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 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 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.
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
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
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 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 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 by
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.
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
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
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 30.831 180.685 70.714 10.979 10.594 30.310 160.801 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 70.295 220.753 140.884 120.758 90.815 50.725 20.927 150.867 90.743 5
OccuSeg+Semantic0.764 20.758 440.796 180.839 120.746 110.907 10.562 50.850 120.680 90.672 50.978 20.610 10.335 80.777 40.819 310.847 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 40.217 560.762 100.888 90.758 90.813 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 50.793 210.802 270.689 260.825 290.556 60.867 80.681 80.602 280.960 70.555 160.365 30.779 30.859 170.747 120.795 170.717 40.917 180.856 170.764 2
PointTransformerV20.752 50.742 510.809 120.872 10.758 50.860 60.552 70.891 50.610 280.687 20.960 70.559 140.304 190.766 80.926 20.767 60.797 130.644 200.942 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
BPNetcopyleft0.749 70.909 40.818 80.811 210.752 80.839 170.485 300.842 150.673 100.644 100.957 120.528 230.305 180.773 60.859 170.788 40.818 40.693 70.916 190.856 170.723 13
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer0.749 70.793 300.790 220.807 240.750 100.856 80.524 150.881 60.588 380.642 130.977 40.591 50.274 320.781 20.929 10.804 30.796 140.642 210.947 30.885 20.715 17
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
MSP0.748 90.623 750.804 140.859 30.745 120.824 310.501 220.912 20.690 60.685 30.956 130.567 110.320 130.768 70.918 30.720 200.802 90.676 100.921 160.881 40.779 1
StratifiedFormerpermissive0.747 100.901 60.803 150.845 80.757 60.846 130.512 180.825 200.696 50.645 90.956 130.576 90.262 420.744 180.861 160.742 130.770 300.705 50.899 300.860 140.734 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 MVFusion0.746 110.771 380.819 60.848 60.702 240.865 50.397 670.899 30.699 30.664 60.948 380.588 60.330 90.746 170.851 230.764 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 40.729 160.850 110.501 220.874 70.587 390.658 70.956 130.564 120.299 200.765 90.900 50.716 230.812 70.631 260.939 80.858 150.709 18
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-FPN0.744 130.842 180.800 160.767 390.740 130.836 210.541 90.914 10.672 110.626 170.958 90.552 170.272 340.777 40.886 110.696 300.801 100.674 120.941 60.858 150.717 15
EQ-Net0.743 140.620 760.799 170.849 50.730 150.822 330.493 280.897 40.664 120.681 40.955 170.562 130.378 10.760 110.903 40.738 140.801 100.673 130.907 230.877 50.745 3
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet0.742 150.816 250.806 130.807 240.752 80.828 270.575 30.839 170.699 30.637 150.954 210.520 250.320 130.755 130.834 270.760 80.772 270.676 100.915 200.862 120.717 15
SAT0.742 150.860 130.765 330.819 160.769 30.848 120.533 110.829 190.663 130.631 160.955 170.586 80.274 320.753 140.896 60.729 150.760 350.666 150.921 160.855 190.733 7
MinkowskiNetpermissive0.736 170.859 140.818 80.832 130.709 210.840 160.521 170.853 110.660 150.643 110.951 290.544 180.286 270.731 190.893 70.675 370.772 270.683 90.874 480.852 210.727 10
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 180.890 70.837 30.864 20.726 170.873 20.530 140.824 210.489 690.647 80.978 20.609 20.336 70.624 350.733 440.758 90.776 250.570 510.949 20.877 50.728 8
SparseConvNet0.725 190.647 720.821 50.846 70.721 190.869 30.533 110.754 400.603 340.614 210.955 170.572 100.325 110.710 200.870 130.724 180.823 20.628 270.934 110.865 110.683 24
PointTransformer++0.725 190.727 580.811 110.819 160.765 40.841 150.502 210.814 260.621 240.623 180.955 170.556 150.284 280.620 360.866 140.781 50.757 380.648 180.932 130.862 120.709 18
MatchingNet0.724 210.812 270.812 100.810 220.735 140.834 220.495 270.860 100.572 450.602 280.954 210.512 270.280 290.757 120.845 250.725 170.780 230.606 370.937 90.851 220.700 21
INS-Conv-semantic0.717 220.751 470.759 360.812 200.704 230.868 40.537 100.842 150.609 300.608 240.953 240.534 190.293 230.616 370.864 150.719 220.793 180.640 220.933 120.845 260.663 29
PointMetaBase0.714 230.835 190.785 240.821 140.684 280.846 130.531 130.865 90.614 250.596 310.953 240.500 300.246 480.674 210.888 90.692 310.764 320.624 280.849 620.844 270.675 26
contrastBoundarypermissive0.705 240.769 410.775 290.809 230.687 270.820 360.439 540.812 270.661 140.591 340.945 470.515 260.171 740.633 320.856 190.720 200.796 140.668 140.889 370.847 240.689 23
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RFCR0.702 250.889 80.745 450.813 190.672 300.818 400.493 280.815 240.623 220.610 220.947 400.470 390.249 470.594 400.848 240.705 270.779 240.646 190.892 350.823 340.611 44
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 Click0.701 260.825 230.796 180.723 460.716 200.832 230.433 560.816 220.634 200.609 230.969 60.418 640.344 50.559 510.833 280.715 240.808 80.560 550.902 270.847 240.680 25
JSENetpermissive0.699 270.881 100.762 340.821 140.667 310.800 520.522 160.792 320.613 260.607 250.935 660.492 320.205 610.576 450.853 210.691 320.758 370.652 170.872 510.828 310.649 33
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-IIpermissive0.696 280.704 620.790 220.787 310.709 210.837 190.459 390.815 240.543 540.615 200.956 130.529 210.250 450.551 560.790 360.703 280.799 120.619 320.908 220.848 230.700 21
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One-Thing-One-Click0.693 290.743 500.794 200.655 690.684 280.822 330.497 260.719 500.622 230.617 190.977 40.447 510.339 60.750 160.664 590.703 280.790 200.596 410.946 40.855 190.647 34
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Feature_GeometricNetpermissive0.690 300.884 90.754 400.795 300.647 360.818 400.422 580.802 300.612 270.604 260.945 470.462 420.189 690.563 500.853 210.726 160.765 310.632 250.904 250.821 370.606 48
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 310.704 620.741 490.754 430.656 320.829 250.501 220.741 450.609 300.548 410.950 330.522 240.371 20.633 320.756 390.715 240.771 290.623 290.861 580.814 390.658 30
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 320.866 120.748 420.819 160.645 380.794 550.450 440.802 300.587 390.604 260.945 470.464 410.201 640.554 530.840 260.723 190.732 470.602 390.907 230.822 360.603 51
KP-FCNN0.684 330.847 170.758 380.784 330.647 360.814 430.473 320.772 350.605 320.594 330.935 660.450 490.181 720.587 410.805 340.690 330.785 220.614 330.882 410.819 380.632 39
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 330.728 570.757 390.776 350.690 250.804 500.464 370.816 220.577 440.587 350.945 470.508 290.276 310.671 220.710 490.663 420.750 410.589 460.881 420.832 300.653 32
Superpoint Network0.683 350.851 160.728 530.800 290.653 340.806 480.468 340.804 280.572 450.602 280.946 440.453 480.239 510.519 620.822 290.689 350.762 340.595 430.895 330.827 320.630 40
PointContrast_LA_SEM0.683 350.757 450.784 250.786 320.639 400.824 310.408 610.775 340.604 330.541 430.934 700.532 200.269 380.552 540.777 370.645 520.793 180.640 220.913 210.824 330.671 27
VI-PointConv0.676 370.770 400.754 400.783 340.621 440.814 430.552 70.758 380.571 470.557 390.954 210.529 210.268 400.530 600.682 540.675 370.719 500.603 380.888 380.833 290.665 28
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 380.789 310.748 420.763 410.635 420.814 430.407 630.747 420.581 430.573 360.950 330.484 330.271 360.607 380.754 400.649 470.774 260.596 410.883 400.823 340.606 48
SALANet0.670 390.816 250.770 310.768 380.652 350.807 470.451 410.747 420.659 160.545 420.924 760.473 380.149 840.571 470.811 330.635 550.746 420.623 290.892 350.794 510.570 61
PointASNLpermissive0.666 400.703 640.781 270.751 450.655 330.830 240.471 330.769 360.474 720.537 450.951 290.475 370.279 300.635 300.698 530.675 370.751 400.553 600.816 690.806 430.703 20
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PointConvpermissive0.666 400.781 330.759 360.699 540.644 390.822 330.475 310.779 330.564 500.504 590.953 240.428 580.203 630.586 430.754 400.661 430.753 390.588 470.902 270.813 410.642 35
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++permissive0.663 420.746 480.708 560.722 470.638 410.820 360.451 410.566 760.599 360.541 430.950 330.510 280.313 150.648 270.819 310.616 600.682 650.590 450.869 540.810 420.656 31
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 430.778 340.702 590.806 260.619 450.813 460.468 340.693 580.494 650.524 510.941 580.449 500.298 210.510 640.821 300.675 370.727 490.568 530.826 670.803 450.637 37
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 440.698 650.743 470.650 700.564 620.820 360.505 200.758 380.631 210.479 630.945 470.480 350.226 520.572 460.774 380.690 330.735 450.614 330.853 610.776 650.597 54
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 450.752 460.734 510.664 670.583 570.815 420.399 660.754 400.639 180.535 470.942 560.470 390.309 170.665 230.539 660.650 460.708 550.635 240.857 600.793 530.642 35
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 460.778 340.731 520.699 540.577 580.829 250.446 460.736 460.477 710.523 530.945 470.454 460.269 380.484 710.749 430.618 580.738 430.599 400.827 660.792 560.621 42
MVPNetpermissive0.641 470.831 200.715 540.671 640.590 530.781 610.394 680.679 600.642 170.553 400.937 630.462 420.256 430.649 260.406 790.626 560.691 620.666 150.877 440.792 560.608 47
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN0.641 470.776 360.703 580.721 480.557 650.826 280.451 410.672 620.563 510.483 620.943 550.425 610.162 790.644 280.726 450.659 440.709 540.572 500.875 460.786 600.559 66
PointMRNet0.640 490.717 610.701 600.692 570.576 590.801 510.467 360.716 510.563 510.459 680.953 240.429 570.169 760.581 440.854 200.605 610.710 520.550 610.894 340.793 530.575 59
FPConvpermissive0.639 500.785 320.760 350.713 520.603 480.798 530.392 690.534 810.603 340.524 510.948 380.457 440.250 450.538 580.723 470.598 650.696 600.614 330.872 510.799 460.567 63
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 510.797 290.769 320.641 750.590 530.820 360.461 380.537 800.637 190.536 460.947 400.388 710.206 600.656 240.668 570.647 500.732 470.585 480.868 550.793 530.473 84
PointSPNet0.637 520.734 540.692 670.714 510.576 590.797 540.446 460.743 440.598 370.437 730.942 560.403 670.150 830.626 340.800 350.649 470.697 590.557 580.846 630.777 640.563 64
SConv0.636 530.830 210.697 630.752 440.572 610.780 630.445 480.716 510.529 570.530 480.951 290.446 520.170 750.507 660.666 580.636 540.682 650.541 660.886 390.799 460.594 55
Supervoxel-CNN0.635 540.656 700.711 550.719 490.613 460.757 720.444 510.765 370.534 560.566 370.928 740.478 360.272 340.636 290.531 680.664 410.645 750.508 730.864 570.792 560.611 44
joint point-basedpermissive0.634 550.614 770.778 280.667 660.633 430.825 290.420 590.804 280.467 740.561 380.951 290.494 310.291 240.566 480.458 740.579 710.764 320.559 570.838 640.814 390.598 53
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 560.731 550.688 700.675 610.591 520.784 600.444 510.565 770.610 280.492 600.949 360.456 450.254 440.587 410.706 500.599 640.665 710.612 360.868 550.791 590.579 58
PointNet2-SFPN0.631 570.771 380.692 670.672 620.524 690.837 190.440 530.706 560.538 550.446 700.944 530.421 630.219 550.552 540.751 420.591 670.737 440.543 650.901 290.768 670.557 67
APCF-Net0.631 570.742 510.687 720.672 620.557 650.792 580.408 610.665 630.545 530.508 560.952 280.428 580.186 700.634 310.702 510.620 570.706 560.555 590.873 490.798 480.581 57
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
3DSM_DMMF0.631 570.626 740.745 450.801 280.607 470.751 730.506 190.729 490.565 490.491 610.866 900.434 530.197 670.595 390.630 610.709 260.705 570.560 550.875 460.740 750.491 79
FusionAwareConv0.630 600.604 790.741 490.766 400.590 530.747 740.501 220.734 470.503 640.527 490.919 800.454 460.323 120.550 570.420 780.678 360.688 630.544 630.896 320.795 500.627 41
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 610.800 280.625 820.719 490.545 670.806 480.445 480.597 710.448 780.519 540.938 620.481 340.328 100.489 700.499 730.657 450.759 360.592 440.881 420.797 490.634 38
SegGroup_sempermissive0.627 620.818 240.747 440.701 530.602 490.764 690.385 730.629 680.490 670.508 560.931 730.409 660.201 640.564 490.725 460.618 580.692 610.539 670.873 490.794 510.548 70
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 630.830 210.694 650.757 420.563 630.772 670.448 450.647 660.520 590.509 550.949 360.431 560.191 680.496 680.614 620.647 500.672 690.535 690.876 450.783 610.571 60
HPEIN0.618 640.729 560.668 730.647 720.597 510.766 680.414 600.680 590.520 590.525 500.946 440.432 540.215 570.493 690.599 630.638 530.617 800.570 510.897 310.806 430.605 50
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-GCNpermissive0.610 650.858 150.772 300.489 870.532 680.792 580.404 650.643 670.570 480.507 580.935 660.414 650.046 930.510 640.702 510.602 630.705 570.549 620.859 590.773 660.534 73
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 660.760 430.667 740.649 710.521 700.793 560.457 400.648 650.528 580.434 750.947 400.401 680.153 820.454 730.721 480.648 490.717 510.536 680.904 250.765 680.485 80
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 670.634 730.743 470.697 560.601 500.781 610.437 550.585 740.493 660.446 700.933 710.394 690.011 950.654 250.661 600.603 620.733 460.526 700.832 650.761 700.480 81
LAP-D0.594 680.720 590.692 670.637 760.456 790.773 660.391 710.730 480.587 390.445 720.940 600.381 720.288 250.434 760.453 760.591 670.649 730.581 490.777 730.749 740.610 46
DPC0.592 690.720 590.700 610.602 800.480 750.762 710.380 740.713 540.585 420.437 730.940 600.369 740.288 250.434 760.509 720.590 690.639 780.567 540.772 740.755 720.592 56
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 700.766 420.659 770.683 590.470 780.740 760.387 720.620 700.490 670.476 640.922 780.355 770.245 490.511 630.511 710.571 720.643 760.493 770.872 510.762 690.600 52
ROSMRF0.580 710.772 370.707 570.681 600.563 630.764 690.362 760.515 820.465 750.465 670.936 650.427 600.207 590.438 740.577 640.536 750.675 680.486 780.723 800.779 620.524 75
SD-DETR0.576 720.746 480.609 860.445 910.517 710.643 870.366 750.714 530.456 760.468 660.870 890.432 540.264 410.558 520.674 550.586 700.688 630.482 790.739 780.733 770.537 72
SQN_0.1%0.569 730.676 670.696 640.657 680.497 720.779 640.424 570.548 780.515 610.376 800.902 870.422 620.357 40.379 800.456 750.596 660.659 720.544 630.685 830.665 880.556 68
TextureNetpermissive0.566 740.672 690.664 750.671 640.494 730.719 770.445 480.678 610.411 840.396 780.935 660.356 760.225 530.412 780.535 670.565 730.636 790.464 810.794 720.680 850.568 62
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
DVVNet0.562 750.648 710.700 610.770 370.586 560.687 810.333 800.650 640.514 620.475 650.906 840.359 750.223 540.340 820.442 770.422 860.668 700.501 740.708 810.779 620.534 73
Pointnet++ & Featurepermissive0.557 760.735 530.661 760.686 580.491 740.744 750.392 690.539 790.451 770.375 810.946 440.376 730.205 610.403 790.356 820.553 740.643 760.497 750.824 680.756 710.515 76
GMLPs0.538 770.495 870.693 660.647 720.471 770.793 560.300 830.477 830.505 630.358 820.903 860.327 800.081 900.472 720.529 690.448 840.710 520.509 710.746 760.737 760.554 69
PanopticFusion-label0.529 780.491 880.688 700.604 790.386 840.632 880.225 930.705 570.434 810.293 880.815 910.348 780.241 500.499 670.669 560.507 770.649 730.442 870.796 710.602 910.561 65
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_weak0.516 790.676 670.591 890.609 770.442 800.774 650.335 790.597 710.422 830.357 830.932 720.341 790.094 890.298 840.528 700.473 820.676 670.495 760.602 890.721 800.349 91
Online SegFusion0.515 800.607 780.644 800.579 820.434 810.630 890.353 770.628 690.440 790.410 760.762 940.307 820.167 770.520 610.403 800.516 760.565 830.447 850.678 840.701 820.514 77
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, FTSDF0.501 810.558 830.608 870.424 930.478 760.690 800.246 890.586 730.468 730.450 690.911 820.394 690.160 800.438 740.212 890.432 850.541 880.475 800.742 770.727 780.477 82
PCNN0.498 820.559 820.644 800.560 840.420 830.711 790.229 910.414 840.436 800.352 840.941 580.324 810.155 810.238 890.387 810.493 780.529 890.509 710.813 700.751 730.504 78
3DMV0.484 830.484 890.538 910.643 740.424 820.606 920.310 810.574 750.433 820.378 790.796 920.301 830.214 580.537 590.208 900.472 830.507 920.413 900.693 820.602 910.539 71
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 840.577 810.611 850.356 950.321 920.715 780.299 850.376 880.328 910.319 860.944 530.285 850.164 780.216 920.229 870.484 800.545 870.456 830.755 750.709 810.475 83
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 850.679 660.604 880.578 830.380 850.682 820.291 860.106 940.483 700.258 930.920 790.258 890.025 940.231 910.325 830.480 810.560 850.463 820.725 790.666 870.231 95
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 860.474 900.623 830.463 890.366 870.651 850.310 810.389 870.349 890.330 850.937 630.271 870.126 860.285 850.224 880.350 910.577 820.445 860.625 870.723 790.394 87
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
SurfaceConvPF0.442 870.505 860.622 840.380 940.342 900.654 840.227 920.397 860.367 870.276 900.924 760.240 900.198 660.359 810.262 850.366 880.581 810.435 880.640 860.668 860.398 86
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET20.442 870.548 840.548 900.597 810.363 880.628 900.300 830.292 890.374 860.307 870.881 880.268 880.186 700.238 890.204 910.407 870.506 930.449 840.667 850.620 900.462 85
Tangent Convolutionspermissive0.438 890.437 920.646 790.474 880.369 860.645 860.353 770.258 910.282 930.279 890.918 810.298 840.147 850.283 860.294 840.487 790.562 840.427 890.619 880.633 890.352 90
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 900.525 850.647 780.522 850.324 910.488 950.077 960.712 550.353 880.401 770.636 960.281 860.176 730.340 820.565 650.175 950.551 860.398 910.370 950.602 910.361 89
SimConv0.410 910.000 960.782 260.772 360.722 180.838 180.407 630.000 970.000 970.595 320.947 400.000 970.270 370.000 970.000 970.000 970.786 210.621 310.000 970.841 280.621 42
SPLAT Netcopyleft0.393 920.472 910.511 920.606 780.311 930.656 830.245 900.405 850.328 910.197 940.927 750.227 920.000 970.001 960.249 860.271 940.510 900.383 930.593 900.699 830.267 93
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+FTSDF0.383 930.297 940.491 930.432 920.358 890.612 910.274 870.116 930.411 840.265 910.904 850.229 910.079 910.250 870.185 920.320 920.510 900.385 920.548 910.597 940.394 87
PointNet++permissive0.339 940.584 800.478 940.458 900.256 950.360 960.250 880.247 920.278 940.261 920.677 950.183 930.117 870.212 930.145 940.364 890.346 960.232 960.548 910.523 950.252 94
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 950.353 930.290 960.278 960.166 960.553 930.169 950.286 900.147 950.148 960.908 830.182 940.064 920.023 950.018 960.354 900.363 940.345 940.546 930.685 840.278 92
ScanNetpermissive0.306 960.203 950.366 950.501 860.311 930.524 940.211 940.002 960.342 900.189 950.786 930.145 950.102 880.245 880.152 930.318 930.348 950.300 950.460 940.437 960.182 96
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 970.000 960.041 970.172 970.030 970.062 970.001 970.035 950.004 960.051 970.143 970.019 960.003 960.041 940.050 950.003 960.054 970.018 970.005 960.264 970.082 97


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 40.898 80.556 200.913 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 60.782 260.818 60.938 30.760 30.749 200.923 30.877 20.760 40.785 10.820 21.000 10.912 60.864 190.878 30.983 340.825 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SoftGrouppermissive0.865 31.000 10.969 100.860 100.860 10.913 50.558 180.899 30.911 40.760 40.828 10.736 50.802 40.981 260.919 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]
SPFormerpermissive0.851 41.000 10.994 20.806 200.774 130.942 20.637 100.849 90.859 110.889 10.720 60.730 60.665 101.000 10.911 100.868 170.873 51.000 10.796 4
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023
IPCA-Inst0.851 41.000 10.968 110.884 70.842 30.862 200.693 70.812 160.888 70.677 170.783 30.698 80.807 31.000 10.911 100.865 180.865 61.000 10.757 7
SphereSeg0.835 61.000 10.963 140.891 50.794 80.954 10.822 20.710 230.961 20.721 90.693 120.530 260.653 111.000 10.867 180.857 220.859 70.991 310.771 5
GraphCut0.832 71.000 10.922 270.724 360.798 70.902 70.701 60.856 70.859 100.715 100.706 70.748 30.640 211.000 10.934 40.862 200.880 21.000 10.729 10
TopoSeg0.832 71.000 10.981 70.933 20.819 50.826 270.524 250.841 100.811 160.681 160.759 50.687 90.727 50.981 260.911 100.883 80.853 81.000 10.756 8
PBNetpermissive0.825 91.000 10.963 130.837 140.843 20.865 150.822 10.647 300.878 90.733 70.639 200.683 100.650 121.000 10.853 190.870 140.820 91.000 10.744 9
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. Arxiv
DKNet0.815 101.000 10.930 200.844 120.765 160.915 40.534 230.805 180.805 180.807 30.654 140.763 20.650 121.000 10.794 310.881 90.766 131.000 10.758 6
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN0.806 111.000 10.992 40.789 220.723 270.891 90.650 90.810 170.832 130.665 190.699 100.658 110.700 61.000 10.881 150.832 290.774 110.997 250.613 29
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAISpermissive0.803 121.000 10.994 20.820 180.759 170.855 210.554 210.882 40.827 150.615 260.676 130.638 140.646 191.000 10.912 60.797 390.767 120.994 300.726 11
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask0.803 121.000 10.962 150.874 80.707 300.887 120.686 80.598 340.961 10.715 110.694 110.469 310.700 61.000 10.912 60.902 30.753 190.997 250.637 23
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group0.792 141.000 10.968 120.812 190.766 150.864 160.460 280.815 150.888 60.598 280.651 170.639 130.600 250.918 300.941 10.896 40.721 241.000 10.723 12
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained0.791 151.000 10.996 10.829 170.767 140.889 110.600 130.819 140.770 240.594 290.620 230.541 220.700 61.000 10.941 10.889 60.763 151.000 10.526 38
SSTNetpermissive0.789 161.000 10.840 410.888 60.717 280.835 230.717 50.684 280.627 370.724 80.652 160.727 70.600 251.000 10.912 60.822 320.757 181.000 10.691 19
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN0.788 171.000 10.978 80.867 90.781 110.833 240.527 240.824 110.806 170.549 360.596 250.551 190.700 61.000 10.853 190.935 20.733 211.000 10.651 20
DENet0.786 181.000 10.929 210.736 340.750 230.720 420.755 40.934 10.794 190.590 300.561 310.537 230.650 121.000 10.882 130.804 370.789 101.000 10.719 13
SSEC0.781 191.000 10.945 170.763 310.780 120.819 290.601 120.824 110.790 200.638 220.622 220.536 240.600 251.000 10.882 130.790 400.765 141.000 10.698 17
PointGroup0.778 201.000 10.900 310.798 210.715 290.863 170.493 260.706 240.895 50.569 340.701 80.576 170.639 221.000 10.880 160.851 240.719 250.997 250.709 15
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]
PE0.776 211.000 10.900 320.860 100.728 260.869 130.400 340.857 60.774 210.568 350.701 90.602 160.646 190.933 290.843 220.890 50.691 320.997 250.709 14
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
DD-UNet+Group0.764 221.000 10.897 340.837 130.753 200.830 260.459 300.824 110.699 310.629 240.653 150.438 340.650 121.000 10.880 160.858 210.690 331.000 10.650 21
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-instance0.762 231.000 10.923 240.765 290.785 100.905 60.600 130.655 290.646 360.683 150.647 180.530 250.650 121.000 10.824 240.830 300.693 310.944 380.644 22
Dyco3Dcopyleft0.761 241.000 10.935 180.893 40.752 220.863 180.600 130.588 350.742 270.641 210.633 210.546 210.550 320.857 330.789 330.853 230.762 160.987 320.699 16
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance0.742 251.000 10.923 240.785 230.745 240.867 140.557 190.578 380.729 280.670 180.644 190.488 290.577 311.000 10.794 310.830 300.620 401.000 10.550 34
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg0.739 261.000 10.899 330.759 320.753 210.823 280.282 380.691 270.658 340.582 330.594 260.547 200.628 231.000 10.795 300.868 160.728 231.000 10.692 18
3D-MPA0.737 271.000 10.933 190.785 230.794 90.831 250.279 400.588 350.695 320.616 250.559 320.556 180.650 121.000 10.809 280.875 110.696 291.000 10.608 31
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML0.731 281.000 10.992 40.779 280.609 390.746 370.308 370.867 50.601 400.607 270.539 350.519 270.550 321.000 10.824 240.869 150.729 221.000 10.616 27
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS0.725 291.000 10.885 370.653 420.657 360.801 310.576 170.695 260.828 140.698 130.534 360.457 330.500 390.857 330.831 230.841 270.627 391.000 10.619 26
SSEN0.724 301.000 10.926 220.781 270.661 340.845 220.596 160.529 400.764 260.653 200.489 410.461 320.500 390.859 320.765 340.872 130.761 171.000 10.577 32
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF0.718 311.000 10.945 160.901 30.754 190.817 300.460 280.700 250.772 220.688 140.568 300.000 510.500 390.981 260.606 420.872 120.740 201.000 10.614 28
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Sparse R-CNN0.714 321.000 10.926 230.694 370.699 320.890 100.636 110.516 410.693 330.743 60.588 270.369 370.601 240.594 440.800 290.886 70.676 340.986 330.546 35
SALoss-ResNet0.695 331.000 10.855 390.579 460.589 410.735 400.484 270.588 350.856 120.634 230.571 290.298 380.500 391.000 10.824 240.818 330.702 280.935 420.545 36
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-inst0.693 341.000 10.852 400.655 410.616 380.788 320.334 360.763 190.771 230.457 460.555 330.652 120.518 360.857 330.765 340.732 460.631 370.944 380.577 33
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-SCS0.688 351.000 10.913 280.730 350.737 250.743 390.442 310.855 80.655 350.546 370.546 340.263 400.508 380.889 310.568 430.771 430.705 270.889 450.625 25
3D-BoNet0.687 361.000 10.887 360.836 150.587 420.643 490.550 220.620 310.724 290.522 410.501 390.243 410.512 371.000 10.751 360.807 360.661 360.909 440.612 30
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
PCJC0.684 371.000 10.895 350.757 330.659 350.862 190.189 470.739 210.606 390.712 120.581 280.515 280.650 120.857 330.357 480.785 410.631 380.889 450.635 24
SPG_WSIS0.678 381.000 10.880 380.836 150.701 310.727 410.273 420.607 330.706 300.541 390.515 380.174 430.600 250.857 330.716 370.846 260.711 261.000 10.506 39
One_Thing_One_Clickpermissive0.675 391.000 10.823 420.782 250.621 370.766 340.211 440.736 220.560 430.586 310.522 370.636 150.453 430.641 430.853 190.850 250.694 300.997 250.411 43
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_inspermissive0.637 401.000 10.923 260.593 450.561 430.746 380.143 490.504 420.766 250.485 440.442 420.372 360.530 350.714 400.815 270.775 420.673 351.000 10.431 42
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASCpermissive0.615 410.711 470.802 430.540 470.757 180.777 330.029 500.577 390.588 420.521 420.600 240.436 350.534 340.697 410.616 410.838 280.526 420.980 350.534 37
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone0.605 421.000 10.909 290.764 300.603 400.704 430.415 330.301 470.548 440.461 450.394 430.267 390.386 450.857 330.649 400.817 340.504 430.959 360.356 46
3D-SISpermissive0.558 431.000 10.773 440.614 440.503 450.691 450.200 450.412 430.498 470.546 380.311 480.103 470.600 250.857 330.382 450.799 380.445 490.938 410.371 44
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.544 440.500 500.655 500.661 400.663 330.765 350.432 320.214 490.612 380.584 320.499 400.204 420.286 490.429 470.655 390.650 510.539 410.950 370.499 40
Hier3Dcopyleft0.540 451.000 10.727 450.626 430.467 480.693 440.200 450.412 430.480 480.528 400.318 470.077 500.600 250.688 420.382 450.768 440.472 450.941 400.350 47
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class0.497 460.250 520.902 300.689 380.540 440.747 360.276 410.610 320.268 510.489 430.348 440.000 510.243 510.220 500.663 380.814 350.459 470.928 430.496 41
tmp0.474 471.000 10.727 450.433 500.481 470.673 470.022 520.380 450.517 460.436 480.338 460.128 450.343 470.429 470.291 500.728 470.473 440.833 480.300 49
SemRegionNet-20cls0.470 481.000 10.727 450.447 490.481 460.678 460.024 510.380 450.518 450.440 470.339 450.128 450.350 460.429 470.212 510.711 480.465 460.833 480.290 50
ASIS0.422 490.333 510.707 480.676 390.401 490.650 480.350 350.177 500.594 410.376 490.202 490.077 490.404 440.571 450.197 520.674 500.447 480.500 510.260 51
3D-BEVIS0.401 500.667 480.687 490.419 510.137 520.587 500.188 480.235 480.359 500.211 510.093 520.080 480.311 480.571 450.382 450.754 450.300 510.874 470.357 45
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.390 510.556 490.636 510.493 480.353 500.539 510.271 430.160 510.450 490.359 500.178 500.146 440.250 500.143 510.347 490.698 490.436 500.667 500.331 48
MaskRCNN 2d->3d Proj0.261 520.903 460.081 520.008 520.233 510.175 520.280 390.106 520.150 520.203 520.175 510.480 300.218 520.143 510.542 440.404 520.153 520.393 520.049 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 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
sort bysort bysort bysort bysort bysort bysort bysort bysort bysorted 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