Presenting the ScanNet200 Benchmark

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

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

ScanNet200 Benchmark

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




Method Infoavg iouhead ioucommon ioutail ioualarm clockarmchairbackpackbagballbarbasketbathroom cabinetbathroom counterbathroom stallbathroom stall doorbathroom vanitybathtubbedbenchbicyclebinblackboardblanketblindsboardbookbookshelfbottlebowlboxbroombucketbulletin boardcabinetcalendarcandlecartcase of water bottlescd caseceilingceiling lightchairclockclosetcloset doorcloset rodcloset wallclothesclothes dryercoat rackcoffee kettlecoffee makercoffee tablecolumncomputer towercontainercopiercouchcountercratecupcurtaincushiondecorationdeskdining tabledish rackdishwasherdividerdoordoorframedresserdumbbelldustpanend tablefanfile cabinetfire alarmfire extinguisherfireplacefloorfolded chairfurnitureguitarguitar casehair dryerhandicap barhatheadphonesironing boardjacketkeyboardkeyboard pianokitchen cabinetkitchen counterladderlamplaptoplaundry basketlaundry detergentlaundry hamperledgelightlight switchluggagemachinemailboxmatmattressmicrowavemini fridgemirrormonitormousemusic standnightstandobjectoffice chairottomanovenpaperpaper bagpaper cutterpaper towel dispenserpaper towel rollpersonpianopicturepillarpillowpipeplantplateplungerposterpotted plantpower outletpower stripprinterprojectorprojector screenpurserackradiatorrailrange hoodrecycling binrefrigeratorscaleseatshelfshoeshowershower curtainshower curtain rodshower doorshower floorshower headshower wallsignsinksoap dishsoap dispensersofa chairspeakerstair railstairsstandstoolstorage binstorage containerstorage organizerstovestructurestuffed animalsuitcasetabletelephonetissue boxtoastertoaster oventoilettoilet papertoilet paper dispensertoilet paper holdertoilet seat cover dispensertoweltrash bintrash cantraytubetvtv standvacuum cleanerventwallwardrobewashing machinewater bottlewater coolerwater pitcherwhiteboardwindowwindowsill
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 by
CSC-Pretrainpermissive0.249 30.455 30.171 20.079 30.418 20.059 30.186 20.000 10.000 10.000 10.335 30.250 20.316 20.766 10.697 30.142 10.170 10.003 20.553 30.112 10.097 10.201 30.186 20.476 30.081 20.000 20.216 30.000 10.000 10.001 30.314 30.000 10.000 10.055 10.000 20.832 30.094 10.659 20.002 10.076 20.310 30.293 30.664 30.000 10.000 10.175 30.634 10.130 20.552 30.686 30.700 30.076 10.110 10.770 30.000 10.000 20.430 30.000 30.319 10.166 20.542 30.327 20.205 30.332 20.052 30.375 10.444 30.000 20.012 30.930 30.203 10.000 10.000 10.046 10.175 10.413 20.592 20.471 20.299 10.152 30.340 20.247 30.000 10.000 10.225 10.058 20.037 20.000 10.207 10.862 30.014 10.548 10.033 20.233 20.816 20.000 10.000 10.542 30.123 20.121 10.019 10.000 10.000 10.463 20.454 30.045 30.128 30.557 20.235 10.441 20.063 30.484 30.000 20.308 30.000 10.000 10.000 10.318 30.000 10.000 20.000 10.545 20.543 20.164 30.734 10.000 10.000 10.215 30.371 20.198 10.743 10.205 30.062 30.000 10.079 20.000 10.683 20.547 20.142 20.000 20.441 20.579 30.000 10.464 10.098 20.041 10.000 10.590 20.000 20.000 10.373 10.494 10.174 10.105 20.001 30.895 20.222 20.537 20.307 20.180 20.625 10.000 10.000 20.591 30.609 20.398 10.000 10.766 30.014 30.638 30.000 10.377 10.004 30.206 30.609 30.465 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 20.463 20.154 30.102 20.381 30.084 10.134 30.000 10.000 10.000 10.386 20.141 30.279 30.737 30.703 20.014 30.164 20.000 30.663 10.092 20.000 20.224 20.291 10.531 10.056 30.000 20.242 20.000 10.000 10.013 20.331 20.000 10.000 10.035 30.001 10.858 10.059 30.650 30.000 30.056 30.353 20.299 20.670 20.000 10.000 10.284 20.484 30.071 30.594 20.720 20.710 20.027 30.068 30.813 10.000 10.005 10.492 10.164 10.274 20.111 30.571 20.307 30.293 20.307 30.150 10.163 30.531 20.002 10.545 10.932 10.093 30.000 10.000 10.002 20.159 20.368 30.581 30.440 30.228 30.406 10.282 30.294 20.000 10.000 10.189 20.060 10.036 30.000 10.000 20.897 10.000 30.525 20.025 30.205 30.771 30.000 10.000 10.593 20.108 30.044 30.000 20.000 10.000 10.282 30.589 20.094 20.169 20.466 30.227 30.419 30.125 20.757 10.002 10.334 20.000 10.000 10.000 10.357 20.000 10.000 20.000 10.582 10.513 30.337 10.612 30.000 10.000 10.250 20.352 30.136 30.724 20.655 10.280 10.000 10.046 30.000 10.606 30.559 10.159 10.102 10.445 10.655 10.000 10.310 30.117 10.000 30.000 10.581 30.026 10.000 10.265 30.483 20.084 30.097 30.044 10.865 30.142 30.588 10.351 10.272 10.596 30.000 10.003 10.622 20.720 10.096 30.000 10.771 20.016 20.772 10.000 10.302 20.194 20.214 20.621 20.197 3
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
LGroundpermissive0.272 10.485 10.184 10.106 10.476 10.077 20.218 10.000 10.000 10.000 10.547 10.295 10.540 10.746 20.745 10.058 20.112 30.005 10.658 20.077 30.000 20.322 10.178 30.512 20.190 10.199 10.277 10.000 10.000 10.173 10.399 10.000 10.000 10.039 20.000 20.858 10.085 20.676 10.002 10.103 10.498 10.323 10.703 10.000 10.000 10.296 10.549 20.216 10.702 10.768 10.718 10.028 20.092 20.786 20.000 10.000 20.453 20.022 20.251 30.252 10.572 10.348 10.321 10.514 10.063 20.279 20.552 10.000 20.019 20.932 10.132 20.000 10.000 10.000 30.156 30.457 10.623 10.518 10.265 20.358 20.381 10.395 10.000 10.000 10.127 30.012 30.051 10.000 10.000 20.886 20.014 10.437 30.179 10.244 10.826 10.000 10.000 10.599 10.136 10.085 20.000 20.000 10.000 10.565 10.612 10.143 10.207 10.566 10.232 20.446 10.127 10.708 20.000 20.384 10.000 10.000 10.000 10.402 10.000 10.059 10.000 10.525 30.566 10.229 20.659 20.000 10.000 10.265 10.446 10.147 20.720 30.597 20.066 20.000 10.187 10.000 10.726 10.467 30.134 30.000 20.413 30.629 20.000 10.363 20.055 30.022 20.000 10.626 10.000 20.000 10.323 20.479 30.154 20.117 10.028 20.901 10.243 10.415 30.295 30.143 30.610 20.000 10.000 20.777 10.397 30.324 20.000 10.778 10.179 10.702 20.000 10.274 30.404 10.233 10.622 10.398 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv


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 bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 by
Mask3D Scannet2000.445 10.653 10.392 10.254 10.648 10.097 10.125 40.000 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 20.300 10.000 10.201 10.000 10.009 10.290 10.556 11.000 10.000 10.063 20.000 10.830 10.573 10.844 10.333 10.204 10.058 40.158 40.552 10.056 10.000 11.000 10.725 30.750 10.927 11.000 10.888 30.042 20.120 20.615 30.226 10.250 10.890 10.792 10.677 20.510 20.818 10.699 10.512 10.167 40.125 10.315 10.943 10.309 10.017 20.200 20.000 10.188 10.000 10.183 20.815 11.000 10.827 10.741 10.442 20.414 30.600 10.000 10.000 10.458 10.049 20.321 10.381 10.000 10.908 10.400 10.841 10.260 10.710 10.966 10.265 10.000 10.924 10.152 10.025 10.500 10.027 10.028 11.000 10.556 40.016 10.080 40.500 10.694 30.608 10.084 10.604 20.194 10.538 30.000 10.500 10.000 10.354 30.000 11.000 10.000 10.761 20.930 10.053 30.890 21.000 10.008 10.262 10.358 11.000 11.000 10.792 30.966 11.000 10.765 10.004 10.930 10.780 10.330 10.027 10.625 10.974 30.050 10.412 40.021 20.000 20.000 10.778 10.000 10.000 10.493 20.746 10.454 10.335 20.396 10.930 40.551 11.000 10.552 10.606 10.853 10.000 10.004 10.806 11.000 10.727 20.000 10.042 20.745 10.000 10.399 30.391 10.630 10.721 10.619 1
CSC-Pretrain Inst.permissive0.275 40.466 40.218 30.110 40.625 20.007 40.500 10.000 10.000 10.000 10.000 40.222 40.377 41.000 10.661 40.400 20.000 40.000 20.000 30.119 40.000 20.000 40.277 40.685 30.067 20.000 10.132 20.000 10.000 20.000 30.367 30.000 20.000 10.000 30.000 10.591 20.055 30.783 40.000 20.014 20.500 20.161 30.278 20.000 20.000 10.667 20.768 10.500 20.866 21.000 10.829 40.000 30.019 40.555 40.000 20.000 20.305 40.000 20.750 10.200 40.783 30.429 30.395 20.677 20.020 40.286 20.584 40.000 20.000 30.115 40.000 10.000 20.000 10.145 40.423 40.500 20.364 40.369 30.571 10.448 20.206 40.000 10.000 10.200 20.106 10.065 40.000 20.000 10.750 20.200 20.774 20.000 40.501 30.841 30.000 20.000 10.692 40.063 30.000 20.000 20.000 20.000 20.500 30.649 10.000 20.084 30.125 40.719 10.413 40.004 30.450 40.000 20.638 10.000 10.000 20.000 10.505 20.000 10.000 20.000 10.727 30.833 20.221 10.779 40.000 20.000 20.168 40.311 40.125 20.571 30.500 40.143 40.000 20.250 30.000 20.869 20.667 30.162 40.000 20.250 31.000 10.000 20.500 10.000 30.000 20.000 10.689 30.000 10.000 10.312 30.383 40.114 20.333 30.000 30.997 20.420 20.613 30.212 40.500 20.819 20.000 10.000 20.768 21.000 10.918 10.000 10.000 30.278 40.000 10.333 40.000 40.353 20.546 40.258 3
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.314 20.529 20.225 20.155 20.578 40.010 20.500 10.000 10.000 10.000 10.515 20.556 20.696 11.000 10.927 20.400 20.083 30.000 21.000 10.252 10.000 20.167 20.350 20.731 10.067 20.000 10.123 30.000 10.000 20.036 20.372 20.000 20.000 10.250 10.000 10.569 30.031 40.810 20.000 20.000 30.630 10.183 10.278 20.000 20.000 10.582 30.589 40.500 20.863 31.000 10.940 10.000 30.144 10.716 20.000 20.000 20.484 20.000 20.500 30.400 30.798 20.500 20.278 30.750 10.093 20.166 30.783 20.000 20.200 10.400 10.000 10.000 20.000 10.219 10.539 20.500 20.578 20.413 20.181 40.457 10.375 20.000 10.000 10.050 40.000 30.077 30.000 20.000 10.500 40.000 40.743 30.250 20.488 40.846 20.000 20.000 10.800 20.069 20.000 20.000 20.000 20.000 21.000 10.607 30.000 20.200 10.500 10.694 20.528 20.063 20.659 10.000 20.594 20.000 10.000 20.000 10.571 10.000 10.000 20.000 10.716 40.647 40.221 10.857 30.000 20.000 20.217 20.346 20.071 40.530 41.000 10.429 20.000 20.286 20.000 20.826 40.706 20.208 30.000 20.250 30.744 40.000 20.500 10.042 10.000 20.000 10.746 20.000 10.000 10.517 10.625 20.085 40.333 30.000 31.000 10.378 30.533 40.376 30.042 40.814 30.000 10.000 20.765 31.000 10.600 30.000 10.000 30.667 20.000 10.472 10.333 20.337 30.605 20.305 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Minkowski 34D Inst.permissive0.280 30.488 30.192 40.124 30.593 30.010 30.500 10.000 10.000 10.000 10.447 30.535 30.445 31.000 10.861 30.400 20.225 20.000 20.000 30.142 30.000 20.074 30.342 30.467 40.067 20.000 10.119 40.000 10.000 20.000 30.337 40.000 20.000 10.000 30.000 10.506 40.070 20.804 30.000 20.000 30.333 30.172 20.150 40.000 20.000 10.479 40.745 20.000 40.830 41.000 10.904 20.167 10.090 30.732 10.000 20.000 20.443 30.000 20.500 30.542 10.772 40.396 40.077 40.385 30.044 30.118 40.777 30.000 20.000 30.200 20.000 10.000 20.000 10.148 30.502 30.500 20.419 30.159 40.281 30.404 40.317 30.000 10.000 10.200 20.000 30.077 20.000 20.000 10.750 20.200 20.715 40.021 30.551 20.828 40.000 20.000 10.743 30.059 40.000 20.000 20.000 20.000 20.125 40.648 20.000 20.191 20.500 10.669 40.502 30.000 40.568 30.000 20.516 40.000 10.000 20.000 10.305 40.000 10.000 20.000 10.825 10.833 20.021 40.918 10.000 20.000 20.191 30.346 30.100 30.981 21.000 10.286 30.000 20.000 40.000 20.868 30.648 40.292 20.000 20.375 21.000 10.000 20.500 10.000 30.333 10.000 10.538 40.000 10.000 10.213 40.518 30.098 30.528 10.250 20.997 20.284 40.677 20.398 20.167 30.790 40.000 10.000 20.618 40.903 40.200 40.000 10.333 10.333 30.000 10.442 20.083 30.213 40.587 30.131 4
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


ScanNet Benchmark

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mix3Dpermissive0.781 10.964 10.855 10.843 100.781 10.858 70.575 20.831 150.685 50.714 10.979 10.594 30.310 150.801 10.892 70.841 20.819 30.723 20.940 70.887 10.725 9
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
OccuSeg+Semantic0.764 20.758 400.796 150.839 110.746 70.907 10.562 30.850 100.680 60.672 50.978 20.610 10.335 70.777 30.819 260.847 10.830 10.691 60.972 10.885 20.727 7
O-CNNpermissive0.762 30.924 20.823 40.844 90.770 20.852 90.577 10.847 110.711 10.640 130.958 80.592 40.217 500.762 90.888 80.758 70.813 50.726 10.932 130.868 80.744 3
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
PointFormerV20.752 40.742 470.809 100.872 10.758 30.860 60.552 40.891 50.610 220.687 20.960 70.559 120.304 180.766 70.926 20.767 50.797 130.644 150.942 50.876 70.722 11
PointConvFormer0.749 50.793 260.790 180.807 200.750 60.856 80.524 100.881 60.588 320.642 120.977 40.591 50.274 290.781 20.929 10.804 30.796 140.642 160.947 30.885 20.715 13
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 50.909 30.818 70.811 170.752 50.839 130.485 240.842 130.673 70.644 100.957 100.528 190.305 170.773 50.859 130.788 40.818 40.693 50.916 150.856 140.723 10
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 70.623 710.804 110.859 30.745 80.824 240.501 160.912 20.690 40.685 30.956 110.567 90.320 120.768 60.918 30.720 160.802 90.676 80.921 140.881 40.779 1
StratifiedFormerpermissive0.747 80.901 40.803 120.845 80.757 40.846 110.512 130.825 160.696 30.645 90.956 110.576 70.262 370.744 140.861 120.742 90.770 270.705 30.899 250.860 110.734 4
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 90.771 340.819 60.848 60.702 190.865 50.397 620.899 30.699 20.664 60.948 330.588 60.330 80.746 130.851 180.764 60.796 140.704 40.935 100.866 90.728 5
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 90.870 90.838 20.858 40.729 120.850 100.501 160.874 70.587 330.658 70.956 110.564 100.299 190.765 80.900 50.716 190.812 60.631 210.939 80.858 120.709 14
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-FPN0.744 110.842 160.800 130.767 340.740 90.836 160.541 60.914 10.672 80.626 140.958 80.552 130.272 300.777 30.886 90.696 260.801 100.674 90.941 60.858 120.717 12
EQ-Net0.743 120.620 720.799 140.849 50.730 110.822 260.493 220.897 40.664 90.681 40.955 150.562 110.378 10.760 100.903 40.738 100.801 100.673 100.907 180.877 50.745 2
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
MinkowskiNetpermissive0.736 130.859 120.818 70.832 120.709 160.840 120.521 120.853 90.660 110.643 110.951 230.544 140.286 250.731 150.893 60.675 320.772 250.683 70.874 450.852 160.727 7
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 140.890 50.837 30.864 20.726 130.873 20.530 90.824 170.489 650.647 80.978 20.609 20.336 60.624 300.733 390.758 70.776 230.570 450.949 20.877 50.728 5
SparseConvNet0.725 150.647 670.821 50.846 70.721 140.869 30.533 80.754 350.603 280.614 170.955 150.572 80.325 100.710 160.870 100.724 140.823 20.628 220.934 110.865 100.683 19
MatchingNet0.724 160.812 230.812 90.810 180.735 100.834 170.495 210.860 80.572 390.602 240.954 170.512 220.280 260.757 110.845 210.725 130.780 210.606 300.937 90.851 170.700 16
INS-Conv-semantic0.717 170.751 430.759 300.812 160.704 180.868 40.537 70.842 130.609 240.608 200.953 190.534 150.293 210.616 310.864 110.719 180.793 170.640 170.933 120.845 210.663 23
contrastBoundarypermissive0.705 180.769 370.775 240.809 190.687 210.820 290.439 490.812 220.661 100.591 270.945 420.515 210.171 680.633 270.856 140.720 160.796 140.668 110.889 330.847 190.689 18
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RFCR0.702 190.889 60.745 390.813 150.672 240.818 330.493 220.815 200.623 180.610 180.947 360.470 340.249 420.594 350.848 190.705 230.779 220.646 140.892 310.823 280.611 39
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 Click0.701 200.825 200.796 150.723 410.716 150.832 180.433 510.816 180.634 160.609 190.969 60.418 600.344 40.559 470.833 230.715 200.808 70.560 490.902 220.847 190.680 20
JSENetpermissive0.699 210.881 80.762 280.821 130.667 250.800 460.522 110.792 270.613 200.607 210.935 620.492 270.205 550.576 410.853 160.691 270.758 320.652 130.872 480.828 250.649 28
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-IIpermissive0.696 220.704 570.790 180.787 260.709 160.837 140.459 340.815 200.543 490.615 160.956 110.529 170.250 400.551 520.790 310.703 240.799 120.619 250.908 170.848 180.700 16
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One-Thing-One-Click0.693 230.743 460.794 170.655 650.684 220.822 260.497 200.719 450.622 190.617 150.977 40.447 470.339 50.750 120.664 540.703 240.790 190.596 340.946 40.855 150.647 29
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
CU-Hybrid Net0.693 230.596 760.789 200.803 220.677 230.800 460.469 280.846 120.554 470.591 270.948 330.500 250.316 130.609 320.847 200.732 110.808 70.593 370.894 290.839 220.652 27
Feature_GeometricNetpermissive0.690 250.884 70.754 340.795 250.647 300.818 330.422 530.802 250.612 210.604 220.945 420.462 380.189 630.563 460.853 160.726 120.765 280.632 200.904 200.821 310.606 43
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 260.704 570.741 430.754 380.656 260.829 200.501 160.741 400.609 240.548 350.950 270.522 200.371 20.633 270.756 340.715 200.771 260.623 230.861 550.814 330.658 24
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 270.866 100.748 360.819 140.645 320.794 510.450 390.802 250.587 330.604 220.945 420.464 370.201 580.554 490.840 220.723 150.732 410.602 320.907 180.822 300.603 46
KP-FCNN0.684 280.847 150.758 320.784 280.647 300.814 360.473 260.772 300.605 260.594 260.935 620.450 450.181 660.587 360.805 290.690 280.785 200.614 260.882 370.819 320.632 34
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 280.728 530.757 330.776 300.690 200.804 440.464 320.816 180.577 380.587 290.945 420.508 240.276 280.671 170.710 440.663 370.750 350.589 400.881 390.832 240.653 26
Superpoint Network0.683 300.851 140.728 480.800 240.653 280.806 420.468 290.804 230.572 390.602 240.946 390.453 440.239 450.519 580.822 240.689 300.762 300.595 360.895 280.827 260.630 35
PointContrast_LA_SEM0.683 300.757 410.784 210.786 270.639 340.824 240.408 570.775 290.604 270.541 370.934 660.532 160.269 330.552 500.777 320.645 470.793 170.640 170.913 160.824 270.671 21
VI-PointConv0.676 320.770 360.754 340.783 290.621 380.814 360.552 40.758 330.571 410.557 330.954 170.529 170.268 350.530 560.682 490.675 320.719 440.603 310.888 340.833 230.665 22
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 330.789 270.748 360.763 360.635 360.814 360.407 590.747 370.581 370.573 300.950 270.484 280.271 320.607 330.754 350.649 420.774 240.596 340.883 360.823 280.606 43
SALANet0.670 340.816 220.770 260.768 330.652 290.807 410.451 360.747 370.659 120.545 360.924 720.473 330.149 780.571 430.811 280.635 500.746 360.623 230.892 310.794 460.570 56
PointConvpermissive0.666 350.781 290.759 300.699 490.644 330.822 260.475 250.779 280.564 440.504 530.953 190.428 540.203 570.586 380.754 350.661 380.753 330.588 410.902 220.813 350.642 30
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 350.703 590.781 220.751 400.655 270.830 190.471 270.769 310.474 680.537 390.951 230.475 320.279 270.635 250.698 480.675 320.751 340.553 540.816 660.806 370.703 15
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++permissive0.663 370.746 440.708 510.722 420.638 350.820 290.451 360.566 730.599 300.541 370.950 270.510 230.313 140.648 220.819 260.616 560.682 600.590 390.869 510.810 360.656 25
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 380.778 300.702 540.806 210.619 390.813 390.468 290.693 530.494 610.524 450.941 530.449 460.298 200.510 600.821 250.675 320.727 430.568 470.826 630.803 390.637 32
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 390.698 600.743 410.650 660.564 570.820 290.505 150.758 330.631 170.479 580.945 420.480 300.226 460.572 420.774 330.690 280.735 390.614 260.853 580.776 600.597 49
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 400.752 420.734 450.664 620.583 510.815 350.399 610.754 350.639 140.535 410.942 510.470 340.309 160.665 180.539 620.650 410.708 500.635 190.857 570.793 480.642 30
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 410.778 300.731 460.699 490.577 520.829 200.446 410.736 410.477 670.523 470.945 420.454 420.269 330.484 670.749 380.618 540.738 370.599 330.827 620.792 510.621 37
MVPNetpermissive0.641 420.831 170.715 490.671 590.590 470.781 570.394 630.679 560.642 130.553 340.937 590.462 380.256 380.649 210.406 760.626 510.691 570.666 120.877 410.792 510.608 42
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN0.641 420.776 320.703 530.721 430.557 600.826 220.451 360.672 580.563 450.483 570.943 500.425 570.162 730.644 230.726 400.659 390.709 490.572 440.875 430.786 550.559 61
PointMRNet0.640 440.717 560.701 550.692 520.576 530.801 450.467 310.716 460.563 450.459 630.953 190.429 530.169 700.581 390.854 150.605 570.710 470.550 550.894 290.793 480.575 54
FPConvpermissive0.639 450.785 280.760 290.713 470.603 420.798 490.392 640.534 780.603 280.524 450.948 330.457 400.250 400.538 540.723 420.598 610.696 550.614 260.872 480.799 400.567 58
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 460.797 250.769 270.641 710.590 470.820 290.461 330.537 770.637 150.536 400.947 360.388 670.206 540.656 190.668 520.647 450.732 410.585 420.868 520.793 480.473 79
PointSPNet0.637 470.734 500.692 620.714 460.576 530.797 500.446 410.743 390.598 310.437 680.942 510.403 630.150 770.626 290.800 300.649 420.697 540.557 520.846 590.777 590.563 59
SConv0.636 480.830 180.697 580.752 390.572 560.780 590.445 430.716 460.529 520.530 420.951 230.446 480.170 690.507 620.666 530.636 490.682 600.541 610.886 350.799 400.594 50
Supervoxel-CNN0.635 490.656 650.711 500.719 440.613 400.757 680.444 460.765 320.534 510.566 310.928 700.478 310.272 300.636 240.531 640.664 360.645 710.508 680.864 540.792 510.611 39
joint point-basedpermissive0.634 500.614 730.778 230.667 610.633 370.825 230.420 540.804 230.467 700.561 320.951 230.494 260.291 220.566 440.458 700.579 670.764 290.559 510.838 600.814 330.598 48
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
MCCNNpermissive0.633 510.866 100.731 460.771 310.576 530.809 400.410 560.684 540.497 600.491 550.949 300.466 360.105 830.581 390.646 560.620 520.680 620.542 600.817 650.795 440.618 38
P. Hermosilla, T. Ritschel, P.P. Vazquez, A. Vinacua, T. Ropinski: Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds. SIGGRAPH Asia 2018
PointMTL0.632 520.731 510.688 650.675 560.591 460.784 560.444 460.565 740.610 220.492 540.949 300.456 410.254 390.587 360.706 450.599 600.665 670.612 290.868 520.791 540.579 53
3DSM_DMMF0.631 530.626 700.745 390.801 230.607 410.751 690.506 140.729 440.565 430.491 550.866 860.434 490.197 610.595 340.630 570.709 220.705 520.560 490.875 430.740 700.491 74
APCF-Net0.631 530.742 470.687 670.672 570.557 600.792 540.408 570.665 590.545 480.508 500.952 220.428 540.186 640.634 260.702 460.620 520.706 510.555 530.873 460.798 420.581 52
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
PointNet2-SFPN0.631 530.771 340.692 620.672 570.524 640.837 140.440 480.706 510.538 500.446 650.944 480.421 590.219 490.552 500.751 370.591 630.737 380.543 590.901 240.768 620.557 62
FusionAwareConv0.630 560.604 750.741 430.766 350.590 470.747 700.501 160.734 420.503 590.527 430.919 760.454 420.323 110.550 530.420 750.678 310.688 580.544 570.896 270.795 440.627 36
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 570.800 240.625 780.719 440.545 620.806 420.445 430.597 670.448 750.519 480.938 580.481 290.328 90.489 660.499 690.657 400.759 310.592 380.881 390.797 430.634 33
SegGroup_sempermissive0.627 580.818 210.747 380.701 480.602 430.764 650.385 690.629 640.490 630.508 500.931 690.409 620.201 580.564 450.725 410.618 540.692 560.539 620.873 460.794 460.548 65
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 590.830 180.694 600.757 370.563 580.772 630.448 400.647 620.520 540.509 490.949 300.431 520.191 620.496 640.614 580.647 450.672 650.535 640.876 420.783 560.571 55
HPEIN0.618 600.729 520.668 680.647 680.597 450.766 640.414 550.680 550.520 540.525 440.946 390.432 500.215 510.493 650.599 590.638 480.617 760.570 450.897 260.806 370.605 45
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-GCNpermissive0.610 610.858 130.772 250.489 830.532 630.792 540.404 600.643 630.570 420.507 520.935 620.414 610.046 890.510 600.702 460.602 590.705 520.549 560.859 560.773 610.534 68
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 620.760 390.667 690.649 670.521 650.793 520.457 350.648 610.528 530.434 700.947 360.401 640.153 760.454 690.721 430.648 440.717 450.536 630.904 200.765 630.485 75
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 630.634 680.743 410.697 510.601 440.781 570.437 500.585 710.493 620.446 650.933 670.394 650.011 910.654 200.661 550.603 580.733 400.526 650.832 610.761 650.480 76
LAP-D0.594 640.720 540.692 620.637 720.456 740.773 620.391 660.730 430.587 330.445 670.940 550.381 680.288 230.434 720.453 720.591 630.649 690.581 430.777 700.749 690.610 41
DPC0.592 650.720 540.700 560.602 760.480 700.762 670.380 700.713 490.585 360.437 680.940 550.369 700.288 230.434 720.509 680.590 650.639 740.567 480.772 710.755 670.592 51
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 660.766 380.659 720.683 540.470 730.740 720.387 680.620 660.490 630.476 590.922 740.355 740.245 430.511 590.511 670.571 680.643 720.493 720.872 480.762 640.600 47
ROSMRF0.580 670.772 330.707 520.681 550.563 580.764 650.362 720.515 790.465 710.465 620.936 610.427 560.207 530.438 700.577 600.536 720.675 640.486 730.723 770.779 570.524 70
SD-DETR0.576 680.746 440.609 820.445 870.517 660.643 830.366 710.714 480.456 720.468 610.870 850.432 500.264 360.558 480.674 500.586 660.688 580.482 750.739 750.733 720.537 67
SQN_0.1%0.569 690.676 620.696 590.657 640.497 670.779 600.424 520.548 750.515 560.376 750.902 830.422 580.357 30.379 760.456 710.596 620.659 680.544 570.685 800.665 840.556 63
TextureNetpermissive0.566 700.672 640.664 700.671 590.494 680.719 730.445 430.678 570.411 810.396 730.935 620.356 730.225 470.412 740.535 630.565 690.636 750.464 770.794 690.680 810.568 57
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
DVVNet0.562 710.648 660.700 560.770 320.586 500.687 770.333 760.650 600.514 570.475 600.906 800.359 720.223 480.340 790.442 740.422 830.668 660.501 690.708 780.779 570.534 68
Pointnet++ & Featurepermissive0.557 720.735 490.661 710.686 530.491 690.744 710.392 640.539 760.451 740.375 760.946 390.376 690.205 550.403 750.356 790.553 710.643 720.497 700.824 640.756 660.515 71
PointMRNet-lite0.553 730.633 690.648 730.659 630.430 770.800 460.390 670.592 690.454 730.371 770.939 570.368 710.136 800.368 770.448 730.560 700.715 460.486 730.882 370.720 760.462 80
GMLPs0.538 740.495 840.693 610.647 680.471 720.793 520.300 790.477 800.505 580.358 780.903 820.327 770.081 860.472 680.529 650.448 810.710 470.509 660.746 730.737 710.554 64
PanopticFusion-label0.529 750.491 850.688 650.604 750.386 800.632 840.225 890.705 520.434 780.293 840.815 870.348 750.241 440.499 630.669 510.507 740.649 690.442 830.796 680.602 870.561 60
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_weak0.516 760.676 620.591 850.609 730.442 750.774 610.335 750.597 670.422 800.357 790.932 680.341 760.094 850.298 810.528 660.473 790.676 630.495 710.602 860.721 750.349 87
Online SegFusion0.515 770.607 740.644 760.579 780.434 760.630 850.353 730.628 650.440 760.410 710.762 900.307 790.167 710.520 570.403 770.516 730.565 790.447 810.678 810.701 780.514 72
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, FTSDF0.501 780.558 800.608 830.424 890.478 710.690 760.246 850.586 700.468 690.450 640.911 780.394 650.160 740.438 700.212 860.432 820.541 840.475 760.742 740.727 730.477 77
PCNN0.498 790.559 790.644 760.560 800.420 790.711 750.229 870.414 810.436 770.352 800.941 530.324 780.155 750.238 860.387 780.493 750.529 850.509 660.813 670.751 680.504 73
3DMV0.484 800.484 860.538 870.643 700.424 780.606 880.310 770.574 720.433 790.378 740.796 880.301 800.214 520.537 550.208 870.472 800.507 880.413 860.693 790.602 870.539 66
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 810.577 780.611 810.356 910.321 880.715 740.299 810.376 850.328 880.319 820.944 480.285 820.164 720.216 890.229 840.484 770.545 830.456 790.755 720.709 770.475 78
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 820.679 610.604 840.578 790.380 810.682 780.291 820.106 910.483 660.258 890.920 750.258 860.025 900.231 880.325 800.480 780.560 810.463 780.725 760.666 830.231 91
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 830.474 870.623 790.463 850.366 830.651 810.310 770.389 840.349 860.330 810.937 590.271 840.126 810.285 820.224 850.350 880.577 780.445 820.625 840.723 740.394 83
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
PNET20.442 840.548 810.548 860.597 770.363 840.628 860.300 790.292 860.374 830.307 830.881 840.268 850.186 640.238 860.204 880.407 840.506 890.449 800.667 820.620 860.462 80
SurfaceConvPF0.442 840.505 830.622 800.380 900.342 860.654 800.227 880.397 830.367 840.276 860.924 720.240 870.198 600.359 780.262 820.366 850.581 770.435 840.640 830.668 820.398 82
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 860.437 890.646 750.474 840.369 820.645 820.353 730.258 880.282 900.279 850.918 770.298 810.147 790.283 830.294 810.487 760.562 800.427 850.619 850.633 850.352 86
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 870.525 820.647 740.522 810.324 870.488 910.077 920.712 500.353 850.401 720.636 920.281 830.176 670.340 790.565 610.175 920.551 820.398 870.370 920.602 870.361 85
SPLAT Netcopyleft0.393 880.472 880.511 880.606 740.311 890.656 790.245 860.405 820.328 880.197 900.927 710.227 890.000 930.001 930.249 830.271 910.510 860.383 890.593 870.699 790.267 89
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+FTSDF0.383 890.297 910.491 890.432 880.358 850.612 870.274 830.116 900.411 810.265 870.904 810.229 880.079 870.250 840.185 890.320 890.510 860.385 880.548 880.597 900.394 83
PointNet++permissive0.339 900.584 770.478 900.458 860.256 910.360 920.250 840.247 890.278 910.261 880.677 910.183 900.117 820.212 900.145 910.364 860.346 920.232 920.548 880.523 910.252 90
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 910.353 900.290 920.278 920.166 920.553 890.169 910.286 870.147 920.148 920.908 790.182 910.064 880.023 920.018 930.354 870.363 900.345 900.546 900.685 800.278 88
ScanNetpermissive0.306 920.203 920.366 910.501 820.311 890.524 900.211 900.002 930.342 870.189 910.786 890.145 920.102 840.245 850.152 900.318 900.348 910.300 910.460 910.437 920.182 92
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 930.000 930.041 930.172 930.030 930.062 930.001 930.035 920.004 930.051 930.143 930.019 930.003 920.041 910.050 920.003 930.054 930.018 930.005 930.264 930.082 93


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
SoftGroup++0.874 11.000 10.972 90.947 10.839 30.898 80.556 180.913 20.881 80.756 50.828 20.748 40.821 11.000 10.937 30.937 10.887 11.000 10.821 2
Mask3D0.870 21.000 10.985 60.782 240.818 50.938 30.760 20.749 200.923 30.877 20.760 40.785 10.820 21.000 10.912 60.864 170.878 30.983 310.825 1
SoftGrouppermissive0.865 31.000 10.969 100.860 90.860 10.913 50.558 160.899 30.911 40.760 40.828 10.736 50.802 40.981 250.919 50.875 100.877 41.000 10.820 3
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
IPCA-Inst0.851 41.000 10.968 110.884 60.842 20.862 190.693 60.812 160.888 70.677 140.783 30.698 80.807 31.000 10.911 100.865 160.865 61.000 10.757 7
SPFormer0.851 41.000 10.994 20.806 180.774 120.942 20.637 90.849 90.859 100.889 10.720 60.730 60.665 101.000 10.911 100.868 150.873 51.000 10.796 4
SphereSeg0.835 61.000 10.963 130.891 40.794 70.954 10.822 10.710 230.961 20.721 80.693 120.530 250.653 111.000 10.867 180.857 200.859 70.991 280.771 5
TopoSeg0.832 71.000 10.981 70.933 20.819 40.826 260.524 230.841 100.811 140.681 130.759 50.687 90.727 50.981 250.911 100.883 80.853 81.000 10.756 8
GraphCut0.832 71.000 10.922 250.724 340.798 60.902 70.701 50.856 70.859 90.715 90.706 70.748 30.640 201.000 10.934 40.862 180.880 21.000 10.729 9
DKNet0.815 91.000 10.930 180.844 110.765 150.915 40.534 210.805 180.805 160.807 30.654 140.763 20.650 121.000 10.794 290.881 90.766 121.000 10.758 6
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN0.806 101.000 10.992 40.789 200.723 250.891 90.650 80.810 170.832 120.665 160.699 100.658 100.700 61.000 10.881 150.832 260.774 100.997 220.613 26
HAISpermissive0.803 111.000 10.994 20.820 160.759 160.855 200.554 190.882 40.827 130.615 230.676 130.638 130.646 181.000 10.912 60.797 360.767 110.994 270.726 10
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask0.803 111.000 10.962 140.874 70.707 280.887 120.686 70.598 310.961 10.715 100.694 110.469 300.700 61.000 10.912 60.902 30.753 180.997 220.637 22
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group0.792 131.000 10.968 120.812 170.766 140.864 150.460 260.815 150.888 60.598 250.651 170.639 120.600 240.918 280.941 10.896 40.721 221.000 10.723 11
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained0.791 141.000 10.996 10.829 150.767 130.889 110.600 120.819 140.770 210.594 260.620 220.541 220.700 61.000 10.941 10.889 60.763 141.000 10.526 35
SSTNetpermissive0.789 151.000 10.840 380.888 50.717 260.835 220.717 40.684 260.627 340.724 70.652 160.727 70.600 241.000 10.912 60.822 290.757 171.000 10.691 18
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN0.788 161.000 10.978 80.867 80.781 100.833 230.527 220.824 110.806 150.549 330.596 240.551 180.700 61.000 10.853 190.935 20.733 191.000 10.651 19
DENet0.786 171.000 10.929 190.736 320.750 210.720 390.755 30.934 10.794 170.590 270.561 290.537 230.650 121.000 10.882 130.804 340.789 91.000 10.719 12
SSEC0.781 181.000 10.945 150.763 290.780 110.819 280.601 110.824 110.790 180.638 190.622 210.550 190.600 241.000 10.882 130.790 370.765 131.000 10.698 16
PointGroup0.778 191.000 10.900 290.798 190.715 270.863 160.493 240.706 240.895 50.569 310.701 80.576 160.639 211.000 10.880 160.851 220.719 230.997 220.709 14
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]
PE0.776 201.000 10.900 300.860 90.728 240.869 130.400 310.857 60.774 190.568 320.701 90.602 150.646 180.933 270.843 210.890 50.691 300.997 220.709 13
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
DD-UNet+Group0.764 211.000 10.897 320.837 120.753 180.830 250.459 270.824 110.699 280.629 210.653 150.438 320.650 121.000 10.880 160.858 190.690 311.000 10.650 20
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-instance0.762 221.000 10.923 220.765 270.785 90.905 60.600 120.655 270.646 330.683 120.647 180.530 240.650 121.000 10.824 220.830 270.693 290.944 350.644 21
Dyco3Dcopyleft0.761 231.000 10.935 160.893 30.752 200.863 170.600 120.588 320.742 240.641 180.633 200.546 210.550 310.857 310.789 310.853 210.762 150.987 290.699 15
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance0.742 241.000 10.923 220.785 210.745 220.867 140.557 170.578 350.729 250.670 150.644 190.488 280.577 301.000 10.794 290.830 270.620 371.000 10.550 31
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg0.739 251.000 10.899 310.759 300.753 190.823 270.282 350.691 250.658 310.582 300.594 250.547 200.628 221.000 10.795 280.868 140.728 211.000 10.692 17
3D-MPA0.737 261.000 10.933 170.785 210.794 80.831 240.279 370.588 320.695 290.616 220.559 300.556 170.650 121.000 10.809 260.875 110.696 271.000 10.608 28
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML0.731 271.000 10.992 40.779 260.609 360.746 340.308 340.867 50.601 370.607 240.539 330.519 260.550 311.000 10.824 220.869 130.729 201.000 10.616 25
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
SSEN0.724 281.000 10.926 200.781 250.661 320.845 210.596 150.529 370.764 230.653 170.489 380.461 310.500 380.859 300.765 320.872 120.761 161.000 10.577 29
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
Sparse R-CNN0.714 291.000 10.926 210.694 350.699 300.890 100.636 100.516 380.693 300.743 60.588 260.369 350.601 230.594 410.800 270.886 70.676 320.986 300.546 32
SALoss-ResNet0.695 301.000 10.855 360.579 430.589 380.735 370.484 250.588 320.856 110.634 200.571 280.298 360.500 381.000 10.824 220.818 300.702 260.935 390.545 33
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-inst0.693 311.000 10.852 370.655 390.616 350.788 290.334 330.763 190.771 200.457 430.555 310.652 110.518 350.857 310.765 320.732 430.631 350.944 350.577 30
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-SCS0.688 321.000 10.913 260.730 330.737 230.743 360.442 280.855 80.655 320.546 340.546 320.263 380.508 370.889 290.568 400.771 400.705 250.889 420.625 24
3D-BoNet0.687 331.000 10.887 340.836 130.587 390.643 460.550 200.620 280.724 260.522 380.501 360.243 390.512 361.000 10.751 340.807 330.661 340.909 410.612 27
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
PCJC0.684 341.000 10.895 330.757 310.659 330.862 180.189 440.739 210.606 360.712 110.581 270.515 270.650 120.857 310.357 450.785 380.631 360.889 420.635 23
SPG_WSIS0.678 351.000 10.880 350.836 130.701 290.727 380.273 390.607 300.706 270.541 360.515 350.174 410.600 240.857 310.716 350.846 240.711 241.000 10.506 36
One_Thing_One_Clickpermissive0.675 361.000 10.823 390.782 230.621 340.766 310.211 410.736 220.560 400.586 280.522 340.636 140.453 400.641 400.853 190.850 230.694 280.997 220.411 40
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_inspermissive0.637 371.000 10.923 240.593 420.561 400.746 350.143 460.504 390.766 220.485 410.442 390.372 340.530 340.714 370.815 250.775 390.673 331.000 10.431 39
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASCpermissive0.615 380.711 440.802 400.540 440.757 170.777 300.029 470.577 360.588 390.521 390.600 230.436 330.534 330.697 380.616 390.838 250.526 390.980 320.534 34
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone0.605 391.000 10.909 270.764 280.603 370.704 400.415 300.301 440.548 410.461 420.394 400.267 370.386 420.857 310.649 380.817 310.504 400.959 330.356 43
3D-SISpermissive0.558 401.000 10.773 410.614 410.503 420.691 420.200 420.412 400.498 440.546 350.311 450.103 450.600 240.857 310.382 420.799 350.445 460.938 380.371 41
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.544 410.500 470.655 470.661 380.663 310.765 320.432 290.214 460.612 350.584 290.499 370.204 400.286 460.429 440.655 370.650 480.539 380.950 340.499 37
Hier3Dcopyleft0.540 421.000 10.727 420.626 400.467 450.693 410.200 420.412 400.480 450.528 370.318 440.077 480.600 240.688 390.382 420.768 410.472 420.941 370.350 44
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class0.497 430.250 490.902 280.689 360.540 410.747 330.276 380.610 290.268 480.489 400.348 410.000 490.243 480.220 470.663 360.814 320.459 440.928 400.496 38
tmp0.474 441.000 10.727 420.433 470.481 440.673 440.022 490.380 420.517 430.436 450.338 430.128 430.343 440.429 440.291 470.728 440.473 410.833 450.300 46
SemRegionNet-20cls0.470 451.000 10.727 420.447 460.481 430.678 430.024 480.380 420.518 420.440 440.339 420.128 430.350 430.429 440.212 480.711 450.465 430.833 450.290 47
ASIS0.422 460.333 480.707 450.676 370.401 460.650 450.350 320.177 470.594 380.376 460.202 460.077 470.404 410.571 420.197 490.674 470.447 450.500 480.260 48
3D-BEVIS0.401 470.667 450.687 460.419 480.137 490.587 470.188 450.235 450.359 470.211 480.093 490.080 460.311 450.571 420.382 420.754 420.300 480.874 440.357 42
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.390 480.556 460.636 480.493 450.353 470.539 480.271 400.160 480.450 460.359 470.178 470.146 420.250 470.143 480.347 460.698 460.436 470.667 470.331 45
MaskRCNN 2d->3d Proj0.261 490.903 430.081 490.008 490.233 480.175 490.280 360.106 490.150 490.203 490.175 480.480 290.218 490.143 480.542 410.404 490.153 490.393 490.049 49


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 20.179 180.648 30.463 30.549 20.742 60.676 20.628 20.961 10.420 20.379 50.684 60.381 130.732 20.723 30.599 20.827 110.851 20.634 5
CMX0.613 40.681 70.725 80.502 110.634 50.297 150.478 80.830 20.651 40.537 60.924 40.375 50.315 100.686 50.451 100.714 40.543 170.504 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 50.856 160.359 90.306 110.596 100.539 20.627 160.706 40.497 70.785 160.757 140.476 17
MCA-Net0.595 60.533 150.756 60.746 40.590 80.334 70.506 50.670 100.587 70.500 100.905 80.366 80.352 70.601 90.506 50.669 130.648 70.501 60.839 100.769 100.516 16
RFBNet0.592 70.616 90.758 50.659 50.581 90.330 80.469 90.655 130.543 120.524 70.924 40.355 100.336 90.572 120.479 70.671 110.648 70.480 90.814 140.814 50.614 8
FAN_NV_RVC0.586 80.510 160.764 40.079 210.620 70.330 80.494 60.753 40.573 80.556 40.884 120.405 30.303 120.718 20.452 90.672 100.658 50.509 40.898 30.813 60.727 2
DCRedNet0.583 90.682 60.723 90.542 100.510 150.310 120.451 100.668 110.549 110.520 80.920 60.375 50.446 20.528 150.417 110.670 120.577 140.478 100.862 70.806 70.628 7
MIX6D_RVC0.582 100.695 40.687 130.225 160.632 60.328 100.550 10.748 50.623 50.494 130.890 100.350 110.254 180.688 40.454 80.716 30.597 130.489 80.881 50.768 110.575 10
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 80.603 80.353 150.709 50.600 110.457 120.901 20.786 80.599 9
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
SN_RN152pyrx8_RVCcopyleft0.546 120.572 130.663 160.638 70.518 130.298 140.366 190.633 160.510 140.446 160.864 140.296 150.267 150.542 140.346 160.704 60.575 150.431 150.853 90.766 120.630 6
UDSSEG_RVC0.545 130.610 110.661 170.588 80.556 120.268 170.482 70.642 150.572 90.475 140.836 180.312 130.367 60.630 70.189 180.639 150.495 190.452 130.826 120.756 150.541 12
segfomer with 6d0.542 140.594 120.687 130.146 190.579 100.308 130.515 40.703 90.472 160.498 110.868 130.369 70.282 130.589 110.390 120.701 70.556 160.416 170.860 80.759 130.539 14
FuseNetpermissive0.535 150.570 140.681 150.182 170.512 140.290 160.431 130.659 120.504 150.495 120.903 90.308 140.428 30.523 160.365 140.676 90.621 100.470 110.762 170.779 90.541 12
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 160.613 100.722 100.418 140.358 210.337 60.370 180.479 190.443 170.368 190.907 70.207 180.213 200.464 190.525 40.618 170.657 60.450 140.788 150.721 180.408 20
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 170.481 190.612 180.579 90.456 170.343 50.384 160.623 170.525 130.381 180.845 170.254 170.264 170.557 130.182 190.581 190.598 120.429 160.760 180.661 200.446 19
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 180.505 170.709 120.092 200.427 180.241 180.411 150.654 140.385 210.457 150.861 150.053 210.279 140.503 170.481 60.645 140.626 90.365 190.748 190.725 170.529 15
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 190.490 180.581 190.289 150.507 160.067 210.379 170.610 180.417 190.435 170.822 200.278 160.267 150.503 170.228 170.616 180.533 180.375 180.820 130.729 160.560 11
Enet (reimpl)0.376 200.264 210.452 210.452 120.365 190.181 190.143 210.456 200.409 200.346 200.769 210.164 190.218 190.359 200.123 210.403 210.381 210.313 210.571 200.685 190.472 18
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)permissive0.330 210.293 200.521 200.657 60.361 200.161 200.250 200.004 210.440 180.183 210.836 180.125 200.060 210.319 210.132 200.417 200.412 200.344 200.541 210.427 210.109 21
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
DMMF0.003 220.000 220.005 220.000 220.000 220.037 220.001 220.000 220.001 220.005 220.003 220.000 220.000 220.000 220.000 220.000 220.002 220.001 220.000 220.006 220.000 22


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