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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
CeCo0.340 10.551 10.247 10.181 10.475 20.057 40.142 30.000 10.000 10.000 10.387 20.463 10.499 20.924 10.774 10.213 10.257 10.000 30.546 40.100 20.006 20.615 10.177 40.534 10.246 10.000 20.400 10.000 10.338 10.006 30.484 10.609 10.000 10.083 10.000 20.873 10.089 20.661 20.000 30.048 40.560 10.408 10.892 10.000 10.000 10.586 10.616 20.000 40.692 20.900 10.721 10.162 10.228 10.860 10.000 10.000 20.575 10.083 20.550 10.347 10.624 10.410 10.360 10.740 10.109 20.321 20.660 10.000 20.121 20.939 10.143 20.000 10.400 10.003 20.190 10.564 10.652 10.615 10.421 10.304 30.579 10.547 10.000 10.000 10.296 10.000 40.030 40.096 10.000 20.916 10.037 10.551 10.171 20.376 10.865 10.286 10.000 10.633 10.102 40.027 40.011 20.000 10.000 10.474 20.742 10.133 20.311 10.824 10.242 10.503 10.068 30.828 10.000 20.429 10.000 10.063 10.000 10.781 10.000 10.000 20.000 10.665 10.633 10.450 10.818 10.000 10.000 10.429 10.532 10.226 10.825 10.510 30.377 10.709 10.079 20.000 10.753 10.683 10.102 40.063 20.401 40.620 30.000 10.619 10.000 40.000 30.000 10.595 20.000 20.000 10.345 20.564 10.411 10.603 10.384 10.945 10.266 10.643 10.367 10.304 10.663 10.000 10.010 10.726 20.767 10.898 10.000 10.784 10.435 10.861 10.000 10.447 10.000 40.257 10.656 10.377 3
: Understanding Imbalanced Semantic Segmentation Through Neural Collapse.
LGroundpermissive0.272 20.485 20.184 20.106 20.476 10.077 20.218 10.000 10.000 10.000 10.547 10.295 20.540 10.746 30.745 20.058 30.112 40.005 10.658 20.077 40.000 30.322 20.178 30.512 30.190 20.199 10.277 20.000 10.000 20.173 10.399 20.000 20.000 10.039 30.000 20.858 20.085 30.676 10.002 10.103 10.498 20.323 20.703 20.000 10.000 10.296 20.549 30.216 10.702 10.768 20.718 20.028 30.092 30.786 30.000 10.000 20.453 30.022 30.251 40.252 20.572 20.348 20.321 20.514 20.063 30.279 30.552 20.000 20.019 30.932 20.132 30.000 10.000 20.000 40.156 40.457 20.623 20.518 20.265 30.358 20.381 20.395 20.000 10.000 10.127 40.012 30.051 10.000 20.000 20.886 30.014 20.437 40.179 10.244 20.826 20.000 20.000 10.599 20.136 10.085 20.000 30.000 10.000 10.565 10.612 20.143 10.207 20.566 20.232 30.446 20.127 10.708 30.000 20.384 20.000 10.000 20.000 10.402 20.000 10.059 10.000 10.525 40.566 20.229 30.659 30.000 10.000 10.265 20.446 20.147 30.720 40.597 20.066 30.000 20.187 10.000 10.726 20.467 40.134 30.000 30.413 30.629 20.000 10.363 30.055 30.022 20.000 10.626 10.000 20.000 10.323 30.479 40.154 30.117 20.028 30.901 20.243 20.415 40.295 40.143 40.610 30.000 10.000 30.777 10.397 40.324 30.000 10.778 20.179 20.702 30.000 10.274 40.404 10.233 20.622 20.398 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrainpermissive0.249 40.455 40.171 30.079 40.418 30.059 30.186 20.000 10.000 10.000 10.335 40.250 30.316 30.766 20.697 40.142 20.170 20.003 20.553 30.112 10.097 10.201 40.186 20.476 40.081 30.000 20.216 40.000 10.000 20.001 40.314 40.000 20.000 10.055 20.000 20.832 40.094 10.659 30.002 10.076 20.310 40.293 40.664 40.000 10.000 10.175 40.634 10.130 20.552 40.686 40.700 40.076 20.110 20.770 40.000 10.000 20.430 40.000 40.319 20.166 30.542 40.327 30.205 40.332 30.052 40.375 10.444 40.000 20.012 40.930 40.203 10.000 10.000 20.046 10.175 20.413 30.592 30.471 30.299 20.152 40.340 30.247 40.000 10.000 10.225 20.058 20.037 20.000 20.207 10.862 40.014 20.548 20.033 30.233 30.816 30.000 20.000 10.542 40.123 20.121 10.019 10.000 10.000 10.463 30.454 40.045 40.128 40.557 30.235 20.441 30.063 40.484 40.000 20.308 40.000 10.000 20.000 10.318 40.000 10.000 20.000 10.545 30.543 30.164 40.734 20.000 10.000 10.215 40.371 30.198 20.743 20.205 40.062 40.000 20.079 20.000 10.683 30.547 30.142 20.000 30.441 20.579 40.000 10.464 20.098 20.041 10.000 10.590 30.000 20.000 10.373 10.494 20.174 20.105 30.001 40.895 30.222 30.537 30.307 30.180 30.625 20.000 10.000 30.591 40.609 30.398 20.000 10.766 40.014 40.638 40.000 10.377 20.004 30.206 40.609 40.465 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 30.463 30.154 40.102 30.381 40.084 10.134 40.000 10.000 10.000 10.386 30.141 40.279 40.737 40.703 30.014 40.164 30.000 30.663 10.092 30.000 30.224 30.291 10.531 20.056 40.000 20.242 30.000 10.000 20.013 20.331 30.000 20.000 10.035 40.001 10.858 20.059 40.650 40.000 30.056 30.353 30.299 30.670 30.000 10.000 10.284 30.484 40.071 30.594 30.720 30.710 30.027 40.068 40.813 20.000 10.005 10.492 20.164 10.274 30.111 40.571 30.307 40.293 30.307 40.150 10.163 40.531 30.002 10.545 10.932 20.093 40.000 10.000 20.002 30.159 30.368 40.581 40.440 40.228 40.406 10.282 40.294 30.000 10.000 10.189 30.060 10.036 30.000 20.000 20.897 20.000 40.525 30.025 40.205 40.771 40.000 20.000 10.593 30.108 30.044 30.000 30.000 10.000 10.282 40.589 30.094 30.169 30.466 40.227 40.419 40.125 20.757 20.002 10.334 30.000 10.000 20.000 10.357 30.000 10.000 20.000 10.582 20.513 40.337 20.612 40.000 10.000 10.250 30.352 40.136 40.724 30.655 10.280 20.000 20.046 40.000 10.606 40.559 20.159 10.102 10.445 10.655 10.000 10.310 40.117 10.000 30.000 10.581 40.026 10.000 10.265 40.483 30.084 40.097 40.044 20.865 40.142 40.588 20.351 20.272 20.596 40.000 10.003 20.622 30.720 20.096 40.000 10.771 30.016 30.772 20.000 10.302 30.194 20.214 30.621 30.197 4
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 ap 50%head ap 50%common ap 50%tail ap 50%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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mask3D Scannet2000.388 10.542 10.357 10.237 10.610 10.091 10.125 40.000 10.000 10.000 10.065 20.668 10.451 11.000 10.955 10.640 10.500 10.039 10.125 20.063 10.409 10.311 10.291 10.609 20.266 10.000 10.163 10.000 10.008 10.044 10.496 11.000 10.000 10.018 10.000 10.756 10.573 10.808 10.000 10.010 10.042 20.130 20.552 10.042 10.000 11.000 10.725 30.750 10.883 11.000 10.832 30.024 10.107 10.614 20.226 10.250 10.628 10.792 10.677 20.400 10.741 10.278 10.511 10.077 40.111 10.313 10.715 10.302 10.017 20.200 10.000 10.188 10.000 10.178 10.736 11.000 10.615 10.514 10.409 10.380 40.600 10.000 10.000 10.400 10.013 10.254 10.381 10.000 10.123 30.400 10.839 10.258 10.463 10.926 10.265 10.000 10.857 10.099 10.021 10.500 10.027 10.028 11.000 10.502 40.016 10.076 30.500 10.612 10.578 10.005 10.597 10.194 10.497 10.000 10.500 10.000 10.323 30.000 11.000 10.000 10.748 10.708 20.050 30.890 11.000 10.008 10.151 20.301 11.000 11.000 10.792 20.945 11.000 10.511 10.004 10.753 10.776 10.287 10.020 10.003 30.974 20.033 10.412 40.000 10.000 10.000 10.667 10.000 10.000 10.491 10.676 10.352 10.335 10.060 10.822 40.527 11.000 10.517 10.606 10.853 10.000 10.004 10.806 11.000 10.727 10.000 10.042 10.739 10.000 10.399 20.391 10.504 10.591 10.571 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
Minkowski 34D Inst.permissive0.203 40.369 30.134 40.078 40.479 30.003 30.500 10.000 10.000 10.000 10.100 10.371 20.300 20.667 30.746 20.400 20.000 20.000 20.000 30.031 20.000 20.074 30.165 30.413 40.000 30.000 10.070 30.000 10.000 20.000 20.221 40.000 20.000 10.000 20.000 10.372 40.070 20.706 30.000 10.000 20.000 40.123 30.033 40.000 20.000 10.422 40.732 20.000 30.778 41.000 10.845 20.000 20.090 30.636 10.000 20.000 20.158 30.000 20.250 40.050 40.693 20.123 30.051 40.385 30.009 30.118 40.406 40.000 20.000 30.200 10.000 10.000 20.000 10.133 30.307 40.500 20.251 30.000 30.281 20.402 30.317 20.000 10.000 10.000 20.000 20.060 30.000 20.000 10.396 10.200 20.669 20.021 30.218 40.720 40.000 20.000 10.696 20.025 30.000 20.000 20.000 20.000 20.125 40.596 10.000 20.191 10.500 10.595 20.369 30.000 20.500 30.000 20.143 40.000 10.000 20.000 10.226 40.000 10.000 20.000 10.701 20.511 30.000 40.851 30.000 20.000 20.150 30.052 40.100 30.981 20.500 30.286 20.000 20.000 40.000 20.545 30.522 40.250 20.000 20.000 40.522 40.000 20.500 10.000 10.000 10.000 10.282 40.000 10.000 10.178 40.382 30.018 40.056 30.000 20.997 20.107 40.677 20.313 30.000 30.726 40.000 10.000 20.583 40.903 30.200 40.000 10.000 20.333 30.000 10.442 10.083 30.109 40.387 30.000 4
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.209 30.361 40.157 30.085 30.506 20.007 20.500 10.000 10.000 10.000 10.000 40.093 40.221 30.667 30.524 40.400 20.000 20.000 20.000 30.004 30.000 20.000 40.109 40.589 30.000 30.000 10.059 40.000 10.000 20.000 20.322 20.000 20.000 10.000 20.000 10.405 20.055 30.700 40.000 10.000 20.028 30.091 40.083 20.000 20.000 10.667 20.768 10.000 30.807 31.000 10.776 40.000 20.000 40.340 40.000 20.000 20.103 40.000 20.750 10.200 30.634 40.053 40.246 20.677 20.006 40.198 20.432 30.000 20.000 30.050 30.000 10.000 20.000 10.111 40.356 30.500 20.188 40.000 30.220 30.448 10.050 40.000 10.000 10.000 20.000 20.032 40.000 20.000 10.396 10.000 30.573 40.000 40.228 30.747 30.000 20.000 10.573 40.021 40.000 20.000 20.000 20.000 20.500 30.573 20.000 20.000 40.125 40.592 30.364 40.000 20.450 40.000 20.364 20.000 10.000 20.000 10.340 20.000 10.000 20.000 10.610 30.833 10.221 10.702 40.000 20.000 20.135 40.094 30.125 20.571 30.500 30.143 40.000 20.125 20.000 20.618 20.667 30.115 40.000 20.125 11.000 10.000 20.500 10.000 10.000 10.000 10.502 30.000 10.000 10.312 30.248 40.050 30.000 40.000 20.997 20.420 20.500 40.149 40.451 20.748 20.000 10.000 20.636 30.667 40.600 20.000 10.000 20.278 40.000 10.333 30.000 40.294 20.381 40.110 2
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.246 20.413 20.170 20.130 20.455 40.003 40.500 10.000 10.000 10.000 10.017 30.333 30.111 41.000 10.681 30.400 20.000 20.000 21.000 10.003 40.000 20.167 20.190 20.637 10.067 20.000 10.081 20.000 10.000 20.000 20.264 30.000 20.000 10.000 20.000 10.387 30.031 40.754 20.000 10.000 20.151 10.135 10.056 30.000 20.000 10.582 30.589 40.500 20.815 21.000 10.903 10.000 20.097 20.588 30.000 20.000 20.234 20.000 20.500 30.400 10.682 30.156 20.159 30.750 10.046 20.125 30.660 20.000 20.200 10.000 40.000 10.000 20.000 10.164 20.402 20.500 20.373 20.025 20.143 40.426 20.317 20.000 10.000 10.000 20.000 20.063 20.000 20.000 10.000 40.000 30.575 30.250 20.241 20.772 20.000 20.000 10.653 30.034 20.000 20.000 20.000 20.000 21.000 10.561 30.000 20.100 20.500 10.541 40.452 20.000 20.581 20.000 20.364 20.000 10.000 20.000 10.571 10.000 10.000 20.000 10.568 40.511 30.167 20.857 20.000 20.000 20.164 10.112 20.000 40.530 41.000 10.286 20.000 20.125 20.000 20.464 40.706 20.208 30.000 20.125 10.744 30.000 20.500 10.000 10.000 10.000 10.511 20.000 10.000 10.344 20.541 20.068 20.333 20.000 21.000 10.196 30.533 30.318 20.000 30.748 30.000 10.000 20.690 21.000 10.400 30.000 10.000 20.667 20.000 10.333 30.333 20.270 30.399 20.083 3
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.


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 10.843 100.781 10.858 70.575 30.831 170.685 60.714 10.979 10.594 30.310 150.801 10.892 80.841 20.819 30.723 30.940 70.887 10.725 12
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
CU-Hybrid Net0.764 20.924 20.819 60.840 110.757 60.853 90.580 10.848 130.709 20.643 110.958 90.587 70.295 210.753 130.884 120.758 80.815 50.725 20.927 150.867 90.743 5
OccuSeg+Semantic0.764 20.758 430.796 170.839 120.746 100.907 10.562 40.850 120.680 80.672 50.978 20.610 10.335 80.777 40.819 300.847 10.830 10.691 80.972 10.885 20.727 10
O-CNNpermissive0.762 40.924 20.823 40.844 90.770 20.852 100.577 20.847 140.711 10.640 140.958 90.592 40.217 550.762 100.888 90.758 80.813 60.726 10.932 130.868 80.744 4
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
DMF-Net0.752 50.906 50.793 200.802 260.689 250.825 280.556 50.867 80.681 70.602 270.960 70.555 160.365 30.779 30.859 170.747 110.795 170.717 40.917 180.856 160.764 2
PointTransformerV20.752 50.742 500.809 120.872 10.758 50.860 60.552 60.891 50.610 270.687 20.960 70.559 140.304 180.766 80.926 20.767 60.797 130.644 190.942 50.876 70.722 14
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer0.749 70.793 290.790 210.807 240.750 90.856 80.524 140.881 60.588 370.642 130.977 40.591 50.274 310.781 20.929 10.804 30.796 140.642 200.947 30.885 20.715 16
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 70.909 40.818 80.811 210.752 80.839 170.485 290.842 150.673 90.644 100.957 120.528 230.305 170.773 60.859 170.788 40.818 40.693 70.916 190.856 160.723 13
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 90.623 740.804 130.859 30.745 110.824 300.501 210.912 20.690 50.685 30.956 130.567 110.320 130.768 70.918 30.720 190.802 90.676 100.921 160.881 40.779 1
StratifiedFormerpermissive0.747 100.901 60.803 140.845 80.757 60.846 130.512 170.825 190.696 40.645 90.956 130.576 90.262 410.744 170.861 160.742 120.770 290.705 50.899 290.860 130.734 6
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 MVFusion0.746 110.771 370.819 60.848 60.702 230.865 50.397 660.899 30.699 30.664 60.948 370.588 60.330 90.746 160.851 230.764 70.796 140.704 60.935 100.866 100.728 8
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNetpermissive0.746 110.870 110.838 20.858 40.729 150.850 110.501 210.874 70.587 380.658 70.956 130.564 120.299 190.765 90.900 50.716 220.812 70.631 250.939 80.858 140.709 17
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-FPN0.744 130.842 180.800 150.767 380.740 120.836 210.541 80.914 10.672 100.626 160.958 90.552 170.272 330.777 40.886 110.696 290.801 100.674 110.941 60.858 140.717 15
EQ-Net0.743 140.620 750.799 160.849 50.730 140.822 320.493 270.897 40.664 110.681 40.955 170.562 130.378 10.760 110.903 40.738 130.801 100.673 120.907 220.877 50.745 3
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT0.742 150.860 130.765 320.819 160.769 30.848 120.533 100.829 180.663 120.631 150.955 170.586 80.274 310.753 130.896 60.729 140.760 340.666 140.921 160.855 180.733 7
MinkowskiNetpermissive0.736 160.859 140.818 80.832 130.709 200.840 160.521 160.853 110.660 140.643 110.951 280.544 180.286 260.731 180.893 70.675 360.772 270.683 90.874 470.852 200.727 10
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 170.890 70.837 30.864 20.726 160.873 20.530 130.824 200.489 680.647 80.978 20.609 20.336 70.624 340.733 430.758 80.776 250.570 500.949 20.877 50.728 8
SparseConvNet0.725 180.647 710.821 50.846 70.721 180.869 30.533 100.754 390.603 330.614 200.955 170.572 100.325 110.710 190.870 130.724 170.823 20.628 260.934 110.865 110.683 23
PointTransformer++0.725 180.727 570.811 110.819 160.765 40.841 150.502 200.814 250.621 230.623 170.955 170.556 150.284 270.620 350.866 140.781 50.757 370.648 170.932 130.862 120.709 17
MatchingNet0.724 200.812 260.812 100.810 220.735 130.834 220.495 260.860 100.572 440.602 270.954 210.512 260.280 280.757 120.845 250.725 160.780 230.606 360.937 90.851 210.700 20
INS-Conv-semantic0.717 210.751 460.759 350.812 200.704 220.868 40.537 90.842 150.609 290.608 230.953 230.534 190.293 220.616 360.864 150.719 210.793 180.640 210.933 120.845 250.663 28
PointMetaBase0.714 220.835 190.785 230.821 140.684 270.846 130.531 120.865 90.614 240.596 300.953 230.500 290.246 470.674 200.888 90.692 300.764 310.624 270.849 610.844 260.675 25
contrastBoundarypermissive0.705 230.769 400.775 280.809 230.687 260.820 350.439 530.812 260.661 130.591 330.945 460.515 250.171 730.633 310.856 190.720 190.796 140.668 130.889 360.847 230.689 22
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RFCR0.702 240.889 80.745 440.813 190.672 290.818 390.493 270.815 230.623 210.610 210.947 390.470 380.249 460.594 390.848 240.705 260.779 240.646 180.892 340.823 330.611 43
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 Click0.701 250.825 230.796 170.723 450.716 190.832 230.433 550.816 210.634 190.609 220.969 60.418 630.344 50.559 500.833 270.715 230.808 80.560 540.902 260.847 230.680 24
JSENetpermissive0.699 260.881 100.762 330.821 140.667 300.800 510.522 150.792 310.613 250.607 240.935 650.492 310.205 600.576 440.853 210.691 310.758 360.652 160.872 500.828 300.649 32
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
PicassoNet-IIpermissive0.696 270.704 610.790 210.787 300.709 200.837 190.459 380.815 230.543 530.615 190.956 130.529 210.250 440.551 550.790 350.703 270.799 120.619 310.908 210.848 220.700 20
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One-Thing-One-Click0.693 280.743 490.794 190.655 680.684 270.822 320.497 250.719 490.622 220.617 180.977 40.447 500.339 60.750 150.664 580.703 270.790 200.596 400.946 40.855 180.647 33
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Feature_GeometricNetpermissive0.690 290.884 90.754 390.795 290.647 350.818 390.422 570.802 290.612 260.604 250.945 460.462 410.189 680.563 490.853 210.726 150.765 300.632 240.904 240.821 360.606 47
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 300.704 610.741 480.754 420.656 310.829 250.501 210.741 440.609 290.548 400.950 320.522 240.371 20.633 310.756 380.715 230.771 280.623 280.861 570.814 380.658 29
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 310.866 120.748 410.819 160.645 370.794 540.450 430.802 290.587 380.604 250.945 460.464 400.201 630.554 520.840 260.723 180.732 460.602 380.907 220.822 350.603 50
KP-FCNN0.684 320.847 170.758 370.784 320.647 350.814 420.473 310.772 340.605 310.594 320.935 650.450 480.181 710.587 400.805 330.690 320.785 220.614 320.882 400.819 370.632 38
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 320.728 560.757 380.776 340.690 240.804 490.464 360.816 210.577 430.587 340.945 460.508 280.276 300.671 210.710 480.663 410.750 400.589 450.881 410.832 290.653 31
Superpoint Network0.683 340.851 160.728 520.800 280.653 330.806 470.468 330.804 270.572 440.602 270.946 430.453 470.239 500.519 610.822 280.689 340.762 330.595 420.895 320.827 310.630 39
PointContrast_LA_SEM0.683 340.757 440.784 240.786 310.639 390.824 300.408 600.775 330.604 320.541 420.934 690.532 200.269 370.552 530.777 360.645 510.793 180.640 210.913 200.824 320.671 26
VI-PointConv0.676 360.770 390.754 390.783 330.621 430.814 420.552 60.758 370.571 460.557 380.954 210.529 210.268 390.530 590.682 530.675 360.719 490.603 370.888 370.833 280.665 27
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 370.789 300.748 410.763 400.635 410.814 420.407 620.747 410.581 420.573 350.950 320.484 320.271 350.607 370.754 390.649 460.774 260.596 400.883 390.823 330.606 47
SALANet0.670 380.816 250.770 300.768 370.652 340.807 460.451 400.747 410.659 150.545 410.924 750.473 370.149 830.571 460.811 320.635 540.746 410.623 280.892 340.794 500.570 60
PointConvpermissive0.666 390.781 320.759 350.699 530.644 380.822 320.475 300.779 320.564 490.504 580.953 230.428 570.203 620.586 420.754 390.661 420.753 380.588 460.902 260.813 400.642 34
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 390.703 630.781 260.751 440.655 320.830 240.471 320.769 350.474 710.537 440.951 280.475 360.279 290.635 290.698 520.675 360.751 390.553 590.816 680.806 420.703 19
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++permissive0.663 410.746 470.708 550.722 460.638 400.820 350.451 400.566 750.599 350.541 420.950 320.510 270.313 140.648 260.819 300.616 590.682 640.590 440.869 530.810 410.656 30
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 420.778 330.702 580.806 250.619 440.813 450.468 330.693 570.494 640.524 500.941 570.449 490.298 200.510 630.821 290.675 360.727 480.568 520.826 660.803 440.637 36
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 430.698 640.743 460.650 690.564 610.820 350.505 190.758 370.631 200.479 620.945 460.480 340.226 510.572 450.774 370.690 320.735 440.614 320.853 600.776 640.597 53
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 440.752 450.734 500.664 660.583 560.815 410.399 650.754 390.639 170.535 460.942 550.470 380.309 160.665 220.539 650.650 450.708 540.635 230.857 590.793 520.642 34
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 450.778 330.731 510.699 530.577 570.829 250.446 450.736 450.477 700.523 520.945 460.454 450.269 370.484 700.749 420.618 570.738 420.599 390.827 650.792 550.621 41
PointConv-SFPN0.641 460.776 350.703 570.721 470.557 640.826 270.451 400.672 610.563 500.483 610.943 540.425 600.162 780.644 270.726 440.659 430.709 530.572 490.875 450.786 590.559 65
MVPNetpermissive0.641 460.831 200.715 530.671 630.590 520.781 600.394 670.679 590.642 160.553 390.937 620.462 410.256 420.649 250.406 780.626 550.691 610.666 140.877 430.792 550.608 46
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 480.717 600.701 590.692 560.576 580.801 500.467 350.716 500.563 500.459 670.953 230.429 560.169 750.581 430.854 200.605 600.710 510.550 600.894 330.793 520.575 58
FPConvpermissive0.639 490.785 310.760 340.713 510.603 470.798 520.392 680.534 800.603 330.524 500.948 370.457 430.250 440.538 570.723 460.598 640.696 590.614 320.872 500.799 450.567 62
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 500.797 280.769 310.641 740.590 520.820 350.461 370.537 790.637 180.536 450.947 390.388 700.206 590.656 230.668 560.647 490.732 460.585 470.868 540.793 520.473 83
PointSPNet0.637 510.734 530.692 660.714 500.576 580.797 530.446 450.743 430.598 360.437 720.942 550.403 660.150 820.626 330.800 340.649 460.697 580.557 570.846 620.777 630.563 63
SConv0.636 520.830 210.697 620.752 430.572 600.780 620.445 470.716 500.529 560.530 470.951 280.446 510.170 740.507 650.666 570.636 530.682 640.541 650.886 380.799 450.594 54
Supervoxel-CNN0.635 530.656 690.711 540.719 480.613 450.757 710.444 500.765 360.534 550.566 360.928 730.478 350.272 330.636 280.531 670.664 400.645 740.508 720.864 560.792 550.611 43
joint point-basedpermissive0.634 540.614 760.778 270.667 650.633 420.825 280.420 580.804 270.467 730.561 370.951 280.494 300.291 230.566 470.458 730.579 700.764 310.559 560.838 630.814 380.598 52
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 550.731 540.688 690.675 600.591 510.784 590.444 500.565 760.610 270.492 590.949 350.456 440.254 430.587 400.706 490.599 630.665 700.612 350.868 540.791 580.579 57
3DSM_DMMF0.631 560.626 730.745 440.801 270.607 460.751 720.506 180.729 480.565 480.491 600.866 890.434 520.197 660.595 380.630 600.709 250.705 560.560 540.875 450.740 740.491 78
APCF-Net0.631 560.742 500.687 710.672 610.557 640.792 570.408 600.665 620.545 520.508 550.952 270.428 570.186 690.634 300.702 500.620 560.706 550.555 580.873 480.798 470.581 56
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN0.631 560.771 370.692 660.672 610.524 680.837 190.440 520.706 550.538 540.446 690.944 520.421 620.219 540.552 530.751 410.591 660.737 430.543 640.901 280.768 660.557 66
FusionAwareConv0.630 590.604 780.741 480.766 390.590 520.747 730.501 210.734 460.503 630.527 480.919 790.454 450.323 120.550 560.420 770.678 350.688 620.544 620.896 310.795 490.627 40
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 600.800 270.625 810.719 480.545 660.806 470.445 470.597 700.448 770.519 530.938 610.481 330.328 100.489 690.499 720.657 440.759 350.592 430.881 410.797 480.634 37
SegGroup_sempermissive0.627 610.818 240.747 430.701 520.602 480.764 680.385 720.629 670.490 660.508 550.931 720.409 650.201 630.564 480.725 450.618 570.692 600.539 660.873 480.794 500.548 69
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 620.830 210.694 640.757 410.563 620.772 660.448 440.647 650.520 580.509 540.949 350.431 550.191 670.496 670.614 610.647 490.672 680.535 680.876 440.783 600.571 59
HPEIN0.618 630.729 550.668 720.647 710.597 500.766 670.414 590.680 580.520 580.525 490.946 430.432 530.215 560.493 680.599 620.638 520.617 790.570 500.897 300.806 420.605 49
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-GCNpermissive0.610 640.858 150.772 290.489 860.532 670.792 570.404 640.643 660.570 470.507 570.935 650.414 640.046 920.510 630.702 500.602 620.705 560.549 610.859 580.773 650.534 72
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 650.760 420.667 730.649 700.521 690.793 550.457 390.648 640.528 570.434 740.947 390.401 670.153 810.454 720.721 470.648 480.717 500.536 670.904 240.765 670.485 79
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 660.634 720.743 460.697 550.601 490.781 600.437 540.585 730.493 650.446 690.933 700.394 680.011 940.654 240.661 590.603 610.733 450.526 690.832 640.761 690.480 80
LAP-D0.594 670.720 580.692 660.637 750.456 780.773 650.391 700.730 470.587 380.445 710.940 590.381 710.288 240.434 750.453 750.591 660.649 720.581 480.777 720.749 730.610 45
DPC0.592 680.720 580.700 600.602 790.480 740.762 700.380 730.713 530.585 410.437 720.940 590.369 730.288 240.434 750.509 710.590 680.639 770.567 530.772 730.755 710.592 55
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 690.766 410.659 760.683 580.470 770.740 750.387 710.620 690.490 660.476 630.922 770.355 760.245 480.511 620.511 700.571 710.643 750.493 760.872 500.762 680.600 51
ROSMRF0.580 700.772 360.707 560.681 590.563 620.764 680.362 750.515 810.465 740.465 660.936 640.427 590.207 580.438 730.577 630.536 740.675 670.486 770.723 790.779 610.524 74
SD-DETR0.576 710.746 470.609 850.445 900.517 700.643 860.366 740.714 520.456 750.468 650.870 880.432 530.264 400.558 510.674 540.586 690.688 620.482 780.739 770.733 760.537 71
SQN_0.1%0.569 720.676 660.696 630.657 670.497 710.779 630.424 560.548 770.515 600.376 790.902 860.422 610.357 40.379 790.456 740.596 650.659 710.544 620.685 820.665 870.556 67
TextureNetpermissive0.566 730.672 680.664 740.671 630.494 720.719 760.445 470.678 600.411 830.396 770.935 650.356 750.225 520.412 770.535 660.565 720.636 780.464 800.794 710.680 840.568 61
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
DVVNet0.562 740.648 700.700 600.770 360.586 550.687 800.333 790.650 630.514 610.475 640.906 830.359 740.223 530.340 810.442 760.422 850.668 690.501 730.708 800.779 610.534 72
Pointnet++ & Featurepermissive0.557 750.735 520.661 750.686 570.491 730.744 740.392 680.539 780.451 760.375 800.946 430.376 720.205 600.403 780.356 810.553 730.643 750.497 740.824 670.756 700.515 75
GMLPs0.538 760.495 860.693 650.647 710.471 760.793 550.300 820.477 820.505 620.358 810.903 850.327 790.081 890.472 710.529 680.448 830.710 510.509 700.746 750.737 750.554 68
PanopticFusion-label0.529 770.491 870.688 690.604 780.386 830.632 870.225 920.705 560.434 800.293 870.815 900.348 770.241 490.499 660.669 550.507 760.649 720.442 860.796 700.602 900.561 64
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_weak0.516 780.676 660.591 880.609 760.442 790.774 640.335 780.597 700.422 820.357 820.932 710.341 780.094 880.298 830.528 690.473 810.676 660.495 750.602 880.721 790.349 90
Online SegFusion0.515 790.607 770.644 790.579 810.434 800.630 880.353 760.628 680.440 780.410 750.762 930.307 810.167 760.520 600.403 790.516 750.565 820.447 840.678 830.701 810.514 76
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, FTSDF0.501 800.558 820.608 860.424 920.478 750.690 790.246 880.586 720.468 720.450 680.911 810.394 680.160 790.438 730.212 880.432 840.541 870.475 790.742 760.727 770.477 81
PCNN0.498 810.559 810.644 790.560 830.420 820.711 780.229 900.414 830.436 790.352 830.941 570.324 800.155 800.238 880.387 800.493 770.529 880.509 700.813 690.751 720.504 77
3DMV0.484 820.484 880.538 900.643 730.424 810.606 910.310 800.574 740.433 810.378 780.796 910.301 820.214 570.537 580.208 890.472 820.507 910.413 890.693 810.602 900.539 70
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 830.577 800.611 840.356 940.321 910.715 770.299 840.376 870.328 900.319 850.944 520.285 840.164 770.216 910.229 860.484 790.545 860.456 820.755 740.709 800.475 82
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 840.679 650.604 870.578 820.380 840.682 810.291 850.106 930.483 690.258 920.920 780.258 880.025 930.231 900.325 820.480 800.560 840.463 810.725 780.666 860.231 94
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 850.474 890.623 820.463 880.366 860.651 840.310 800.389 860.349 880.330 840.937 620.271 860.126 850.285 840.224 870.350 900.577 810.445 850.625 860.723 780.394 86
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
PNET20.442 860.548 830.548 890.597 800.363 870.628 890.300 820.292 880.374 850.307 860.881 870.268 870.186 690.238 880.204 900.407 860.506 920.449 830.667 840.620 890.462 84
SurfaceConvPF0.442 860.505 850.622 830.380 930.342 890.654 830.227 910.397 850.367 860.276 890.924 750.240 890.198 650.359 800.262 840.366 870.581 800.435 870.640 850.668 850.398 85
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 880.437 910.646 780.474 870.369 850.645 850.353 760.258 900.282 920.279 880.918 800.298 830.147 840.283 850.294 830.487 780.562 830.427 880.619 870.633 880.352 89
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 890.525 840.647 770.522 840.324 900.488 940.077 950.712 540.353 870.401 760.636 950.281 850.176 720.340 810.565 640.175 940.551 850.398 900.370 940.602 900.361 88
SimConv0.410 900.000 950.782 250.772 350.722 170.838 180.407 620.000 960.000 960.595 310.947 390.000 960.270 360.000 960.000 960.000 960.786 210.621 300.000 960.841 270.621 41
SPLAT Netcopyleft0.393 910.472 900.511 910.606 770.311 920.656 820.245 890.405 840.328 900.197 930.927 740.227 910.000 960.001 950.249 850.271 930.510 890.383 920.593 890.699 820.267 92
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+FTSDF0.383 920.297 930.491 920.432 910.358 880.612 900.274 860.116 920.411 830.265 900.904 840.229 900.079 900.250 860.185 910.320 910.510 890.385 910.548 900.597 930.394 86
PointNet++permissive0.339 930.584 790.478 930.458 890.256 940.360 950.250 870.247 910.278 930.261 910.677 940.183 920.117 860.212 920.145 930.364 880.346 950.232 950.548 900.523 940.252 93
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 940.353 920.290 950.278 950.166 950.553 920.169 940.286 890.147 940.148 950.908 820.182 930.064 910.023 940.018 950.354 890.363 930.345 930.546 920.685 830.278 91
ScanNetpermissive0.306 950.203 940.366 940.501 850.311 920.524 930.211 930.002 950.342 890.189 940.786 920.145 940.102 870.245 870.152 920.318 920.348 940.300 940.460 930.437 950.182 95
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 960.000 950.041 960.172 960.030 960.062 960.001 960.035 940.004 950.051 960.143 960.019 950.003 950.041 930.050 940.003 950.054 960.018 960.005 950.264 960.082 96


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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mask3D0.780 11.000 10.786 240.716 220.696 40.885 30.500 20.714 170.810 10.672 30.715 30.679 60.809 11.000 10.831 10.833 70.787 31.000 10.602 4
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SPFormerpermissive0.770 20.903 340.903 10.806 100.609 120.886 20.568 10.815 60.705 40.711 10.655 40.652 90.685 81.000 10.789 30.809 110.776 41.000 10.583 8
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023
SoftGroup++0.769 31.000 10.803 180.937 10.684 50.865 50.213 170.870 20.664 60.571 70.758 10.702 40.807 21.000 10.653 150.902 10.792 21.000 10.626 1
SoftGrouppermissive0.761 41.000 10.808 150.845 60.716 10.862 70.243 140.824 30.655 80.620 40.734 20.699 50.791 40.981 220.716 60.844 40.769 51.000 10.594 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]
PBNetpermissive0.747 51.000 10.818 110.837 80.713 20.844 90.457 40.647 230.711 30.614 50.617 90.657 80.650 101.000 10.692 90.822 80.765 61.000 10.595 6
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. Arxiv
GraphCut0.732 61.000 10.788 220.724 210.642 80.859 80.248 130.787 100.618 120.596 60.653 60.722 20.583 261.000 10.766 40.861 20.825 11.000 10.504 19
IPCA-Inst0.731 71.000 10.788 230.884 50.698 30.788 230.252 120.760 120.646 90.511 150.637 80.665 70.804 31.000 10.644 160.778 130.747 81.000 10.561 13
TopoSeg0.725 81.000 10.806 170.933 20.668 70.758 260.272 100.734 160.630 100.549 110.654 50.606 100.697 70.966 240.612 200.839 50.754 71.000 10.573 9
DKNet0.718 91.000 10.814 120.782 130.619 90.872 40.224 150.751 140.569 140.677 20.585 120.724 10.633 180.981 220.515 270.819 90.736 91.000 10.617 2
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
HAISpermissive0.699 101.000 10.849 50.820 90.675 60.808 160.279 80.757 130.465 190.517 140.596 100.559 120.600 201.000 10.654 140.767 150.676 140.994 310.560 14
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSEC0.699 101.000 10.848 60.763 190.609 130.792 210.262 110.824 30.627 110.535 130.547 200.481 160.600 201.000 10.712 80.731 250.689 131.000 10.563 12
SSTNetpermissive0.698 121.000 10.697 390.888 40.556 190.803 170.387 50.626 250.417 230.556 100.585 130.702 30.600 201.000 10.824 20.720 280.692 111.000 10.509 18
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SphereSeg0.680 131.000 10.856 40.744 200.618 100.893 10.151 190.651 220.713 20.537 120.579 150.430 240.651 91.000 10.389 360.744 220.697 100.991 320.601 5
Box2Mask0.677 141.000 10.847 70.771 150.509 270.816 120.277 90.558 320.482 160.562 90.640 70.448 200.700 51.000 10.666 100.852 30.578 260.997 260.488 23
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
OccuSeg+instance0.672 151.000 10.758 310.682 240.576 170.842 100.477 30.504 360.524 150.567 80.585 140.451 190.557 271.000 10.751 50.797 120.563 291.000 10.467 27
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group0.664 161.000 10.822 100.764 180.616 110.815 130.139 230.694 190.597 130.459 210.566 160.599 110.600 200.516 430.715 70.819 100.635 191.000 10.603 3
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
INS-Conv-instance0.657 171.000 10.760 290.667 260.581 150.863 60.323 60.655 210.477 170.473 190.549 180.432 230.650 101.000 10.655 130.738 230.585 250.944 360.472 26
CSC-Pretrained0.648 181.000 10.810 130.768 160.523 250.813 140.143 220.819 50.389 250.422 290.511 230.443 210.650 101.000 10.624 180.732 240.634 201.000 10.375 33
PE0.645 191.000 10.773 260.798 120.538 210.786 240.088 300.799 90.350 290.435 280.547 190.545 130.646 170.933 250.562 230.761 180.556 340.997 260.501 21
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN0.643 201.000 10.758 300.582 350.539 200.826 110.046 340.765 110.372 270.436 270.588 110.539 150.650 101.000 10.577 210.750 200.653 170.997 260.495 22
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
Dyco3Dcopyleft0.641 211.000 10.841 80.893 30.531 230.802 180.115 270.588 300.448 200.438 250.537 220.430 250.550 280.857 270.534 250.764 170.657 150.987 330.568 10
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN0.638 221.000 10.895 30.800 110.480 300.676 320.144 210.737 150.354 280.447 220.400 340.365 300.700 51.000 10.569 220.836 60.599 221.000 10.473 25
PointGroup0.636 231.000 10.765 270.624 280.505 290.797 190.116 260.696 180.384 260.441 230.559 170.476 170.596 241.000 10.666 100.756 190.556 330.997 260.513 17
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]
DD-UNet+Group0.635 240.667 350.797 210.714 230.562 180.774 250.146 200.810 80.429 220.476 180.546 210.399 270.633 181.000 10.632 170.722 270.609 211.000 10.514 16
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
DENet0.629 251.000 10.797 200.608 290.589 140.627 360.219 160.882 10.310 310.402 330.383 360.396 280.650 101.000 10.663 120.543 440.691 121.000 10.568 11
3D-MPA0.611 261.000 10.833 90.765 170.526 240.756 270.136 250.588 300.470 180.438 260.432 320.358 310.650 100.857 270.429 320.765 160.557 321.000 10.430 29
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
OSIS0.605 271.000 10.801 190.599 300.535 220.728 300.286 70.436 400.679 50.491 160.433 300.256 330.404 400.857 270.620 190.724 260.510 381.000 10.539 15
PCJC0.578 281.000 10.810 140.583 340.449 330.813 150.042 350.603 280.341 300.490 170.465 270.410 260.650 100.835 350.264 420.694 320.561 300.889 400.504 20
SSEN0.575 291.000 10.761 280.473 370.477 310.795 200.066 310.529 330.658 70.460 200.461 280.380 290.331 420.859 260.401 350.692 340.653 161.000 10.348 35
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RWSeg0.567 300.528 450.708 380.626 270.580 160.745 290.063 320.627 240.240 350.400 340.497 240.464 180.515 291.000 10.475 290.745 210.571 271.000 10.429 30
NeuralBF0.555 310.667 350.896 20.843 70.517 260.751 280.029 360.519 340.414 240.439 240.465 260.000 510.484 310.857 270.287 400.693 330.651 181.000 10.485 24
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
MTML0.549 321.000 10.807 160.588 330.327 380.647 340.004 410.815 70.180 370.418 300.364 380.182 360.445 341.000 10.442 310.688 350.571 281.000 10.396 31
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
One_Thing_One_Clickpermissive0.529 330.667 350.718 340.777 140.399 340.683 310.000 440.669 200.138 400.391 350.374 370.539 140.360 410.641 400.556 240.774 140.593 230.997 260.251 40
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Sparse R-CNN0.515 341.000 10.538 460.282 400.468 320.790 220.173 180.345 420.429 210.413 320.484 250.176 370.595 250.591 410.522 260.668 360.476 390.986 340.327 36
Occipital-SCS0.512 351.000 10.716 350.509 360.506 280.611 370.092 290.602 290.177 380.346 380.383 350.165 380.442 350.850 340.386 370.618 400.543 350.889 400.389 32
3D-BoNet0.488 361.000 10.672 410.590 320.301 400.484 470.098 280.620 260.306 320.341 390.259 420.125 400.434 370.796 360.402 340.499 460.513 370.909 390.439 28
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
PanopticFusion-inst0.478 370.667 350.712 370.595 310.259 430.550 430.000 440.613 270.175 390.250 440.434 290.437 220.411 390.857 270.485 280.591 430.267 490.944 360.359 34
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
SPG_WSIS0.470 380.667 350.685 400.677 250.372 360.562 410.000 440.482 370.244 340.316 410.298 390.052 460.442 360.857 270.267 410.702 290.559 311.000 10.287 38
SALoss-ResNet0.459 391.000 10.737 330.159 500.259 420.587 390.138 240.475 380.217 360.416 310.408 330.128 390.315 430.714 370.411 330.536 450.590 240.873 430.304 37
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)
MASCpermissive0.447 400.528 450.555 440.381 380.382 350.633 350.002 420.509 350.260 330.361 370.432 310.327 320.451 330.571 420.367 380.639 380.386 400.980 350.276 39
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_inspermissive0.445 410.667 350.773 250.185 470.317 390.656 330.000 440.407 410.134 410.381 360.267 410.217 350.476 320.714 370.452 300.629 390.514 361.000 10.222 43
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
3D-SISpermissive0.382 421.000 10.432 480.245 420.190 440.577 400.013 390.263 440.033 470.320 400.240 430.075 420.422 380.857 270.117 460.699 300.271 480.883 420.235 42
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3Dcopyleft0.323 430.667 350.542 450.264 410.157 470.550 420.000 440.205 470.009 480.270 430.218 440.075 420.500 300.688 390.007 520.698 310.301 450.459 490.200 44
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone0.319 440.667 350.715 360.233 430.189 450.479 480.008 400.218 450.067 460.201 460.173 450.107 410.123 480.438 440.150 440.615 410.355 410.916 380.093 51
R-PointNet0.306 450.500 470.405 490.311 390.348 370.589 380.054 330.068 500.126 420.283 420.290 400.028 470.219 460.214 470.331 390.396 500.275 460.821 450.245 41
Region-18class0.284 460.250 510.751 320.228 450.270 410.521 440.000 440.468 390.008 500.205 450.127 460.000 510.068 500.070 500.262 430.652 370.323 430.740 460.173 45
SemRegionNet-20cls0.250 470.333 480.613 420.229 440.163 460.493 450.000 440.304 430.107 430.147 480.100 470.052 450.231 440.119 480.039 480.445 480.325 420.654 470.141 47
tmp0.248 480.667 350.437 470.188 460.153 480.491 460.000 440.208 460.094 450.153 470.099 480.057 440.217 470.119 480.039 480.466 470.302 440.640 480.140 48
3D-BEVIS0.248 480.667 350.566 430.076 510.035 520.394 500.027 380.035 510.098 440.099 500.030 510.025 480.098 490.375 460.126 450.604 420.181 500.854 440.171 46
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
ASIS0.199 500.333 480.253 510.167 490.140 490.438 490.000 440.177 480.008 490.121 490.069 490.004 500.231 450.429 450.036 500.445 490.273 470.333 510.119 50
Sgpn_scannet0.143 510.208 520.390 500.169 480.065 500.275 510.029 370.069 490.000 510.087 510.043 500.014 490.027 520.000 510.112 470.351 510.168 510.438 500.138 49
MaskRCNN 2d->3d Proj0.058 520.333 480.002 520.000 520.053 510.002 520.002 430.021 520.000 510.045 520.024 520.238 340.065 510.000 510.014 510.107 520.020 520.110 520.006 52


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 10.422 140.898 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 20.451 100.769 30.656 30.567 30.931 30.395 40.390 40.700 30.534 30.689 80.770 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 20.179 190.648 30.463 30.549 20.742 60.676 20.628 20.961 10.420 20.379 50.684 60.381 140.732 20.723 30.599 20.827 120.851 20.634 6
CMX0.613 40.681 70.725 80.502 110.634 50.297 150.478 80.830 20.651 40.537 60.924 40.375 50.315 110.686 50.451 110.714 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 50.856 170.359 90.306 120.596 110.539 20.627 170.706 40.497 70.785 170.757 150.476 18
MCA-Net0.595 60.533 160.756 60.746 40.590 80.334 70.506 50.670 110.587 70.500 100.905 80.366 80.352 80.601 100.506 50.669 140.648 70.501 60.839 110.769 110.516 17
RFBNet0.592 70.616 90.758 50.659 50.581 90.330 80.469 90.655 140.543 120.524 70.924 40.355 100.336 100.572 130.479 70.671 120.648 70.480 90.814 150.814 50.614 9
FAN_NV_RVC0.586 80.510 170.764 40.079 220.620 70.330 80.494 60.753 40.573 80.556 40.884 120.405 30.303 130.718 20.452 100.672 110.658 50.509 40.898 30.813 60.727 2
DCRedNet0.583 90.682 60.723 90.542 100.510 160.310 120.451 100.668 120.549 110.520 80.920 60.375 50.446 20.528 160.417 120.670 130.577 150.478 100.862 70.806 70.628 8
MIX6D_RVC0.582 100.695 40.687 130.225 170.632 60.328 100.550 10.748 50.623 50.494 130.890 100.350 110.254 190.688 40.454 90.716 30.597 140.489 80.881 50.768 120.575 11
SSMAcopyleft0.577 110.695 40.716 110.439 130.563 110.314 110.444 120.719 80.551 100.503 90.887 110.346 120.348 90.603 90.353 160.709 50.600 120.457 120.901 20.786 80.599 10
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
UNIV_CNP_RVC_UE0.566 120.569 150.686 150.435 140.524 130.294 160.421 150.712 90.543 120.463 150.872 130.320 130.363 70.611 80.477 80.686 90.627 90.443 150.862 70.775 100.639 5
SN_RN152pyrx8_RVCcopyleft0.546 130.572 130.663 170.638 70.518 140.298 140.366 200.633 170.510 150.446 170.864 150.296 160.267 160.542 150.346 170.704 60.575 160.431 160.853 100.766 130.630 7
UDSSEG_RVC0.545 140.610 110.661 180.588 80.556 120.268 180.482 70.642 160.572 90.475 140.836 190.312 140.367 60.630 70.189 190.639 160.495 200.452 130.826 130.756 160.541 13
segfomer with 6d0.542 150.594 120.687 130.146 200.579 100.308 130.515 40.703 100.472 170.498 110.868 140.369 70.282 140.589 120.390 130.701 70.556 170.416 180.860 90.759 140.539 15
FuseNetpermissive0.535 160.570 140.681 160.182 180.512 150.290 170.431 130.659 130.504 160.495 120.903 90.308 150.428 30.523 170.365 150.676 100.621 110.470 110.762 180.779 90.541 13
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 170.613 100.722 100.418 150.358 220.337 60.370 190.479 200.443 180.368 200.907 70.207 190.213 210.464 200.525 40.618 180.657 60.450 140.788 160.721 190.408 21
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 180.481 200.612 190.579 90.456 180.343 50.384 170.623 180.525 140.381 190.845 180.254 180.264 180.557 140.182 200.581 200.598 130.429 170.760 190.661 210.446 20
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 190.505 180.709 120.092 210.427 190.241 190.411 160.654 150.385 220.457 160.861 160.053 220.279 150.503 180.481 60.645 150.626 100.365 200.748 200.725 180.529 16
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 200.490 190.581 200.289 160.507 170.067 220.379 180.610 190.417 200.435 180.822 210.278 170.267 160.503 180.228 180.616 190.533 190.375 190.820 140.729 170.560 12
Enet (reimpl)0.376 210.264 220.452 220.452 120.365 200.181 200.143 220.456 210.409 210.346 210.769 220.164 200.218 200.359 210.123 220.403 220.381 220.313 220.571 210.685 200.472 19
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)permissive0.330 220.293 210.521 210.657 60.361 210.161 210.250 210.004 220.440 190.183 220.836 190.125 210.060 220.319 220.132 210.417 210.412 210.344 210.541 220.427 220.109 22
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
DMMF0.003 230.000 230.005 230.000 230.000 230.037 230.001 230.000 230.001 230.005 230.003 230.000 230.000 230.000 230.000 230.000 230.002 230.001 230.000 230.006 230.000 23


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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
UniDet_RVC0.358 10.554 10.543 10.128 10.402 10.381 10.200 10.461 10.328 10.138 10.232 10.148 20.466 10.109 10.538 10.506 10.294 10.862 10.159 1
MaskRCNN_ScanNetpermissive0.227 20.228 20.381 20.013 20.237 20.339 20.089 20.339 20.150 20.134 20.143 20.179 10.255 20.053 20.331 20.244 20.154 20.687 20.127 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