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 iouwallchairfloortabledoorcouchcabinetshelfdeskoffice chairbedpillowsinkpicturewindowtoiletbookshelfmonitorcurtainbookarmchaircoffee tableboxrefrigeratorlampkitchen cabinettowelclothestvnightstandcounterdresserstoolcushionplantceilingbathtubend tabledining tablekeyboardbagbackpacktoilet paperprintertv standwhiteboardblanketshower curtaintrash canclosetstairsmicrowavestoveshoecomputer towerbottlebinottomanbenchboardwashing machinemirrorcopierbasketsofa chairfile cabinetfanlaptopshowerpaperpersonpaper towel dispenserovenblindsrackplateblackboardpianosuitcaserailradiatorrecycling bincontainerwardrobesoap dispensertelephonebucketclockstandlightlaundry basketpipeclothes dryerguitartoilet paper holderseatspeakercolumnbicycleladderbathroom stallshower wallcupjacketstorage bincoffee makerdishwasherpaper towel rollmachinematwindowsillbartoasterbulletin boardironing boardfireplacesoap dishkitchen counterdoorframetoilet paper dispensermini fridgefire extinguisherballhatshower curtain rodwater coolerpaper cuttertrayshower doorpillarledgetoaster ovenmousetoilet seat cover dispenserfurniturecartstorage containerscaletissue boxlight switchcratepower outletdecorationsignprojectorcloset doorvacuum cleanercandleplungerstuffed animalheadphonesdish rackbroomguitar caserange hooddustpanhair dryerwater bottlehandicap barpurseventshower floorwater pitchermailboxbowlpaper bagalarm clockmusic standprojector screendividerlaundry detergentbathroom counterobjectbathroom vanitycloset walllaundry hamperbathroom stall doorceiling lighttrash bindumbbellstair railtubebathroom cabinetcd casecloset rodcoffee kettlestructureshower headkeyboard pianocase of water bottlescoat rackstorage organizerfolded chairfire alarmpower stripcalendarposterpotted plantluggagemattress
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 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 by
CeCo0.340 10.551 10.247 10.181 10.784 10.661 20.939 10.564 10.624 10.721 10.484 10.429 10.575 10.027 40.774 10.503 10.753 10.242 10.656 10.945 10.534 10.865 10.860 10.177 40.616 20.400 10.818 10.579 10.615 10.367 10.408 10.726 20.633 10.162 10.360 10.619 10.000 10.828 10.873 10.924 10.109 20.083 20.564 10.057 40.475 20.266 10.781 10.767 10.257 10.100 20.825 10.663 10.048 40.620 30.551 10.595 20.532 10.692 20.246 10.000 30.213 10.615 10.861 10.376 10.900 10.000 10.102 40.660 10.321 20.547 10.226 10.000 10.311 10.742 10.011 20.006 20.000 10.000 20.546 40.824 10.345 20.665 10.450 10.435 10.683 10.411 10.338 10.000 30.000 10.030 40.000 10.068 30.892 10.000 10.063 20.000 40.257 10.304 30.387 20.079 20.228 10.190 10.000 40.586 10.347 10.133 20.000 20.037 10.377 30.000 10.384 10.006 30.003 20.421 10.410 10.643 10.171 20.121 20.142 30.000 10.510 30.447 10.474 20.000 10.000 40.286 10.083 10.000 30.000 10.603 10.096 10.063 10.000 20.000 10.000 10.898 10.000 10.429 10.000 10.400 10.550 10.000 10.633 10.000 10.000 10.377 10.000 40.916 10.000 20.000 10.000 10.000 20.000 10.102 40.499 20.296 10.463 10.089 20.304 10.740 10.401 40.010 10.000 10.560 10.000 10.000 20.709 10.652 10.000 20.000 10.000 10.143 20.000 20.000 10.609 10.000 1
: Understanding Imbalanced Semantic Segmentation Through Neural Collapse.
LGroundpermissive0.272 20.485 20.184 20.106 20.778 20.676 10.932 20.479 40.572 20.718 20.399 20.265 20.453 30.085 20.745 20.446 20.726 20.232 30.622 20.901 20.512 30.826 20.786 30.178 30.549 30.277 20.659 30.381 20.518 20.295 40.323 20.777 10.599 20.028 30.321 20.363 30.000 10.708 30.858 20.746 30.063 30.022 30.457 20.077 20.476 10.243 20.402 20.397 40.233 20.077 40.720 40.610 30.103 10.629 20.437 40.626 10.446 20.702 10.190 20.005 10.058 30.322 20.702 30.244 20.768 20.000 10.134 30.552 20.279 30.395 20.147 30.000 10.207 20.612 20.000 30.000 30.000 10.000 20.658 20.566 20.323 30.525 40.229 30.179 20.467 40.154 30.000 20.002 10.000 10.051 10.000 10.127 10.703 20.000 10.000 30.216 10.112 40.358 20.547 10.187 10.092 30.156 40.055 30.296 20.252 20.143 10.000 20.014 20.398 20.000 10.028 30.173 10.000 40.265 30.348 20.415 40.179 10.019 30.218 10.000 10.597 20.274 40.565 10.000 10.012 30.000 20.039 30.022 20.000 10.117 20.000 20.000 20.000 20.000 10.000 10.324 30.000 10.384 20.000 10.000 20.251 40.000 10.566 20.000 10.000 10.066 30.404 10.886 30.199 10.000 10.000 10.059 10.000 10.136 10.540 10.127 40.295 20.085 30.143 40.514 20.413 30.000 30.000 10.498 20.000 10.000 20.000 20.623 20.000 20.000 10.000 10.132 30.000 20.000 10.000 20.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
CSC-Pretrainpermissive0.249 40.455 40.171 30.079 40.766 40.659 30.930 40.494 20.542 40.700 40.314 40.215 40.430 40.121 10.697 40.441 30.683 30.235 20.609 40.895 30.476 40.816 30.770 40.186 20.634 10.216 40.734 20.340 30.471 30.307 30.293 40.591 40.542 40.076 20.205 40.464 20.000 10.484 40.832 40.766 20.052 40.000 40.413 30.059 30.418 30.222 30.318 40.609 30.206 40.112 10.743 20.625 20.076 20.579 40.548 20.590 30.371 30.552 40.081 30.003 20.142 20.201 40.638 40.233 30.686 40.000 10.142 20.444 40.375 10.247 40.198 20.000 10.128 40.454 40.019 10.097 10.000 10.000 20.553 30.557 30.373 10.545 30.164 40.014 40.547 30.174 20.000 20.002 10.000 10.037 20.000 10.063 40.664 40.000 10.000 30.130 20.170 20.152 40.335 40.079 20.110 20.175 20.098 20.175 40.166 30.045 40.207 10.014 20.465 10.000 10.001 40.001 40.046 10.299 20.327 30.537 30.033 30.012 40.186 20.000 10.205 40.377 20.463 30.000 10.058 20.000 20.055 20.041 10.000 10.105 30.000 20.000 20.000 20.000 10.000 10.398 20.000 10.308 40.000 10.000 20.319 20.000 10.543 30.000 10.000 10.062 40.004 30.862 40.000 20.000 10.000 10.000 20.000 10.123 20.316 30.225 20.250 30.094 10.180 30.332 30.441 20.000 30.000 10.310 40.000 10.000 20.000 20.592 30.000 20.000 10.000 10.203 10.000 20.000 10.000 20.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 30.463 30.154 40.102 30.771 30.650 40.932 20.483 30.571 30.710 30.331 30.250 30.492 20.044 30.703 30.419 40.606 40.227 40.621 30.865 40.531 20.771 40.813 20.291 10.484 40.242 30.612 40.282 40.440 40.351 20.299 30.622 30.593 30.027 40.293 30.310 40.000 10.757 20.858 20.737 40.150 10.164 10.368 40.084 10.381 40.142 40.357 30.720 20.214 30.092 30.724 30.596 40.056 30.655 10.525 30.581 40.352 40.594 30.056 40.000 30.014 40.224 30.772 20.205 40.720 30.000 10.159 10.531 30.163 40.294 30.136 40.000 10.169 30.589 30.000 30.000 30.000 10.002 10.663 10.466 40.265 40.582 20.337 20.016 30.559 20.084 40.000 20.000 30.000 10.036 30.000 10.125 20.670 30.000 10.102 10.071 30.164 30.406 10.386 30.046 40.068 40.159 30.117 10.284 30.111 40.094 30.000 20.000 40.197 40.000 10.044 20.013 20.002 30.228 40.307 40.588 20.025 40.545 10.134 40.000 10.655 10.302 30.282 40.000 10.060 10.000 20.035 40.000 30.000 10.097 40.000 20.000 20.005 10.000 10.000 10.096 40.000 10.334 30.000 10.000 20.274 30.000 10.513 40.000 10.000 10.280 20.194 20.897 20.000 20.000 10.000 10.000 20.000 10.108 30.279 40.189 30.141 40.059 40.272 20.307 40.445 10.003 20.000 10.353 30.000 10.026 10.000 20.581 40.001 10.000 10.000 10.093 40.002 10.000 10.000 20.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


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




Method Infoavg aphead apcommon aptail apchairtabledoorcouchcabinetshelfdeskoffice chairbedpillowsinkpicturewindowtoiletbookshelfmonitorcurtainbookarmchaircoffee tableboxrefrigeratorlampkitchen cabinettowelclothestvnightstandcounterdresserstoolcushionplantceilingbathtubend tabledining tablekeyboardbagbackpacktoilet paperprintertv standwhiteboardblanketshower curtaintrash canclosetstairsmicrowavestoveshoecomputer towerbottlebinottomanbenchboardwashing machinemirrorcopierbasketsofa chairfile cabinetfanlaptopshowerpaperpersonpaper towel dispenserovenblindsrackplateblackboardpianosuitcaserailradiatorrecycling bincontainerwardrobesoap dispensertelephonebucketclockstandlightlaundry basketpipeclothes dryerguitartoilet paper holderseatspeakercolumnbicycleladderbathroom stallshower wallcupjacketstorage bincoffee makerdishwasherpaper towel rollmachinematwindowsillbartoasterbulletin boardironing boardfireplacesoap dishkitchen counterdoorframetoilet paper dispensermini fridgefire extinguisherballhatshower curtain rodwater coolerpaper cuttertrayshower doorpillarledgetoaster ovenmousetoilet seat cover dispenserfurniturecartstorage containerscaletissue boxlight switchcratepower outletdecorationsignprojectorcloset doorvacuum cleanercandleplungerstuffed animalheadphonesdish rackbroomguitar caserange hooddustpanhair dryerwater bottlehandicap barpurseventshower floorwater pitchermailboxbowlpaper bagalarm clockmusic standprojector screendividerlaundry detergentbathroom counterobjectbathroom vanitycloset walllaundry hamperbathroom stall doorceiling lighttrash bindumbbellstair railtubebathroom cabinetcd casecloset rodcoffee kettlestructureshower headkeyboard pianocase of water bottlescoat rackstorage organizerfolded chairfire alarmpower stripcalendarposterpotted plantluggagemattress
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 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 by
Mask3D Scannet2000.278 10.383 10.263 10.168 10.661 10.465 10.572 10.665 20.391 10.121 30.304 10.015 10.647 10.349 10.474 10.489 10.321 10.816 40.351 20.722 10.402 30.195 10.515 20.082 10.795 10.215 10.396 10.377 10.082 30.724 10.586 10.015 10.277 10.377 40.201 10.475 10.572 10.778 20.089 10.759 10.556 10.068 10.506 10.467 10.323 20.778 10.427 10.027 10.789 10.744 10.003 10.570 10.561 10.337 10.265 10.711 10.258 10.031 10.569 10.311 10.441 10.179 11.000 10.000 10.233 10.411 10.283 10.380 10.667 10.016 10.048 30.418 10.139 10.173 10.000 10.086 10.014 20.500 10.384 10.497 10.044 20.032 10.752 10.287 10.003 10.000 10.007 10.208 10.000 10.001 10.349 10.008 10.014 10.509 10.500 10.323 10.023 10.176 10.107 10.105 20.000 10.605 10.378 10.016 10.000 10.400 10.192 10.000 10.048 10.037 10.000 10.275 10.119 10.810 10.258 10.006 20.083 40.000 10.568 10.377 20.708 10.000 10.005 10.147 10.014 10.000 10.556 10.085 10.325 10.500 10.083 10.004 10.000 10.590 10.000 10.365 10.000 10.116 10.491 10.000 10.626 10.000 10.000 10.579 10.391 10.050 30.000 10.028 10.000 10.222 10.000 10.063 10.302 10.356 10.149 30.573 10.415 10.013 40.002 30.004 10.000 10.005 30.000 10.000 10.444 10.514 10.000 10.028 10.000 10.156 10.267 10.000 11.000 10.000 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
Minkowski 34D Inst.permissive0.130 30.246 30.083 30.043 40.547 40.236 30.415 30.672 10.141 40.133 20.067 30.000 20.521 20.114 40.238 40.289 20.232 30.883 10.182 40.373 40.486 10.076 30.488 30.022 30.529 30.199 40.110 30.217 30.100 10.460 40.319 30.000 20.025 40.472 10.000 20.394 20.210 30.537 30.004 30.000 20.083 40.000 40.299 30.061 40.201 40.761 30.084 40.008 20.720 20.557 40.000 20.317 40.280 20.094 40.020 40.564 40.000 30.000 20.400 20.048 30.259 30.101 31.000 10.000 10.190 20.142 40.094 40.137 30.089 30.000 20.101 10.355 40.000 20.000 20.000 10.000 20.000 30.444 20.082 40.384 20.000 40.000 20.334 40.004 40.000 20.000 10.000 20.041 30.000 10.000 20.026 40.000 20.000 20.000 30.000 20.082 40.022 20.000 40.021 30.088 30.000 10.241 40.033 40.000 20.000 10.067 20.000 40.000 10.000 20.000 20.000 10.000 30.026 30.262 20.016 30.000 30.278 10.000 10.500 30.394 10.028 40.000 10.000 20.000 20.000 20.000 10.000 20.019 30.000 20.000 20.000 20.000 20.000 10.156 40.000 10.032 40.000 10.000 20.194 40.000 10.248 40.000 10.000 10.099 30.019 30.308 10.000 10.000 20.000 10.000 20.000 10.007 30.122 20.000 20.175 20.063 20.000 30.271 10.000 40.000 20.000 10.000 40.000 10.000 10.000 20.278 20.000 10.000 20.000 10.111 20.000 20.000 10.000 20.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.123 40.223 40.082 40.046 30.564 30.152 40.394 40.578 40.235 20.116 40.034 40.000 20.348 40.119 30.297 20.285 30.202 40.838 30.323 30.407 30.184 40.037 40.516 10.013 40.424 40.214 20.093 40.105 40.078 40.542 30.250 40.000 20.064 30.444 20.000 20.224 40.231 20.537 30.001 40.000 20.126 30.004 20.308 20.193 20.244 30.343 40.228 20.000 40.441 30.588 20.000 20.338 30.275 30.189 30.030 30.600 30.000 30.000 20.378 30.000 40.108 40.098 41.000 10.000 10.096 40.172 30.144 20.011 40.125 20.000 20.000 40.376 30.000 20.000 20.000 10.000 20.000 30.042 40.141 30.377 30.051 10.000 20.483 20.017 30.000 20.000 10.000 20.022 40.000 10.000 20.065 20.000 20.000 20.000 30.000 20.094 30.000 40.042 20.000 40.064 40.000 10.259 30.089 30.000 20.000 10.000 30.022 30.000 10.000 20.000 20.000 10.000 30.018 40.111 40.000 40.000 30.278 10.000 10.444 40.333 30.333 30.000 10.000 20.000 20.000 20.000 10.000 20.000 40.000 20.000 20.000 20.000 20.000 10.267 30.000 10.184 30.000 10.000 20.211 30.000 10.378 20.000 10.000 10.063 40.000 40.275 20.000 10.000 20.000 10.000 20.000 10.007 40.105 30.000 20.032 40.045 30.198 20.171 30.028 10.000 20.000 10.006 20.000 10.000 10.000 20.278 20.000 10.000 20.000 10.044 30.000 20.000 10.000 20.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.154 20.275 20.108 20.060 20.573 20.381 20.434 20.654 30.190 30.141 10.097 20.000 20.503 30.180 20.252 30.242 40.242 20.881 20.448 10.494 20.429 20.078 20.364 40.024 20.654 20.213 30.222 20.239 20.099 20.616 20.363 20.000 20.092 20.444 20.000 20.383 30.209 40.815 10.030 20.000 20.166 20.002 30.295 40.099 30.364 10.778 10.177 30.001 30.427 40.585 30.000 20.470 20.268 40.205 20.045 20.642 20.007 20.000 20.333 40.148 20.407 20.130 21.000 10.000 10.156 30.189 20.097 30.169 20.000 40.000 20.056 20.400 20.000 20.000 20.000 10.000 20.556 10.278 30.203 20.323 40.019 30.000 20.402 30.026 20.000 20.000 10.000 20.044 20.000 10.000 20.037 30.000 20.000 20.181 20.000 20.127 20.006 30.028 30.023 20.115 10.000 10.327 20.267 20.000 20.000 10.000 30.028 20.000 10.000 20.000 20.000 10.003 20.048 20.135 30.222 20.089 10.278 10.000 10.514 20.333 30.611 20.000 10.000 20.000 20.000 20.000 10.000 20.037 20.000 20.000 20.000 20.000 20.000 10.322 20.000 10.209 20.000 10.000 20.278 20.000 10.302 30.000 10.000 10.143 20.148 20.000 40.000 10.000 20.000 10.000 20.000 10.015 20.064 40.000 20.272 10.031 40.000 30.257 20.028 10.000 20.000 10.041 10.000 10.000 10.000 20.222 40.000 10.000 20.000 10.000 40.000 20.000 10.000 20.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.


ScanNet Benchmark

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mix3Dpermissive0.781 10.964 10.855 10.843 100.781 10.858 70.575 30.831 180.685 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 70.840 110.757 60.853 90.580 10.848 130.709 20.643 110.958 90.587 70.295 220.753 140.884 120.758 100.815 50.725 20.927 160.867 90.743 5
OccuSeg+Semantic0.764 20.758 450.796 190.839 120.746 110.907 10.562 50.850 120.680 90.672 50.978 20.610 10.335 80.777 40.819 320.847 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 10.640 150.958 90.592 40.217 570.762 100.888 90.758 100.813 60.726 10.932 140.868 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 60.793 220.802 280.689 270.825 300.556 60.867 80.681 80.602 290.960 70.555 160.365 30.779 30.859 170.747 130.795 170.717 40.917 190.856 170.764 2
PointTransformerV20.752 50.742 520.809 130.872 10.758 50.860 60.552 70.891 50.610 280.687 20.960 70.559 140.304 190.766 80.926 20.767 70.797 130.644 210.942 50.876 70.722 14
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer0.749 70.793 310.790 230.807 240.750 100.856 80.524 160.881 60.588 390.642 140.977 40.591 50.274 320.781 20.929 10.804 30.796 140.642 220.947 30.885 20.715 17
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 70.909 40.818 90.811 210.752 80.839 180.485 310.842 150.673 100.644 100.957 120.528 240.305 180.773 60.859 170.788 40.818 40.693 70.916 200.856 170.723 13
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 90.623 760.804 150.859 30.745 120.824 320.501 230.912 20.690 60.685 30.956 130.567 110.320 130.768 70.918 30.720 210.802 90.676 110.921 170.881 40.779 1
StratifiedFormerpermissive0.747 100.901 70.803 160.845 80.757 60.846 140.512 190.825 210.696 50.645 90.956 130.576 90.262 430.744 180.861 160.742 140.770 300.705 50.899 310.860 140.734 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
VMNetpermissive0.746 110.870 120.838 20.858 40.729 170.850 120.501 230.874 70.587 400.658 70.956 130.564 120.299 200.765 90.900 50.716 240.812 70.631 270.939 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)
Virtual MVFusion0.746 110.771 390.819 70.848 60.702 250.865 50.397 680.899 30.699 30.664 60.948 390.588 60.330 90.746 170.851 240.764 80.796 140.704 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
Retro-FPN0.744 130.842 190.800 170.767 400.740 130.836 220.541 100.914 10.672 110.626 180.958 90.552 170.272 340.777 40.886 110.696 310.801 100.674 130.941 60.858 150.717 15
EQ-Net0.743 140.620 770.799 180.849 50.730 160.822 340.493 290.897 40.664 120.681 40.955 170.562 130.378 10.760 110.903 40.738 150.801 100.673 140.907 240.877 50.745 3
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet0.742 150.816 260.806 140.807 240.752 80.828 280.575 30.839 170.699 30.637 160.954 220.520 260.320 130.755 130.834 280.760 90.772 270.676 110.915 210.862 120.717 15
SAT0.742 150.860 140.765 340.819 160.769 30.848 130.533 120.829 190.663 130.631 170.955 170.586 80.274 320.753 140.896 60.729 160.760 360.666 160.921 170.855 190.733 7
LargeKernel3D0.739 170.909 40.820 60.806 260.740 130.852 100.545 90.826 200.594 380.643 110.955 170.541 190.263 420.723 200.858 190.775 60.767 310.678 100.933 120.848 230.694 23
MinkowskiNetpermissive0.736 180.859 150.818 90.832 130.709 220.840 170.521 180.853 110.660 150.643 110.951 300.544 180.286 270.731 190.893 70.675 380.772 270.683 90.874 490.852 210.727 10
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 190.890 80.837 30.864 20.726 180.873 20.530 150.824 220.489 700.647 80.978 20.609 20.336 70.624 360.733 450.758 100.776 250.570 520.949 20.877 50.728 8
SparseConvNet0.725 200.647 730.821 50.846 70.721 200.869 30.533 120.754 410.603 340.614 220.955 170.572 100.325 110.710 210.870 130.724 190.823 20.628 280.934 110.865 110.683 25
PointTransformer++0.725 200.727 590.811 120.819 160.765 40.841 160.502 220.814 270.621 240.623 190.955 170.556 150.284 280.620 370.866 140.781 50.757 390.648 190.932 140.862 120.709 18
MatchingNet0.724 220.812 280.812 110.810 220.735 150.834 230.495 280.860 100.572 460.602 290.954 220.512 280.280 290.757 120.845 260.725 180.780 230.606 380.937 90.851 220.700 21
INS-Conv-semantic0.717 230.751 480.759 370.812 200.704 240.868 40.537 110.842 150.609 300.608 250.953 250.534 200.293 230.616 380.864 150.719 230.793 180.640 230.933 120.845 270.663 30
PointMetaBase0.714 240.835 200.785 250.821 140.684 290.846 140.531 140.865 90.614 250.596 320.953 250.500 310.246 490.674 220.888 90.692 320.764 330.624 290.849 630.844 280.675 27
contrastBoundarypermissive0.705 250.769 420.775 300.809 230.687 280.820 370.439 550.812 280.661 140.591 350.945 480.515 270.171 750.633 330.856 200.720 210.796 140.668 150.889 380.847 250.689 24
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
RFCR0.702 260.889 90.745 460.813 190.672 310.818 410.493 290.815 250.623 220.610 230.947 410.470 400.249 480.594 410.848 250.705 280.779 240.646 200.892 360.823 350.611 45
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 Click0.701 270.825 240.796 190.723 470.716 210.832 240.433 570.816 230.634 200.609 240.969 60.418 650.344 50.559 520.833 290.715 250.808 80.560 560.902 280.847 250.680 26
JSENetpermissive0.699 280.881 110.762 350.821 140.667 320.800 530.522 170.792 330.613 260.607 260.935 670.492 330.205 620.576 460.853 220.691 330.758 380.652 180.872 520.828 320.649 34
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-IIpermissive0.696 290.704 630.790 230.787 320.709 220.837 200.459 400.815 250.543 550.615 210.956 130.529 220.250 460.551 570.790 370.703 290.799 120.619 330.908 230.848 230.700 21
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
One-Thing-One-Click0.693 300.743 510.794 210.655 700.684 290.822 340.497 270.719 510.622 230.617 200.977 40.447 520.339 60.750 160.664 600.703 290.790 200.596 420.946 40.855 190.647 35
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Feature_GeometricNetpermissive0.690 310.884 100.754 410.795 310.647 370.818 410.422 590.802 310.612 270.604 270.945 480.462 430.189 700.563 510.853 220.726 170.765 320.632 260.904 260.821 380.606 49
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 320.704 630.741 500.754 440.656 330.829 260.501 230.741 460.609 300.548 420.950 340.522 250.371 20.633 330.756 400.715 250.771 290.623 300.861 590.814 400.658 31
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 330.866 130.748 430.819 160.645 390.794 560.450 450.802 310.587 400.604 270.945 480.464 420.201 650.554 540.840 270.723 200.732 480.602 400.907 240.822 370.603 52
KP-FCNN0.684 340.847 180.758 390.784 340.647 370.814 440.473 330.772 360.605 320.594 340.935 670.450 500.181 730.587 420.805 350.690 340.785 220.614 340.882 420.819 390.632 40
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 340.728 580.757 400.776 360.690 260.804 510.464 380.816 230.577 450.587 360.945 480.508 300.276 310.671 230.710 500.663 430.750 420.589 470.881 430.832 310.653 33
Superpoint Network0.683 360.851 170.728 540.800 300.653 350.806 490.468 350.804 290.572 460.602 290.946 450.453 490.239 520.519 630.822 300.689 360.762 350.595 440.895 340.827 330.630 41
PointContrast_LA_SEM0.683 360.757 460.784 260.786 330.639 410.824 320.408 620.775 350.604 330.541 440.934 710.532 210.269 380.552 550.777 380.645 530.793 180.640 230.913 220.824 340.671 28
VI-PointConv0.676 380.770 410.754 410.783 350.621 450.814 440.552 70.758 390.571 480.557 400.954 220.529 220.268 400.530 610.682 550.675 380.719 510.603 390.888 390.833 300.665 29
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 390.789 320.748 430.763 420.635 430.814 440.407 640.747 430.581 440.573 370.950 340.484 340.271 360.607 390.754 410.649 480.774 260.596 420.883 410.823 350.606 49
SALANet0.670 400.816 260.770 320.768 390.652 360.807 480.451 420.747 430.659 160.545 430.924 770.473 390.149 850.571 480.811 340.635 560.746 430.623 300.892 360.794 520.570 62
PointASNLpermissive0.666 410.703 650.781 280.751 460.655 340.830 250.471 340.769 370.474 730.537 460.951 300.475 380.279 300.635 310.698 540.675 380.751 410.553 610.816 700.806 440.703 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
PointConvpermissive0.666 410.781 340.759 370.699 550.644 400.822 340.475 320.779 340.564 510.504 600.953 250.428 590.203 640.586 440.754 410.661 440.753 400.588 480.902 280.813 420.642 36
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++permissive0.663 430.746 490.708 570.722 480.638 420.820 370.451 420.566 770.599 360.541 440.950 340.510 290.313 150.648 280.819 320.616 610.682 660.590 460.869 550.810 430.656 32
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 440.778 350.702 600.806 260.619 460.813 470.468 350.693 590.494 660.524 520.941 590.449 510.298 210.510 650.821 310.675 380.727 500.568 540.826 680.803 460.637 38
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 450.698 660.743 480.650 710.564 630.820 370.505 210.758 390.631 210.479 640.945 480.480 360.226 530.572 470.774 390.690 340.735 460.614 340.853 620.776 660.597 55
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 460.752 470.734 520.664 680.583 580.815 430.399 670.754 410.639 180.535 480.942 570.470 400.309 170.665 240.539 670.650 470.708 560.635 250.857 610.793 540.642 36
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 470.778 350.731 530.699 550.577 590.829 260.446 470.736 470.477 720.523 540.945 480.454 470.269 380.484 720.749 440.618 590.738 440.599 410.827 670.792 570.621 43
MVPNetpermissive0.641 480.831 210.715 550.671 650.590 540.781 620.394 690.679 610.642 170.553 410.937 640.462 430.256 440.649 270.406 800.626 570.691 630.666 160.877 450.792 570.608 48
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointConv-SFPN0.641 480.776 370.703 590.721 490.557 660.826 290.451 420.672 630.563 520.483 630.943 560.425 620.162 800.644 290.726 460.659 450.709 550.572 510.875 470.786 610.559 67
PointMRNet0.640 500.717 620.701 610.692 580.576 600.801 520.467 370.716 520.563 520.459 690.953 250.429 580.169 770.581 450.854 210.605 620.710 530.550 620.894 350.793 540.575 60
FPConvpermissive0.639 510.785 330.760 360.713 530.603 490.798 540.392 700.534 820.603 340.524 520.948 390.457 450.250 460.538 590.723 480.598 660.696 610.614 340.872 520.799 470.567 64
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 520.797 300.769 330.641 760.590 540.820 370.461 390.537 810.637 190.536 470.947 410.388 720.206 610.656 250.668 580.647 510.732 480.585 490.868 560.793 540.473 85
PointSPNet0.637 530.734 550.692 680.714 520.576 600.797 550.446 470.743 450.598 370.437 740.942 570.403 680.150 840.626 350.800 360.649 480.697 600.557 590.846 640.777 650.563 65
SConv0.636 540.830 220.697 640.752 450.572 620.780 640.445 490.716 520.529 580.530 490.951 300.446 530.170 760.507 670.666 590.636 550.682 660.541 670.886 400.799 470.594 56
Supervoxel-CNN0.635 550.656 710.711 560.719 500.613 470.757 730.444 520.765 380.534 570.566 380.928 750.478 370.272 340.636 300.531 690.664 420.645 760.508 740.864 580.792 570.611 45
joint point-basedpermissive0.634 560.614 780.778 290.667 670.633 440.825 300.420 600.804 290.467 750.561 390.951 300.494 320.291 240.566 490.458 750.579 720.764 330.559 580.838 650.814 400.598 54
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 570.731 560.688 710.675 620.591 530.784 610.444 520.565 780.610 280.492 610.949 370.456 460.254 450.587 420.706 510.599 650.665 720.612 370.868 560.791 600.579 59
PointNet2-SFPN0.631 580.771 390.692 680.672 630.524 700.837 200.440 540.706 570.538 560.446 710.944 540.421 640.219 560.552 550.751 430.591 680.737 450.543 660.901 300.768 680.557 68
APCF-Net0.631 580.742 520.687 730.672 630.557 660.792 590.408 620.665 640.545 540.508 570.952 290.428 590.186 710.634 320.702 520.620 580.706 570.555 600.873 500.798 490.581 58
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
3DSM_DMMF0.631 580.626 750.745 460.801 290.607 480.751 740.506 200.729 500.565 500.491 620.866 910.434 540.197 680.595 400.630 620.709 270.705 580.560 560.875 470.740 760.491 80
FusionAwareConv0.630 610.604 800.741 500.766 410.590 540.747 750.501 230.734 480.503 650.527 500.919 810.454 470.323 120.550 580.420 790.678 370.688 640.544 640.896 330.795 510.627 42
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 620.800 290.625 830.719 500.545 680.806 490.445 490.597 720.448 790.519 550.938 630.481 350.328 100.489 710.499 740.657 460.759 370.592 450.881 430.797 500.634 39
SegGroup_sempermissive0.627 630.818 250.747 450.701 540.602 500.764 700.385 740.629 690.490 680.508 570.931 740.409 670.201 650.564 500.725 470.618 590.692 620.539 680.873 500.794 520.548 71
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 640.830 220.694 660.757 430.563 640.772 680.448 460.647 670.520 600.509 560.949 370.431 570.191 690.496 690.614 630.647 510.672 700.535 700.876 460.783 620.571 61
HPEIN0.618 650.729 570.668 740.647 730.597 520.766 690.414 610.680 600.520 600.525 510.946 450.432 550.215 580.493 700.599 640.638 540.617 810.570 520.897 320.806 440.605 51
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-GCNpermissive0.610 660.858 160.772 310.489 880.532 690.792 590.404 660.643 680.570 490.507 590.935 670.414 660.046 940.510 650.702 520.602 640.705 580.549 630.859 600.773 670.534 74
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 670.760 440.667 750.649 720.521 710.793 570.457 410.648 660.528 590.434 760.947 410.401 690.153 830.454 740.721 490.648 500.717 520.536 690.904 260.765 690.485 81
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 680.634 740.743 480.697 570.601 510.781 620.437 560.585 750.493 670.446 710.933 720.394 700.011 960.654 260.661 610.603 630.733 470.526 710.832 660.761 710.480 82
LAP-D0.594 690.720 600.692 680.637 770.456 800.773 670.391 720.730 490.587 400.445 730.940 610.381 730.288 250.434 770.453 770.591 680.649 740.581 500.777 740.749 750.610 47
DPC0.592 700.720 600.700 620.602 810.480 760.762 720.380 750.713 550.585 430.437 740.940 610.369 750.288 250.434 770.509 730.590 700.639 790.567 550.772 750.755 730.592 57
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 710.766 430.659 780.683 600.470 790.740 770.387 730.620 710.490 680.476 650.922 790.355 780.245 500.511 640.511 720.571 730.643 770.493 780.872 520.762 700.600 53
ROSMRF0.580 720.772 380.707 580.681 610.563 640.764 700.362 770.515 830.465 760.465 680.936 660.427 610.207 600.438 750.577 650.536 760.675 690.486 790.723 810.779 630.524 76
SD-DETR0.576 730.746 490.609 870.445 920.517 720.643 880.366 760.714 540.456 770.468 670.870 900.432 550.264 410.558 530.674 560.586 710.688 640.482 800.739 790.733 780.537 73
SQN_0.1%0.569 740.676 680.696 650.657 690.497 730.779 650.424 580.548 790.515 620.376 810.902 880.422 630.357 40.379 810.456 760.596 670.659 730.544 640.685 840.665 890.556 69
TextureNetpermissive0.566 750.672 700.664 760.671 650.494 740.719 780.445 490.678 620.411 850.396 790.935 670.356 770.225 540.412 790.535 680.565 740.636 800.464 820.794 730.680 860.568 63
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
DVVNet0.562 760.648 720.700 620.770 380.586 570.687 820.333 810.650 650.514 630.475 660.906 850.359 760.223 550.340 830.442 780.422 870.668 710.501 750.708 820.779 630.534 74
Pointnet++ & Featurepermissive0.557 770.735 540.661 770.686 590.491 750.744 760.392 700.539 800.451 780.375 820.946 450.376 740.205 620.403 800.356 830.553 750.643 770.497 760.824 690.756 720.515 77
GMLPs0.538 780.495 880.693 670.647 730.471 780.793 570.300 840.477 840.505 640.358 830.903 870.327 810.081 910.472 730.529 700.448 850.710 530.509 720.746 770.737 770.554 70
PanopticFusion-label0.529 790.491 890.688 710.604 800.386 850.632 890.225 940.705 580.434 820.293 890.815 920.348 790.241 510.499 680.669 570.507 780.649 740.442 880.796 720.602 920.561 66
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_weak0.516 800.676 680.591 900.609 780.442 810.774 660.335 800.597 720.422 840.357 840.932 730.341 800.094 900.298 850.528 710.473 830.676 680.495 770.602 900.721 810.349 92
Online SegFusion0.515 810.607 790.644 810.579 830.434 820.630 900.353 780.628 700.440 800.410 770.762 950.307 830.167 780.520 620.403 810.516 770.565 840.447 860.678 850.701 830.514 78
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, FTSDF0.501 820.558 840.608 880.424 940.478 770.690 810.246 900.586 740.468 740.450 700.911 830.394 700.160 810.438 750.212 900.432 860.541 890.475 810.742 780.727 790.477 83
PCNN0.498 830.559 830.644 810.560 850.420 840.711 800.229 920.414 850.436 810.352 850.941 590.324 820.155 820.238 900.387 820.493 790.529 900.509 720.813 710.751 740.504 79
3DMV0.484 840.484 900.538 920.643 750.424 830.606 930.310 820.574 760.433 830.378 800.796 930.301 840.214 590.537 600.208 910.472 840.507 930.413 910.693 830.602 920.539 72
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 850.577 820.611 860.356 960.321 930.715 790.299 860.376 890.328 920.319 870.944 540.285 860.164 790.216 930.229 880.484 810.545 880.456 840.755 760.709 820.475 84
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 860.679 670.604 890.578 840.380 860.682 830.291 870.106 950.483 710.258 940.920 800.258 900.025 950.231 920.325 840.480 820.560 860.463 830.725 800.666 880.231 96
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 870.474 910.623 840.463 900.366 880.651 860.310 820.389 880.349 900.330 860.937 640.271 880.126 870.285 860.224 890.350 920.577 830.445 870.625 880.723 800.394 88
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
SurfaceConvPF0.442 880.505 870.622 850.380 950.342 910.654 850.227 930.397 870.367 880.276 910.924 770.240 910.198 670.359 820.262 860.366 890.581 820.435 890.640 870.668 870.398 87
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET20.442 880.548 850.548 910.597 820.363 890.628 910.300 840.292 900.374 870.307 880.881 890.268 890.186 710.238 900.204 920.407 880.506 940.449 850.667 860.620 910.462 86
Tangent Convolutionspermissive0.438 900.437 930.646 800.474 890.369 870.645 870.353 780.258 920.282 940.279 900.918 820.298 850.147 860.283 870.294 850.487 800.562 850.427 900.619 890.633 900.352 91
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 910.525 860.647 790.522 860.324 920.488 960.077 970.712 560.353 890.401 780.636 970.281 870.176 740.340 830.565 660.175 960.551 870.398 920.370 960.602 920.361 90
SimConv0.410 920.000 970.782 270.772 370.722 190.838 190.407 640.000 980.000 980.595 330.947 410.000 980.270 370.000 980.000 980.000 980.786 210.621 320.000 980.841 290.621 43
SPLAT Netcopyleft0.393 930.472 920.511 930.606 790.311 940.656 840.245 910.405 860.328 920.197 950.927 760.227 930.000 980.001 970.249 870.271 950.510 910.383 940.593 910.699 840.267 94
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+FTSDF0.383 940.297 950.491 940.432 930.358 900.612 920.274 880.116 940.411 850.265 920.904 860.229 920.079 920.250 880.185 930.320 930.510 910.385 930.548 920.597 950.394 88
PointNet++permissive0.339 950.584 810.478 950.458 910.256 960.360 970.250 890.247 930.278 950.261 930.677 960.183 940.117 880.212 940.145 950.364 900.346 970.232 970.548 920.523 960.252 95
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 960.353 940.290 970.278 970.166 970.553 940.169 960.286 910.147 960.148 970.908 840.182 950.064 930.023 960.018 970.354 910.363 950.345 950.546 940.685 850.278 93
ScanNetpermissive0.306 970.203 960.366 960.501 870.311 940.524 950.211 950.002 970.342 910.189 960.786 940.145 960.102 890.245 890.152 940.318 940.348 960.300 960.460 950.437 970.182 97
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 980.000 970.041 980.172 980.030 980.062 980.001 980.035 960.004 970.051 980.143 980.019 970.003 970.041 950.050 960.003 970.054 980.018 980.005 970.264 980.082 98


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




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PBNetpermissive0.573 10.926 20.575 80.619 10.472 10.736 40.239 30.487 210.383 20.459 20.506 50.533 60.585 40.767 70.404 60.717 20.559 30.969 10.381 4
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. Arxiv
Mask3D0.566 20.926 20.597 40.408 160.420 20.737 30.239 20.598 70.386 10.458 30.549 10.568 40.716 10.601 230.480 30.646 60.575 20.922 30.364 5
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
GraphCut0.552 31.000 10.611 30.438 120.392 50.714 50.139 60.598 80.327 40.389 50.510 40.598 10.427 190.754 100.463 40.761 10.588 10.903 60.329 12
SPFormerpermissive0.549 40.745 110.640 10.484 50.395 40.739 20.311 10.566 120.335 30.468 10.492 60.555 50.478 110.747 120.436 50.712 30.540 40.893 80.343 11
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
DKNet0.532 50.815 60.624 20.517 30.377 70.749 10.107 80.509 180.304 60.437 40.475 70.581 20.539 70.775 60.339 100.640 80.506 60.901 70.385 3
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
IPCA-Inst0.520 60.889 40.551 110.548 20.418 30.665 140.064 160.585 90.260 130.277 150.471 90.500 70.644 20.785 40.369 70.591 130.511 50.878 140.362 6
SoftGroup++0.513 70.704 170.578 70.398 170.363 110.704 60.061 170.647 40.297 110.378 80.537 20.343 90.614 30.828 30.295 150.710 50.505 70.875 160.394 1
SSTNetpermissive0.506 80.738 140.549 120.497 40.316 150.693 90.178 50.377 280.198 180.330 90.463 100.576 30.515 90.857 20.494 10.637 90.457 120.943 20.290 19
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SoftGrouppermissive0.504 90.667 230.579 60.372 200.381 60.694 80.072 130.677 20.303 70.387 60.531 30.319 130.582 50.754 90.318 110.643 70.492 80.907 50.388 2
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
OccuSeg+instance0.486 100.802 70.536 140.428 140.369 80.702 70.205 40.331 330.301 80.379 70.474 80.327 100.437 150.862 10.485 20.601 120.394 210.846 240.273 21
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
TopoSeg0.479 110.704 170.564 90.467 80.366 90.633 210.068 140.554 150.262 120.328 100.447 110.323 110.534 80.722 140.288 170.614 100.482 90.912 40.358 8
SSEC0.462 120.778 80.586 50.394 180.341 120.674 110.114 70.556 140.313 50.303 120.430 120.264 170.358 250.616 220.295 140.589 140.467 110.880 120.355 9
HAISpermissive0.457 130.704 170.561 100.457 90.364 100.673 120.046 240.547 160.194 190.308 110.426 130.288 150.454 140.711 150.262 200.563 210.434 150.889 100.344 10
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
DD-UNet+Group0.436 140.630 290.508 210.480 60.310 160.624 240.065 150.638 50.174 200.256 190.384 170.194 260.428 170.759 80.289 160.574 180.400 190.849 220.291 18
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
INS-Conv-instance0.435 150.716 160.495 230.355 220.331 130.689 100.102 100.394 270.208 170.280 130.395 160.250 190.544 60.741 130.309 130.536 270.391 220.842 270.258 25
Mask-Group0.434 160.778 80.516 180.471 70.330 140.658 150.029 260.526 170.249 140.256 180.400 150.309 140.384 230.296 410.368 80.575 170.425 160.877 150.362 7
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
Box2Mask0.433 170.741 120.463 280.433 130.283 180.625 230.103 90.298 370.125 270.260 170.424 140.322 120.472 120.701 170.363 90.711 40.309 350.882 110.272 23
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
RPGN0.428 180.630 290.508 200.367 210.249 250.658 160.016 330.673 30.131 260.234 220.383 180.270 160.434 160.748 110.274 190.609 110.406 180.842 260.267 24
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
DENet0.413 190.741 120.520 160.237 330.284 170.523 310.097 110.691 10.138 230.209 320.229 330.238 210.390 210.707 160.310 120.448 360.470 100.892 90.310 14
PointGroup0.407 200.639 280.496 220.415 150.243 270.645 200.021 310.570 110.114 280.211 300.359 200.217 240.428 180.660 190.256 210.562 220.341 270.860 190.291 17
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
CSC-Pretrained0.405 210.738 140.465 270.331 260.205 300.655 170.051 210.601 60.092 310.211 310.329 230.198 250.459 130.775 50.195 280.524 290.400 200.878 130.184 32
PE0.396 220.667 230.467 260.446 110.243 260.624 250.022 300.577 100.106 290.219 250.340 210.239 200.487 100.475 320.225 240.541 260.350 250.818 280.273 22
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
Dyco3Dcopyleft0.395 230.642 270.518 170.447 100.259 240.666 130.050 220.251 410.166 210.231 230.362 190.232 220.331 270.535 260.229 230.587 150.438 140.850 200.317 13
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OSIS0.392 240.778 80.530 150.220 350.278 190.567 280.083 120.330 340.299 90.270 160.310 260.143 310.260 310.624 210.277 180.568 200.361 230.865 180.301 15
SSEN0.384 250.852 50.494 240.192 360.226 290.648 190.022 290.398 260.299 100.277 140.317 250.231 230.194 380.514 290.196 260.586 160.444 130.843 250.184 31
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
PCJC0.375 260.704 170.542 130.284 300.197 320.649 180.006 370.426 220.138 240.242 200.304 270.183 290.388 220.629 200.141 380.546 250.344 260.738 340.283 20
SphereSeg0.357 270.651 260.411 300.345 230.264 230.630 220.059 180.289 390.212 150.240 210.336 220.158 300.305 280.557 240.159 340.455 350.341 280.726 360.294 16
3D-MPA0.355 280.457 400.484 250.299 280.277 200.591 270.047 230.332 310.212 160.217 260.278 280.193 270.413 200.410 350.195 270.574 190.352 240.849 210.213 29
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
NeuralBF0.353 290.593 310.511 190.375 190.264 220.597 260.008 350.332 320.160 220.229 240.274 300.000 510.206 350.678 180.155 350.485 310.422 170.816 290.254 26
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
RWSeg0.348 300.475 370.456 290.320 270.275 210.476 330.020 320.491 200.056 380.212 290.320 240.261 180.302 290.520 270.182 300.557 230.285 370.867 170.197 30
GICN0.341 310.580 320.371 320.344 240.198 310.469 340.052 200.564 130.093 300.212 280.212 350.127 330.347 260.537 250.206 250.525 280.329 300.729 350.241 27
One_Thing_One_Clickpermissive0.326 320.472 380.361 330.232 340.183 330.555 290.000 440.498 190.038 400.195 330.226 340.362 80.168 390.469 330.251 220.553 240.335 290.846 230.117 40
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Occipital-SCS0.320 330.679 220.352 340.334 250.229 280.436 350.025 270.412 250.058 360.161 390.240 320.085 350.262 300.496 310.187 290.467 330.328 310.775 300.231 28
Sparse R-CNN0.292 340.704 170.213 440.153 380.154 350.551 300.053 190.212 420.132 250.174 360.274 290.070 370.363 240.441 340.176 310.424 380.234 390.758 320.161 36
MTML0.282 350.577 330.380 310.182 370.107 410.430 360.001 410.422 230.057 370.179 350.162 380.070 380.229 330.511 300.161 320.491 300.313 320.650 410.162 34
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
SALoss-ResNet0.262 360.667 230.335 350.067 450.123 390.427 370.022 280.280 400.058 350.216 270.211 360.039 410.142 410.519 280.106 420.338 420.310 340.721 370.138 37
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
MASCpermissive0.254 370.463 390.249 430.113 390.167 340.412 390.000 430.374 290.073 320.173 370.243 310.130 320.228 340.368 370.160 330.356 400.208 400.711 380.136 38
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
3D-BoNet0.253 380.519 350.324 380.251 320.137 380.345 440.031 250.419 240.069 330.162 380.131 400.052 390.202 370.338 390.147 370.301 450.303 360.651 400.178 33
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
SPG_WSIS0.251 390.380 420.274 410.289 290.144 360.413 380.000 440.311 350.065 340.113 410.130 410.029 430.204 360.388 360.108 410.459 340.311 330.769 310.127 39
SegGroup_inspermissive0.246 400.556 340.335 360.062 470.115 400.490 320.000 440.297 380.018 440.186 340.142 390.083 360.233 320.216 430.153 360.469 320.251 380.744 330.083 43
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
PanopticFusion-inst0.214 410.250 460.330 370.275 310.103 420.228 500.000 440.345 300.024 420.088 430.203 370.186 280.167 400.367 380.125 390.221 480.112 500.666 390.162 35
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
UNet-backbone0.161 420.519 350.259 420.084 410.059 440.325 460.002 390.093 470.009 460.077 450.064 440.045 400.044 480.161 450.045 440.331 430.180 420.566 420.033 51
3D-SISpermissive0.161 420.407 410.155 480.068 440.043 480.346 430.001 400.134 440.005 470.088 420.106 430.037 420.135 430.321 400.028 470.339 410.116 490.466 450.093 42
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.158 440.356 430.173 460.113 400.140 370.359 400.012 340.023 490.039 390.134 400.123 420.008 470.089 440.149 460.117 400.221 470.128 470.563 430.094 41
Region-18class0.146 450.175 500.321 390.080 420.062 430.357 410.000 440.307 360.002 480.066 460.044 460.000 510.018 500.036 500.054 430.447 370.133 450.472 440.060 46
SemRegionNet-20cls0.121 460.296 450.203 450.071 430.058 450.349 420.000 440.150 430.019 430.054 470.034 480.017 460.052 460.042 490.013 500.209 490.183 410.371 460.057 47
3D-BEVIS0.117 470.250 460.308 400.020 510.009 520.269 490.006 380.008 500.029 410.037 500.014 510.003 490.036 490.147 470.042 450.381 390.118 480.362 470.069 45
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Hier3Dcopyleft0.117 470.222 480.161 470.054 490.027 490.289 470.000 440.124 450.001 500.079 440.061 450.027 440.141 420.240 420.005 510.310 440.129 460.153 510.081 44
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
tmp0.113 490.333 440.151 490.056 480.053 460.344 450.000 440.105 460.016 450.049 480.035 470.020 450.053 450.048 480.013 490.183 500.173 430.344 480.054 48
ASIS0.085 500.037 510.080 510.066 460.047 470.282 480.000 440.052 480.002 490.047 490.026 490.001 500.046 470.194 440.031 460.264 460.140 440.167 500.047 50
Sgpn_scannet0.049 510.023 520.134 500.031 500.013 510.144 510.006 360.008 510.000 510.028 510.017 500.003 480.009 520.000 510.021 480.122 510.095 510.175 490.054 49
MaskRCNN 2d->3d Proj0.022 520.185 490.000 520.000 520.015 500.000 520.000 420.006 520.000 510.010 520.006 520.107 340.012 510.000 510.002 520.027 520.004 520.022 520.001 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
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