The 3D semantic instance prediction task involves detecting and segmenting the object in an 3D scan mesh.

Evaluation and metrics

Similarly to the ScanNet benchmark in ScanNet200 our evaluation ranks all methods according to the average precision for each class. We report the mean average precision AP at overlap 0.25 (AP 25%), overlap 0.5 (AP 50%), and over overlaps in the range [0.5:0.95:0.05] (AP) for all 200 categories. Note that multiple predictions of the same ground truth instance are penalized as false positives.



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




Method Infoavg ap 50%head ap 50%common ap 50%tail ap 50%chairtabledoorcouchcabinetshelfdeskoffice 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
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 Scannet2000.314 10.480 10.264 10.171 10.000 40.497 20.728 10.845 20.348 10.273 10.692 10.039 10.853 10.566 10.707 10.490 40.540 10.817 40.443 30.887 10.650 10.320 10.758 20.069 30.664 40.611 10.522 10.449 10.162 10.645 20.515 40.000 10.689 10.500 10.143 10.944 10.758 11.000 10.126 10.125 10.744 10.024 10.500 20.359 20.097 40.667 30.040 40.188 11.000 10.863 10.167 11.000 10.804 10.649 10.262 10.833 10.345 10.004 10.865 10.178 10.528 20.496 11.000 10.000 10.227 20.741 10.143 20.543 10.250 10.000 10.052 30.661 10.083 10.000 10.000 10.083 10.250 20.500 10.363 10.679 20.000 30.000 10.784 10.342 10.000 10.000 10.000 10.147 10.000 10.000 10.333 10.000 10.111 10.250 20.500 10.397 10.362 10.538 10.109 10.119 30.000 10.192 40.200 20.028 10.167 10.400 10.468 10.000 10.000 10.143 10.000 10.328 10.377 10.677 10.250 10.017 20.500 10.000 10.500 20.333 21.000 10.000 10.000 10.429 10.000 10.000 10.000 10.333 10.036 10.000 10.000 10.000 10.000 10.050 40.000 10.519 10.000 10.063 10.533 20.000 10.667 20.000 10.000 10.938 10.126 20.042 30.000 10.000 10.000 11.000 10.000 10.049 10.366 10.342 10.265 30.121 10.629 10.500 30.150 10.000 10.000 10.167 10.000 10.000 10.050 10.500 10.000 10.000 10.000 10.400 10.000 10.000 11.000 10.000 1
LGround Inst.permissive0.246 20.413 20.170 20.130 20.754 10.541 10.682 30.903 10.264 30.164 20.234 20.000 20.681 30.452 20.464 40.541 30.399 21.000 10.637 10.772 20.588 30.190 20.589 40.081 10.857 10.426 30.373 20.318 20.135 20.690 10.653 20.000 10.159 30.500 10.000 20.581 20.387 31.000 10.046 20.000 20.402 20.003 40.455 40.196 30.571 11.000 10.270 20.003 40.530 40.748 30.000 20.744 30.575 30.511 20.112 20.815 20.067 20.000 20.400 20.167 20.667 10.241 21.000 10.000 10.208 30.660 20.125 30.317 20.000 40.000 10.100 20.561 40.000 20.000 10.000 10.000 21.000 10.500 10.344 20.568 40.167 20.000 10.706 20.068 20.000 10.000 10.000 10.063 20.000 10.000 10.056 30.000 10.000 20.500 10.000 20.143 40.017 30.125 20.097 20.164 10.000 10.582 20.400 10.000 20.000 20.000 30.083 30.000 10.000 10.000 20.000 10.025 20.156 20.533 30.250 10.200 10.500 10.000 11.000 10.333 21.000 10.000 10.000 10.000 20.000 10.000 10.000 10.333 10.000 20.000 10.000 10.000 10.000 10.400 20.000 10.364 20.000 10.000 20.500 30.000 10.511 30.000 10.000 10.286 20.333 10.000 40.000 10.000 10.000 10.000 20.000 10.034 20.111 40.000 20.333 20.031 40.000 30.750 10.125 20.000 10.000 10.151 20.000 10.000 10.000 20.500 10.000 10.000 10.000 10.000 40.000 10.000 10.000 20.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
CSC-Pretrain Inst.permissive0.209 30.361 40.157 30.085 30.700 30.248 40.634 40.776 40.322 20.135 40.103 40.000 20.524 40.364 40.618 20.592 20.381 40.997 20.589 20.747 30.340 40.109 40.768 10.059 40.702 30.448 20.188 40.149 40.091 40.636 30.573 30.000 10.246 20.500 10.000 20.450 40.405 20.667 30.006 40.000 20.356 30.007 20.506 10.420 10.340 20.667 30.294 10.004 30.571 30.748 20.000 21.000 10.573 40.502 30.094 30.807 30.000 30.000 20.400 20.000 40.278 40.228 31.000 10.000 10.115 40.432 30.198 10.050 40.125 20.000 10.000 40.573 30.000 20.000 10.000 10.000 20.000 30.125 40.312 30.610 30.221 10.000 10.667 30.050 30.000 10.000 10.000 10.032 40.000 10.000 10.083 20.000 10.000 20.000 30.000 20.220 30.000 40.125 20.000 40.111 40.000 10.667 10.200 20.000 20.000 20.000 30.110 20.000 10.000 10.000 20.000 10.000 30.053 40.500 40.000 40.000 30.500 10.000 10.500 20.333 20.500 30.000 10.000 10.000 20.000 10.000 10.000 10.000 40.000 20.000 10.000 10.000 10.000 10.600 10.000 10.364 20.000 10.000 20.750 10.000 10.833 10.000 10.000 10.143 40.000 40.396 10.000 10.000 10.000 10.000 20.000 10.021 40.221 30.000 20.093 40.055 30.451 20.677 20.125 20.000 10.000 10.028 30.000 10.000 10.000 20.500 10.000 10.000 10.000 10.050 30.000 10.000 10.000 20.000 1
Ji Hou, Benjamin Graham, Matthias Nie├čner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34D Inst.permissive0.203 40.369 30.134 40.078 40.706 20.382 30.693 20.845 30.221 40.150 30.158 30.000 20.746 20.369 30.545 30.595 10.387 30.997 20.413 40.720 40.636 20.165 30.732 30.070 20.851 20.402 40.251 30.313 30.123 30.583 40.696 10.000 10.051 40.500 10.000 20.500 30.372 40.667 30.009 30.000 20.307 40.003 30.479 30.107 40.226 30.903 20.109 30.031 20.981 20.726 40.000 20.522 40.669 20.282 40.052 40.778 40.000 30.000 20.400 20.074 30.333 30.218 41.000 10.000 10.250 10.406 40.118 40.317 20.100 30.000 10.191 10.596 20.000 20.000 10.000 10.000 20.000 30.500 10.178 40.701 10.000 30.000 10.522 40.018 40.000 10.000 10.000 10.060 30.000 10.000 10.033 40.000 10.000 20.000 30.000 20.281 20.100 20.000 40.090 30.133 20.000 10.422 30.050 40.000 20.000 20.200 20.000 40.000 10.000 10.000 20.000 10.000 30.123 30.677 10.021 30.000 30.500 10.000 10.500 20.442 10.125 40.000 10.000 10.000 20.000 10.000 10.000 10.056 30.000 20.000 10.000 10.000 10.000 10.200 30.000 10.143 40.000 10.000 20.250 40.000 10.511 30.000 10.000 10.286 20.083 30.396 10.000 10.000 10.000 10.000 20.000 10.025 30.300 20.000 20.371 10.070 20.000 30.385 40.000 40.000 10.000 10.000 40.000 10.000 10.000 20.500 10.000 10.000 10.000 10.200 20.000 10.000 10.000 20.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019