.570 580.949 40.877 90.728 14
PointTransformer++0.725 270.727 680.811 160.819 230.765 80.841 240.502 290.814 350.621 310.623 280.955 230.556 210.284 330.620 450.866 190.781 70.757 470.648 250.932 170.862 190.709 25
SparseConvNet0.725 270.647 830.821 80.846 100.721 270.869 40.533 170.754 500.603 410.614 300.955 230.572 150.325 160.710 270.870 170.724 250.823 20.628 340.934 140.865 180.683 33
MatchingNet0.724 290.812 320.812 150.810 290.735 230.834 310.495 360.860 160.572 540.602 370.954 290.512 350.280 360.757 150.845 330.725 240.780 300.606 440.937 110.851 300.700 29
INS-Conv-semantic0.717 300.751 560.759 450.812 270.704 300.868 50.537 160.842 220.609 370.608 330.953 320.534 280.293 280.616 460.864 200.719 290.793 250.640 290.933 150.845 350.663 38
PointMetaBase0.714 310.835 240.785 320.821 210.684 350.846 210.531 190.865 140.614 320.596 410.953 320.500 380.246 550.674 290.888 130.692 390.764 400.624 360.849 730.844 360.675 35
contrastBoundarypermissive0.705 320.769 500.775 370.809 300.687 340.820 450.439 650.812 360.661 160.591 430.945 560.515 340.171 830.633 400.856 250.720 270.796 210.668 210.889 450.847 320.689 31
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 330.774 450.800 220.793 390.760 90.847 200.471 430.802 390.463 860.634 240.968 90.491 410.271 430.726 250.910 50.706 340.815 50.551 690.878 530.833 370.570 69
RFCR0.702 340.889 120.745 540.813 260.672 380.818 490.493 370.815 340.623 290.610 310.947 500.470 490.249 540.594 490.848 320.705 350.779 310.646 260.892 430.823 430.611 52
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 Click0.701 350.825 280.796 250.723 550.716 280.832 320.433 670.816 320.634 260.609 320.969 70.418 740.344 80.559 610.833 360.715 310.808 110.560 630.902 350.847 320.680 34
JSENetpermissive0.699 360.881 140.762 430.821 210.667 390.800 620.522 220.792 420.613 330.607 340.935 760.492 400.205 700.576 540.853 290.691 400.758 460.652 240.872 610.828 400.649 42
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-Click0.693 370.743 590.794 270.655 790.684 350.822 420.497 350.719 600.622 300.617 290.977 50.447 610.339 100.750 210.664 680.703 360.790 270.596 480.946 60.855 260.647 43
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 380.732 640.772 380.786 400.677 370.866 60.517 240.848 190.509 710.626 260.952 360.536 260.225 610.545 670.704 590.689 430.810 100.564 620.903 340.854 280.729 13
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 390.884 130.754 490.795 380.647 450.818 490.422 690.802 390.612 340.604 350.945 560.462 520.189 780.563 600.853 290.726 230.765 390.632 320.904 320.821 460.606 56
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 400.704 730.741 580.754 520.656 410.829 340.501 300.741 550.609 370.548 500.950 420.522 320.371 20.633 400.756 470.715 310.771 360.623 370.861 690.814 480.658 39
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 410.866 160.748 510.819 230.645 470.794 650.450 540.802 390.587 480.604 350.945 560.464 510.201 730.554 630.840 340.723 260.732 560.602 460.907 300.822 450.603 59
KP-FCNN0.684 420.847 220.758 470.784 420.647 450.814 520.473 420.772 450.605 390.594 420.935 760.450 590.181 810.587 500.805 420.690 410.785 290.614 400.882 490.819 470.632 48
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DGNet0.684 420.712 720.784 330.782 440.658 400.835 300.499 340.823 310.641 230.597 400.950 420.487 420.281 350.575 550.619 710.647 590.764 400.620 390.871 640.846 340.688 32
VACNN++0.684 420.728 670.757 480.776 450.690 320.804 590.464 480.816 320.577 530.587 440.945 560.508 370.276 380.671 300.710 570.663 510.750 500.589 530.881 500.832 390.653 41
Superpoint Network0.683 450.851 210.728 620.800 370.653 430.806 570.468 450.804 370.572 540.602 370.946 530.453 580.239 580.519 720.822 370.689 430.762 430.595 500.895 410.827 410.630 49
PointContrast_LA_SEM0.683 450.757 540.784 330.786 400.639 490.824 400.408 720.775 440.604 400.541 520.934 800.532 290.269 450.552 640.777 450.645 620.793 250.640 290.913 280.824 420.671 36
VI-PointConv0.676 470.770 490.754 490.783 430.621 530.814 520.552 100.758 480.571 560.557 480.954 290.529 300.268 470.530 700.682 630.675 460.719 590.603 450.888 460.833 370.665 37
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 480.789 360.748 510.763 500.635 510.814 520.407 740.747 520.581 520.573 450.950 420.484 430.271 430.607 470.754 480.649 560.774 330.596 480.883 480.823 430.606 56
SALANet0.670 490.816 300.770 400.768 470.652 440.807 560.451 510.747 520.659 180.545 510.924 860.473 480.149 930.571 570.811 410.635 650.746 510.623 370.892 430.794 600.570 69
PointConvpermissive0.666 500.781 400.759 450.699 640.644 480.822 420.475 410.779 430.564 590.504 680.953 320.428 680.203 720.586 520.754 480.661 520.753 480.588 540.902 350.813 500.642 44
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 500.703 740.781 350.751 540.655 420.830 330.471 430.769 460.474 820.537 540.951 380.475 470.279 370.635 380.698 620.675 460.751 490.553 680.816 800.806 520.703 28
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++permissive0.663 520.746 570.708 660.722 560.638 500.820 450.451 510.566 870.599 430.541 520.950 420.510 360.313 200.648 350.819 390.616 700.682 750.590 520.869 650.810 510.656 40
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 530.778 410.702 690.806 330.619 540.813 550.468 450.693 680.494 740.524 600.941 670.449 600.298 260.510 740.821 380.675 460.727 580.568 600.826 780.803 540.637 46
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 540.698 750.743 560.650 800.564 710.820 450.505 280.758 480.631 270.479 730.945 560.480 450.226 590.572 560.774 460.690 410.735 540.614 400.853 720.776 750.597 62
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 550.752 550.734 600.664 770.583 660.815 510.399 760.754 500.639 240.535 560.942 650.470 490.309 220.665 310.539 770.650 550.708 640.635 310.857 710.793 620.642 44
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 560.778 410.731 610.699 640.577 670.829 340.446 560.736 560.477 810.523 620.945 560.454 560.269 450.484 810.749 510.618 680.738 520.599 470.827 770.792 650.621 51
MVPNetpermissive0.641 570.831 250.715 640.671 740.590 620.781 710.394 780.679 700.642 220.553 490.937 730.462 520.256 510.649 340.406 900.626 660.691 720.666 220.877 540.792 650.608 55
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN0.641 570.776 430.703 680.721 570.557 740.826 370.451 510.672 720.563 600.483 720.943 640.425 710.162 880.644 360.726 530.659 530.709 630.572 570.875 560.786 700.559 75
PointMRNet0.640 590.717 710.701 700.692 670.576 680.801 610.467 470.716 610.563 600.459 780.953 320.429 670.169 850.581 530.854 280.605 710.710 610.550 700.894 420.793 620.575 67
FPConvpermissive0.639 600.785 380.760 440.713 620.603 570.798 630.392 790.534 920.603 410.524 600.948 480.457 540.250 530.538 680.723 550.598 750.696 700.614 400.872 610.799 550.567 72
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 610.797 340.769 410.641 850.590 620.820 450.461 490.537 910.637 250.536 550.947 500.388 820.206 690.656 320.668 660.647 590.732 560.585 550.868 660.793 620.473 94
PointSPNet0.637 620.734 630.692 770.714 610.576 680.797 640.446 560.743 540.598 440.437 830.942 650.403 780.150 920.626 420.800 440.649 560.697 690.557 660.846 740.777 740.563 73
SConv0.636 630.830 260.697 730.752 530.572 700.780 730.445 580.716 610.529 650.530 570.951 380.446 620.170 840.507 760.666 670.636 640.682 750.541 750.886 470.799 550.594 63
Supervoxel-CNN0.635 640.656 810.711 650.719 580.613 550.757 820.444 610.765 470.534 640.566 460.928 840.478 460.272 410.636 370.531 790.664 500.645 850.508 830.864 680.792 650.611 52
joint point-basedpermissive0.634 650.614 880.778 360.667 760.633 520.825 380.420 700.804 370.467 840.561 470.951 380.494 390.291 290.566 580.458 850.579 820.764 400.559 650.838 750.814 480.598 61
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 660.731 650.688 800.675 710.591 610.784 700.444 610.565 880.610 350.492 700.949 460.456 550.254 520.587 500.706 580.599 740.665 810.612 430.868 660.791 690.579 66
3DSM_DMMF0.631 670.626 850.745 540.801 360.607 560.751 830.506 270.729 590.565 580.491 710.866 1000.434 630.197 760.595 480.630 700.709 330.705 660.560 630.875 560.740 850.491 89
APCF-Net0.631 670.742 600.687 820.672 720.557 740.792 680.408 720.665 730.545 620.508 650.952 360.428 680.186 790.634 390.702 600.620 670.706 650.555 670.873 590.798 570.581 65
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN0.631 670.771 470.692 770.672 720.524 790.837 270.440 640.706 660.538 630.446 800.944 620.421 730.219 640.552 640.751 500.591 780.737 530.543 740.901 370.768 770.557 76
FusionAwareConv0.630 700.604 900.741 580.766 490.590 620.747 840.501 300.734 570.503 730.527 580.919 900.454 560.323 170.550 660.420 890.678 450.688 730.544 720.896 400.795 590.627 50
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 710.800 330.625 920.719 580.545 770.806 570.445 580.597 820.448 890.519 630.938 720.481 440.328 150.489 800.499 840.657 540.759 450.592 510.881 500.797 580.634 47
SegGroup_sempermissive0.627 720.818 290.747 530.701 630.602 580.764 790.385 830.629 790.490 770.508 650.931 830.409 760.201 730.564 590.725 540.618 680.692 710.539 760.873 590.794 600.548 79
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 730.830 260.694 750.757 510.563 720.772 770.448 550.647 760.520 670.509 640.949 460.431 660.191 770.496 780.614 720.647 590.672 790.535 780.876 550.783 710.571 68
HPEIN0.618 740.729 660.668 830.647 820.597 600.766 780.414 710.680 690.520 670.525 590.946 530.432 640.215 660.493 790.599 730.638 630.617 900.570 580.897 390.806 520.605 58
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-GCNpermissive0.610 750.858 200.772 380.489 970.532 780.792 680.404 750.643 780.570 570.507 670.935 760.414 750.046 1020.510 740.702 600.602 730.705 660.549 710.859 700.773 760.534 82
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 760.760 520.667 840.649 810.521 800.793 660.457 500.648 750.528 660.434 850.947 500.401 790.153 910.454 830.721 560.648 580.717 600.536 770.904 320.765 780.485 90
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 770.634 840.743 560.697 660.601 590.781 710.437 660.585 850.493 750.446 800.933 810.394 800.011 1040.654 330.661 690.603 720.733 550.526 790.832 760.761 800.480 91
dtc_net0.596 780.683 760.725 630.715 600.549 760.803 600.444 610.647 760.493 750.495 690.941 670.409 760.000 1060.424 880.544 760.598 750.703 680.522 800.912 290.792 650.520 85
LAP-D0.594 790.720 690.692 770.637 860.456 890.773 760.391 810.730 580.587 480.445 820.940 700.381 830.288 300.434 860.453 870.591 780.649 830.581 560.777 840.749 840.610 54
DPC0.592 800.720 690.700 710.602 900.480 850.762 810.380 840.713 640.585 510.437 830.940 700.369 850.288 300.434 860.509 830.590 800.639 880.567 610.772 850.755 820.592 64
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 810.766 510.659 870.683 690.470 880.740 860.387 820.620 810.490 770.476 740.922 880.355 880.245 560.511 730.511 820.571 830.643 860.493 870.872 610.762 790.600 60
ROSMRF0.580 820.772 460.707 670.681 700.563 720.764 790.362 860.515 930.465 850.465 770.936 750.427 700.207 680.438 840.577 740.536 860.675 780.486 880.723 910.779 720.524 84
SD-DETR0.576 830.746 570.609 960.445 1010.517 810.643 970.366 850.714 630.456 870.468 760.870 990.432 640.264 480.558 620.674 640.586 810.688 730.482 890.739 890.733 870.537 81
SQN_0.1%0.569 840.676 780.696 740.657 780.497 820.779 740.424 680.548 890.515 690.376 900.902 970.422 720.357 50.379 910.456 860.596 770.659 820.544 720.685 940.665 980.556 77
TextureNetpermissive0.566 850.672 800.664 850.671 740.494 830.719 870.445 580.678 710.411 950.396 880.935 760.356 870.225 610.412 890.535 780.565 840.636 890.464 910.794 830.680 950.568 71
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
DVVNet0.562 860.648 820.700 710.770 460.586 650.687 910.333 900.650 740.514 700.475 750.906 940.359 860.223 630.340 930.442 880.422 970.668 800.501 840.708 920.779 720.534 82
Pointnet++ & Featurepermissive0.557 870.735 620.661 860.686 680.491 840.744 850.392 790.539 900.451 880.375 910.946 530.376 840.205 700.403 900.356 930.553 850.643 860.497 850.824 790.756 810.515 86
GMLPs0.538 880.495 980.693 760.647 820.471 870.793 660.300 930.477 940.505 720.358 920.903 960.327 910.081 990.472 820.529 800.448 950.710 610.509 810.746 870.737 860.554 78
PanopticFusion-label0.529 890.491 990.688 800.604 890.386 940.632 980.225 1030.705 670.434 920.293 980.815 1010.348 890.241 570.499 770.669 650.507 880.649 830.442 970.796 820.602 1010.561 74
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_weak0.516 900.676 780.591 990.609 870.442 900.774 750.335 890.597 820.422 940.357 930.932 820.341 900.094 980.298 950.528 810.473 930.676 770.495 860.602 1000.721 900.349 101
Online SegFusion0.515 910.607 890.644 900.579 920.434 910.630 990.353 870.628 800.440 900.410 860.762 1040.307 930.167 860.520 710.403 910.516 870.565 930.447 950.678 950.701 920.514 87
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, FTSDF0.501 920.558 940.608 970.424 1030.478 860.690 900.246 990.586 840.468 830.450 790.911 920.394 800.160 890.438 840.212 1000.432 960.541 980.475 900.742 880.727 880.477 92
PCNN0.498 930.559 930.644 900.560 940.420 930.711 890.229 1010.414 950.436 910.352 940.941 670.324 920.155 900.238 1000.387 920.493 890.529 990.509 810.813 810.751 830.504 88
3DMV0.484 940.484 1000.538 1010.643 840.424 920.606 1020.310 910.574 860.433 930.378 890.796 1020.301 940.214 670.537 690.208 1010.472 940.507 1020.413 1000.693 930.602 1010.539 80
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 950.577 920.611 950.356 1050.321 1020.715 880.299 950.376 990.328 1020.319 960.944 620.285 960.164 870.216 1030.229 980.484 910.545 970.456 930.755 860.709 910.475 93
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 960.679 770.604 980.578 930.380 950.682 920.291 960.106 1050.483 800.258 1030.920 890.258 1000.025 1030.231 1020.325 940.480 920.560 950.463 920.725 900.666 970.231 105
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 970.474 1010.623 930.463 990.366 970.651 950.310 910.389 980.349 1000.330 950.937 730.271 980.126 950.285 960.224 990.350 1020.577 920.445 960.625 980.723 890.394 97
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
PNET20.442 980.548 950.548 1000.597 910.363 980.628 1000.300 930.292 1000.374 970.307 970.881 980.268 990.186 790.238 1000.204 1020.407 980.506 1030.449 940.667 960.620 1000.462 95
SurfaceConvPF0.442 980.505 970.622 940.380 1040.342 1000.654 940.227 1020.397 970.367 980.276 1000.924 860.240 1010.198 750.359 920.262 960.366 990.581 910.435 980.640 970.668 960.398 96
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 1000.437 1030.646 890.474 980.369 960.645 960.353 870.258 1020.282 1040.279 990.918 910.298 950.147 940.283 970.294 950.487 900.562 940.427 990.619 990.633 990.352 100
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1010.525 960.647 880.522 950.324 1010.488 1050.077 1060.712 650.353 990.401 870.636 1060.281 970.176 820.340 930.565 750.175 1060.551 960.398 1010.370 1060.602 1010.361 99
SPLAT Netcopyleft0.393 1020.472 1020.511 1020.606 880.311 1030.656 930.245 1000.405 960.328 1020.197 1040.927 850.227 1030.000 1060.001 1070.249 970.271 1050.510 1000.383 1030.593 1010.699 930.267 103
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 1030.297 1050.491 1030.432 1020.358 990.612 1010.274 970.116 1040.411 950.265 1010.904 950.229 1020.079 1000.250 980.185 1030.320 1030.510 1000.385 1020.548 1020.597 1040.394 97
PointNet++permissive0.339 1040.584 910.478 1040.458 1000.256 1050.360 1060.250 980.247 1030.278 1050.261 1020.677 1050.183 1040.117 960.212 1040.145 1050.364 1000.346 1060.232 1060.548 1020.523 1050.252 104
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 1050.353 1040.290 1060.278 1060.166 1060.553 1030.169 1050.286 1010.147 1060.148 1060.908 930.182 1050.064 1010.023 1060.018 1070.354 1010.363 1040.345 1040.546 1040.685 940.278 102
ScanNetpermissive0.306 1060.203 1060.366 1050.501 960.311 1030.524 1040.211 1040.002 1070.342 1010.189 1050.786 1030.145 1060.102 970.245 990.152 1040.318 1040.348 1050.300 1050.460 1050.437 1060.182 106
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 1070.000 1070.041 1070.172 1070.030 1070.062 1070.001 1070.035 1060.004 1070.051 1070.143 1070.019 1070.003 1050.041 1050.050 1060.003 1070.054 1070.018 1070.005 1070.264 1070.082 107


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




Method Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
TD3D0.875 11.000 10.976 120.877 90.783 150.970 10.889 10.828 120.945 30.803 70.713 100.720 110.709 81.000 10.936 70.934 30.873 71.000 10.791 6
Queryformer0.874 21.000 10.978 110.809 250.876 10.936 60.702 90.716 270.920 50.875 40.766 40.772 30.818 31.000 10.995 10.916 40.892 11.000 10.767 9
SoftGroup++0.874 21.000 10.972 130.947 10.839 50.898 130.556 250.913 20.881 100.756 90.828 20.748 60.821 11.000 10.937 60.937 10.887 21.000 10.821 3
Mask3D0.870 41.000 10.985 70.782 320.818 100.938 50.760 60.749 230.923 40.877 30.760 50.785 20.820 21.000 10.912 100.864 230.878 50.983 400.825 2
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SoftGrouppermissive0.865 51.000 10.969 140.860 120.860 20.913 90.558 220.899 30.911 60.760 80.828 10.736 80.802 50.981 300.919 90.875 140.877 61.000 10.820 4
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
MAFT0.860 61.000 10.990 60.810 240.829 60.949 30.809 40.688 330.836 160.904 10.751 70.796 10.741 61.000 10.864 240.848 300.837 121.000 10.828 1
IPCA-Inst0.851 71.000 10.968 150.884 80.842 40.862 250.693 110.812 170.888 90.677 210.783 30.698 120.807 41.000 10.911 140.865 220.865 91.000 10.757 12
SPFormerpermissive0.851 71.000 10.994 20.806 260.774 170.942 40.637 140.849 100.859 130.889 20.720 90.730 90.665 131.000 10.911 140.868 210.873 81.000 10.796 5
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SphereSeg0.835 91.000 10.963 180.891 60.794 120.954 20.822 30.710 280.961 20.721 130.693 160.530 320.653 151.000 10.867 230.857 260.859 100.991 370.771 8
ISBNetpermissive0.835 91.000 10.950 200.731 400.819 80.918 70.790 50.740 240.851 150.831 50.661 180.742 70.650 161.000 10.937 50.814 420.836 131.000 10.765 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
TopoSeg0.832 111.000 10.981 90.933 20.819 90.826 330.524 310.841 110.811 200.681 200.759 60.687 130.727 70.981 300.911 140.883 100.853 111.000 10.756 13
GraphCut0.832 111.000 10.922 330.724 420.798 110.902 120.701 100.856 80.859 120.715 140.706 110.748 50.640 271.000 10.934 80.862 240.880 31.000 10.729 15
PBNetpermissive0.825 131.000 10.963 170.837 160.843 30.865 200.822 20.647 360.878 110.733 110.639 250.683 140.650 161.000 10.853 250.870 180.820 141.000 10.744 14
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
SSEC0.820 141.000 10.983 80.924 30.826 70.817 360.415 400.899 40.793 240.673 220.731 80.636 190.653 141.000 10.939 40.804 440.878 41.000 10.780 7
DKNet0.815 151.000 10.930 250.844 140.765 210.915 80.534 290.805 190.805 220.807 60.654 190.763 40.650 161.000 10.794 370.881 110.766 181.000 10.758 11
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN0.806 161.000 10.992 40.789 280.723 330.891 140.650 130.810 180.832 170.665 240.699 140.658 150.700 91.000 10.881 180.832 340.774 160.997 300.613 35
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAISpermissive0.803 171.000 10.994 20.820 200.759 220.855 260.554 260.882 50.827 190.615 300.676 170.638 180.646 251.000 10.912 100.797 470.767 170.994 350.726 16
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask0.803 171.000 10.962 190.874 100.707 370.887 170.686 120.598 400.961 10.715 150.694 150.469 370.700 91.000 10.912 100.902 50.753 230.997 300.637 29
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group0.792 191.000 10.968 160.812 210.766 200.864 210.460 340.815 160.888 80.598 340.651 220.639 170.600 320.918 350.941 20.896 60.721 301.000 10.723 17
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained0.791 201.000 10.996 10.829 190.767 190.889 160.600 170.819 150.770 290.594 350.620 280.541 290.700 91.000 10.941 20.889 80.763 191.000 10.526 44
SSTNetpermissive0.789 211.000 10.840 470.888 70.717 340.835 290.717 80.684 340.627 430.724 120.652 210.727 100.600 321.000 10.912 100.822 370.757 221.000 10.691 23
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN0.788 221.000 10.978 100.867 110.781 160.833 300.527 300.824 130.806 210.549 430.596 310.551 250.700 91.000 10.853 250.935 20.733 271.000 10.651 26
DENet0.786 231.000 10.929 260.736 390.750 280.720 490.755 70.934 10.794 230.590 360.561 370.537 300.650 161.000 10.882 170.804 450.789 151.000 10.719 18
DualGroup0.782 241.000 10.927 270.811 220.772 180.853 270.631 160.805 190.773 260.613 310.611 290.610 210.650 160.835 460.881 180.879 130.750 251.000 10.675 24
PointGroup0.778 251.000 10.900 370.798 270.715 350.863 220.493 320.706 290.895 70.569 410.701 120.576 230.639 281.000 10.880 200.851 280.719 310.997 300.709 20
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]
PE0.776 261.000 10.900 380.860 120.728 320.869 180.400 410.857 70.774 250.568 420.701 130.602 220.646 250.933 340.843 280.890 70.691 380.997 300.709 19
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA0.767 271.000 10.937 220.810 230.740 300.906 100.550 270.800 210.706 350.577 400.624 270.544 280.596 370.857 380.879 220.880 120.750 240.992 360.658 25
DD-UNet+Group0.764 281.000 10.897 400.837 150.753 250.830 320.459 360.824 130.699 370.629 280.653 200.438 400.650 161.000 10.880 200.858 250.690 391.000 10.650 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-instance0.762 291.000 10.923 300.765 350.785 140.905 110.600 170.655 350.646 420.683 190.647 230.530 310.650 161.000 10.824 300.830 350.693 370.944 440.644 28
Dyco3Dcopyleft0.761 301.000 10.935 230.893 50.752 270.863 230.600 170.588 410.742 320.641 260.633 260.546 270.550 390.857 380.789 390.853 270.762 200.987 380.699 21
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance0.742 311.000 10.923 300.785 290.745 290.867 190.557 230.578 440.729 330.670 230.644 240.488 350.577 381.000 10.794 370.830 350.620 471.000 10.550 40
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg0.739 321.000 10.899 390.759 370.753 260.823 340.282 450.691 320.658 400.582 390.594 320.547 260.628 301.000 10.795 360.868 200.728 291.000 10.692 22
3D-MPA0.737 331.000 10.933 240.785 290.794 130.831 310.279 470.588 410.695 380.616 290.559 380.556 240.650 161.000 10.809 340.875 150.696 351.000 10.608 37
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML0.731 341.000 10.992 40.779 340.609 460.746 440.308 440.867 60.601 460.607 320.539 410.519 330.550 391.000 10.824 300.869 190.729 281.000 10.616 33
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS0.725 351.000 10.885 430.653 480.657 430.801 370.576 210.695 310.828 180.698 170.534 420.457 390.500 460.857 380.831 290.841 320.627 451.000 10.619 32
SSEN0.724 361.000 10.926 280.781 330.661 410.845 280.596 200.529 470.764 310.653 250.489 480.461 380.500 460.859 370.765 400.872 170.761 211.000 10.577 38
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF0.718 371.000 10.945 210.901 40.754 240.817 350.460 340.700 300.772 270.688 180.568 360.000 580.500 460.981 300.606 490.872 160.740 261.000 10.614 34
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
Sparse R-CNN0.714 381.000 10.926 290.694 430.699 390.890 150.636 150.516 480.693 390.743 100.588 330.369 440.601 310.594 510.800 350.886 90.676 400.986 390.546 41
SALoss-ResNet0.695 391.000 10.855 450.579 530.589 480.735 470.484 330.588 410.856 140.634 270.571 350.298 450.500 461.000 10.824 300.818 380.702 340.935 490.545 42
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)
PanopticFusion-inst0.693 401.000 10.852 460.655 470.616 450.788 390.334 430.763 220.771 280.457 530.555 390.652 160.518 430.857 380.765 400.732 530.631 430.944 440.577 39
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Occipital-SCS0.688 411.000 10.913 340.730 410.737 310.743 460.442 370.855 90.655 410.546 440.546 400.263 470.508 450.889 360.568 500.771 500.705 330.889 520.625 31
3D-BoNet0.687 421.000 10.887 420.836 170.587 490.643 560.550 270.620 370.724 340.522 480.501 460.243 480.512 441.000 10.751 420.807 430.661 420.909 510.612 36
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
ClickSeg_Instance0.685 431.000 10.818 490.600 510.715 360.795 380.557 230.533 460.591 480.601 330.519 440.429 420.638 290.938 330.706 440.817 400.624 460.944 440.502 46
PCJC0.684 441.000 10.895 410.757 380.659 420.862 240.189 540.739 250.606 450.712 160.581 340.515 340.650 160.857 380.357 550.785 480.631 440.889 520.635 30
SPG_WSIS0.678 451.000 10.880 440.836 170.701 380.727 480.273 490.607 390.706 360.541 460.515 450.174 500.600 320.857 380.716 430.846 310.711 321.000 10.506 45
One_Thing_One_Clickpermissive0.675 461.000 10.823 480.782 310.621 440.766 410.211 510.736 260.560 500.586 370.522 430.636 200.453 500.641 500.853 250.850 290.694 360.997 300.411 50
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_inspermissive0.637 471.000 10.923 320.593 520.561 500.746 450.143 560.504 490.766 300.485 510.442 490.372 430.530 420.714 470.815 330.775 490.673 411.000 10.431 49
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASCpermissive0.615 480.711 540.802 500.540 540.757 230.777 400.029 570.577 450.588 490.521 490.600 300.436 410.534 410.697 480.616 480.838 330.526 490.980 410.534 43
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone0.605 491.000 10.909 350.764 360.603 470.704 500.415 390.301 540.548 510.461 520.394 500.267 460.386 520.857 380.649 470.817 390.504 500.959 420.356 53
3D-SISpermissive0.558 501.000 10.773 510.614 500.503 520.691 520.200 520.412 500.498 540.546 450.311 550.103 540.600 320.857 380.382 520.799 460.445 560.938 480.371 51
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.544 510.500 570.655 570.661 460.663 400.765 420.432 380.214 560.612 440.584 380.499 470.204 490.286 560.429 540.655 460.650 580.539 480.950 430.499 47
Hier3Dcopyleft0.540 521.000 10.727 520.626 490.467 550.693 510.200 520.412 500.480 550.528 470.318 540.077 570.600 320.688 490.382 520.768 510.472 520.941 470.350 54
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class0.497 530.250 590.902 360.689 440.540 510.747 430.276 480.610 380.268 580.489 500.348 510.000 580.243 580.220 570.663 450.814 410.459 540.928 500.496 48
tmp0.474 541.000 10.727 520.433 570.481 540.673 540.022 590.380 520.517 530.436 550.338 530.128 520.343 540.429 540.291 570.728 540.473 510.833 550.300 56
SemRegionNet-20cls0.470 551.000 10.727 520.447 560.481 530.678 530.024 580.380 520.518 520.440 540.339 520.128 520.350 530.429 540.212 580.711 550.465 530.833 550.290 57
ASIS0.422 560.333 580.707 550.676 450.401 560.650 550.350 420.177 570.594 470.376 560.202 560.077 560.404 510.571 520.197 590.674 570.447 550.500 580.260 58
3D-BEVIS0.401 570.667 550.687 560.419 580.137 590.587 570.188 550.235 550.359 570.211 580.093 590.080 550.311 550.571 520.382 520.754 520.300 580.874 540.357 52
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.390 580.556 560.636 580.493 550.353 570.539 580.271 500.160 580.450 560.359 570.178 570.146 510.250 570.143 580.347 560.698 560.436 570.667 570.331 55
MaskRCNN 2d->3d Proj0.261 590.903 530.081 590.008 590.233 580.175 590.280 460.106 590.150 590.203 590.175 580.480 360.218 590.143 580.542 510.404 590.153 590.393 590.049 59


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 70.518 150.298 140.366 210.633 180.510 150.446 170.864 160.296 170.267 170.542 160.346 180.704 70.575 160.431 160.853 100.766 140.630 7
UDSSEG_RVC0.545 150.610 110.661 190.588 80.556 120.268 180.482 80.642 170.572 90.475 140.836 200.312 150.367 60.630 70.189 200.639 170.495 200.452 130.826 140.756 170.541 14
segfomer with 6d0.542 160.594 120.687 140.146 210.579 100.308 130.515 50.703 100.472 180.498 110.868 150.369 70.282 150.589 120.390 140.701 80.556 170.416 180.860 90.759 150.539 16
FuseNetpermissive0.535 170.570 150.681 170.182 190.512 160.290 170.431 140.659 140.504 160.495 120.903 100.308 160.428 30.523 180.365 160.676 110.621 110.470 110.762 190.779 100.541 14
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 180.613 100.722 110.418 160.358 230.337 60.370 200.479 210.443 190.368 210.907 70.207 200.213 220.464 210.525 50.618 190.657 60.450 140.788 170.721 200.408 22
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 190.481 210.612 200.579 90.456 190.343 50.384 180.623 190.525 140.381 200.845 190.254 190.264 190.557 150.182 210.581 210.598 130.429 170.760 200.661 220.446 21
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 200.505 190.709 130.092 220.427 200.241 190.411 170.654 160.385 230.457 160.861 170.053 230.279 160.503 190.481 70.645 160.626 100.365 210.748 210.725 190.529 17
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 210.490 200.581 210.289 170.507 180.067 230.379 190.610 200.417 210.435 180.822 220.278 180.267 170.503 190.228 190.616 200.533 190.375 200.820 150.729 180.560 13
Enet (reimpl)0.376 220.264 230.452 230.452 130.365 210.181 210.143 230.456 220.409 220.346 220.769 230.164 210.218 210.359 220.123 230.403 230.381 230.313 230.571 220.685 210.472 20
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
ScanNet (2d proj)permissive0.330 230.293 220.521 220.657 60.361 220.161 220.250 220.004 230.440 200.183 230.836 200.125 220.060 230.319 230.132 220.417 220.412 220.344 220.541 230.427 230.109 23
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
DMMF0.003 240.000 240.005 240.000 240.000 240.037 240.001 240.000 240.001 240.005 240.003 240.000 240.000 240.000 240.000 240.000 240.002 240.001 240.000 240.006 240.000 24


This table lists the benchmark results for the 2D 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
UniDet_RVC0.205 10.381 10.323 10.037 10.226 10.177 10.063 10.277 10.120 10.067 10.131 10.074 20.317 10.080 10.235 10.289 10.141 10.678 10.080 1
MaskRCNN_ScanNetpermissive0.119 20.129 20.212 20.002 20.112 20.148 20.014 20.205 20.044 20.066 20.078 20.095 10.142 20.030 20.128 20.139 20.080 20.459 20.057 2
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17


This table lists the benchmark results for the scene type classification scenario.




Method Infoavg recallapartmentbathroombedroom / hotelbookstore / libraryconference roomcopy/mail roomhallwaykitchenlaundry roomliving room / loungemiscofficestorage / basement / garage
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
multi-taskpermissive0.700 10.500 11.000 10.882 20.500 21.000 11.000 10.500 21.000 11.000 10.778 10.000 20.938 10.000 2
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
3DASPP-SCE0.691 20.500 10.938 20.824 31.000 11.000 10.500 21.000 10.857 20.500 20.556 30.000 20.812 20.500 1
SE-ResNeXt-SSMA0.498 30.000 40.812 30.941 10.500 20.500 30.500 20.500 20.429 40.500 20.667 20.500 10.625 30.000 2
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
resnet50_scannet0.353 40.250 30.812 30.529 40.500 20.500 30.000 40.500 20.571 30.000 40.556 30.000 20.375 40.000 2