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

ScanNet200 3D Semantic Label 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 bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 by
ALS-MinkowskiNetcopyleft0.414 20.610 20.322 30.271 20.852 10.710 20.973 10.572 40.719 30.795 20.477 60.506 20.601 30.000 140.804 50.646 30.804 20.344 20.777 10.984 10.671 10.879 20.936 10.342 50.632 70.449 40.817 30.475 100.723 20.798 10.376 80.832 20.693 10.031 90.564 10.510 130.000 10.893 30.905 10.672 160.314 10.000 70.718 10.153 30.542 20.397 30.726 30.752 80.252 80.226 20.916 20.800 10.047 160.807 30.769 10.709 30.630 30.769 10.217 100.000 30.285 10.598 40.846 100.535 10.956 40.000 70.137 110.784 20.464 70.463 130.230 120.000 10.598 30.662 90.000 40.087 20.000 10.135 30.900 20.780 110.703 20.741 10.571 20.149 90.697 70.646 20.000 30.076 20.000 10.025 110.000 40.106 60.981 10.000 10.043 70.113 40.888 20.248 150.404 40.252 60.314 10.220 70.245 20.466 70.366 20.159 20.000 40.149 80.690 20.000 30.531 50.253 30.285 60.460 10.440 50.813 10.230 30.283 60.159 110.000 10.728 10.666 50.958 10.000 10.021 50.252 80.118 50.000 70.445 30.223 100.285 10.194 30.390 20.000 10.475 40.842 70.000 10.455 30.000 10.250 70.458 80.000 10.865 10.000 10.000 10.635 10.359 50.972 10.087 30.447 10.000 10.000 90.000 10.129 20.532 60.446 80.503 50.071 130.135 120.699 40.717 20.097 20.000 10.665 10.000 20.000 21.000 10.752 60.000 30.000 10.000 10.142 90.200 10.259 11.000 10.000 1
Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum: ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding. CVPR 2025
BFANet ScanNet200permissive0.360 50.553 70.293 50.193 50.827 40.689 40.970 30.528 130.661 60.753 60.436 80.378 80.469 150.042 70.810 30.654 20.760 40.266 100.659 100.973 40.574 30.849 110.897 50.382 30.546 130.372 90.698 140.491 90.617 100.526 100.436 10.764 140.476 170.101 50.409 60.585 100.000 10.835 60.901 30.810 50.102 140.000 70.688 20.096 60.483 100.264 120.612 90.591 160.358 20.161 60.863 50.707 40.128 40.814 20.669 40.629 100.563 40.651 140.258 50.000 30.194 100.494 90.806 120.394 60.953 50.000 70.233 10.757 40.508 60.556 40.476 40.000 10.573 50.741 60.000 40.000 90.000 10.000 60.000 170.852 50.678 30.616 60.460 50.338 30.710 50.534 50.000 30.025 40.000 10.043 30.000 40.056 120.493 170.000 10.000 100.109 50.785 70.590 60.298 130.282 30.143 130.262 40.053 110.526 40.337 50.215 10.000 40.135 90.510 40.000 30.596 40.043 140.511 30.321 120.459 30.772 20.124 130.060 140.266 60.000 10.574 90.568 90.653 100.000 10.093 10.298 40.239 30.000 70.516 20.129 140.284 20.000 80.431 10.000 10.000 50.848 60.000 10.492 10.000 10.376 30.522 60.000 10.469 170.000 10.000 10.330 60.151 100.875 140.000 90.254 40.000 10.000 90.000 10.088 130.661 10.481 50.255 120.105 10.139 90.666 50.641 50.000 120.000 10.614 20.000 20.000 20.000 110.921 20.000 30.000 10.000 10.497 10.000 70.000 30.000 110.000 1
Weiguang Zhao, Rui Zhang, Qiufeng Wang, Guangliang Cheng, Kaizhu Huang: BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis. CVPR 2025
DITR0.449 10.629 10.392 10.289 10.851 20.727 10.969 40.600 10.741 20.805 10.519 10.480 30.636 10.014 100.867 10.680 10.849 10.318 30.753 20.982 20.508 120.871 60.934 20.482 10.596 110.551 20.804 40.508 60.729 10.718 20.417 40.886 10.664 30.000 170.500 20.698 10.000 10.913 10.901 30.766 70.113 120.000 70.617 50.168 20.650 10.477 10.826 10.962 10.348 30.300 10.947 10.776 20.160 30.889 10.651 50.720 20.700 10.728 30.317 10.000 30.238 50.664 10.869 40.514 20.998 10.313 30.138 100.815 10.828 10.622 20.421 50.000 10.823 10.817 10.000 40.000 90.000 10.157 20.866 30.991 10.805 10.660 40.571 20.043 120.709 60.642 30.000 30.000 70.000 10.028 100.018 30.134 30.967 20.000 10.150 20.130 20.949 10.855 10.580 10.262 50.314 10.230 50.222 40.498 50.367 10.153 30.869 10.334 20.397 80.000 30.904 10.486 21.000 10.423 40.484 10.632 60.716 10.733 20.862 10.000 10.433 140.710 10.851 20.000 10.034 40.315 30.385 10.000 70.001 90.268 90.066 110.000 80.278 40.000 10.978 10.839 80.000 10.448 40.000 10.579 10.403 120.000 10.647 30.000 10.000 10.411 30.315 60.904 70.420 10.392 20.000 10.091 60.000 10.128 30.564 30.591 30.568 20.079 90.139 91.000 10.714 30.178 10.000 10.606 30.000 20.000 20.148 60.983 10.000 30.000 10.000 10.374 20.000 70.000 30.662 40.000 1
Karim Abou Zeid, Kadir Yilmaz, Daan de Geus, Alexander Hermans, David Adrian, Timm Linder, Bastian Leibe: DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation.
CeCo0.340 70.551 90.247 130.181 60.784 130.661 140.939 130.564 60.624 130.721 120.484 50.429 50.575 50.027 80.774 110.503 140.753 50.242 130.656 110.945 90.534 70.865 70.860 110.177 170.616 80.400 50.818 20.579 10.615 110.367 140.408 60.726 150.633 50.162 10.360 90.619 30.000 10.828 90.873 90.924 20.109 130.083 30.564 60.057 150.475 120.266 110.781 20.767 70.257 70.100 110.825 110.663 100.048 150.620 130.551 120.595 130.532 70.692 80.246 60.000 30.213 60.615 20.861 70.376 70.900 80.000 70.102 150.660 80.321 150.547 50.226 130.000 10.311 130.742 50.011 30.006 80.000 10.000 60.546 150.824 80.345 140.665 20.450 60.435 10.683 80.411 80.338 10.000 70.000 10.030 90.000 40.068 90.892 80.000 10.063 50.000 100.257 130.304 130.387 60.079 140.228 60.190 110.000 140.586 10.347 40.133 70.000 40.037 130.377 100.000 30.384 80.006 160.003 130.421 50.410 100.643 50.171 90.121 90.142 120.000 10.510 110.447 110.474 140.000 10.000 110.286 50.083 110.000 70.000 100.603 10.096 70.063 50.000 110.000 10.000 50.898 30.000 10.429 70.000 10.400 20.550 40.000 10.633 60.000 10.000 10.377 50.000 150.916 40.000 90.000 110.000 10.000 90.000 10.102 120.499 90.296 140.463 60.089 50.304 10.740 30.401 160.010 70.000 10.560 40.000 20.000 20.709 20.652 100.000 30.000 10.000 10.143 80.000 70.000 30.609 50.000 1
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
PTv3 ScanNet2000.393 30.592 30.330 20.216 30.851 20.687 60.971 20.586 20.755 10.752 70.505 20.404 70.575 50.000 140.848 20.616 40.761 30.349 10.738 30.978 30.546 60.860 80.926 30.346 40.654 30.384 70.828 10.523 40.699 30.583 60.387 70.822 30.688 20.118 40.474 30.603 50.000 10.832 80.903 20.753 90.140 100.000 70.650 30.109 50.520 30.457 20.497 100.871 40.281 40.192 50.887 40.748 30.168 20.727 70.733 20.740 10.644 20.714 50.190 130.000 30.256 30.449 100.914 10.514 20.759 150.337 10.172 60.692 70.617 30.636 10.325 70.000 10.641 20.782 20.000 40.065 30.000 10.000 60.842 40.903 20.661 40.662 30.612 10.405 20.731 40.566 40.000 30.000 70.000 10.017 150.301 10.088 70.941 30.000 10.077 40.000 100.717 80.790 20.310 120.026 170.264 40.349 10.220 50.397 120.366 20.115 130.000 40.337 10.463 60.000 30.531 50.218 40.593 20.455 20.469 20.708 30.210 40.592 40.108 160.000 10.728 10.682 30.671 80.000 10.000 110.407 10.136 40.022 30.575 10.436 40.259 30.428 10.048 60.000 10.000 50.879 50.000 10.480 20.000 10.133 90.597 20.000 10.690 20.000 10.000 10.009 160.000 150.921 30.000 90.151 50.000 10.000 90.000 10.109 80.494 110.622 20.394 90.073 120.141 70.798 20.528 80.026 50.000 10.551 50.000 20.000 20.134 70.717 80.000 30.000 10.000 10.188 40.000 70.000 30.791 30.000 1
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
L3DETR-ScanNet_2000.336 80.533 110.279 60.155 100.801 90.689 40.946 60.539 110.660 70.759 40.380 140.333 140.583 40.000 140.788 100.529 100.740 80.261 120.679 90.940 120.525 100.860 80.883 70.226 130.613 90.397 60.720 110.512 50.565 120.620 30.417 40.775 130.629 60.158 20.298 120.579 110.000 10.835 60.883 60.927 10.114 110.079 40.511 100.073 110.508 50.312 60.629 60.861 50.192 140.098 130.908 30.636 110.032 170.563 170.514 150.664 60.505 100.697 70.225 90.000 30.264 20.411 120.860 80.321 130.960 30.058 60.109 130.776 30.526 50.557 30.303 90.000 10.339 120.712 70.000 40.014 70.000 10.000 60.638 120.856 40.641 70.579 110.107 170.119 110.661 110.416 70.000 30.000 70.000 10.007 170.000 40.067 100.910 50.000 10.000 100.000 100.463 110.448 80.294 140.324 10.293 30.211 80.108 80.448 80.068 170.141 60.000 40.330 30.699 10.000 30.256 110.192 60.000 150.355 80.418 70.209 170.146 120.679 30.101 170.000 10.503 130.687 20.671 80.000 10.000 110.174 110.117 60.000 70.122 70.515 20.104 60.259 20.312 30.000 10.000 50.765 120.000 10.369 120.000 10.183 80.422 110.000 10.646 40.000 10.000 10.565 20.001 140.125 170.010 70.002 100.000 10.487 10.000 10.075 140.548 40.420 90.233 140.082 80.138 110.430 120.427 130.000 120.000 10.549 60.000 20.000 20.074 80.409 160.000 30.000 10.000 10.152 70.051 30.000 30.598 60.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
PPT-SpUNet-F.T.0.332 120.556 60.270 70.123 140.816 60.682 90.946 60.549 100.657 80.756 50.459 70.376 90.550 110.001 120.807 40.616 40.727 120.267 90.691 50.942 110.530 90.872 50.874 80.330 80.542 140.374 80.792 50.400 140.673 40.572 70.433 20.793 90.623 70.008 160.351 100.594 80.000 10.783 130.876 70.833 40.213 60.000 70.537 80.091 70.519 40.304 80.620 80.942 20.264 50.124 80.855 70.695 50.086 80.646 100.506 160.658 70.535 60.715 40.314 20.000 30.241 40.608 30.897 20.359 80.858 110.000 70.076 170.611 110.392 120.509 70.378 60.000 10.579 40.565 150.000 40.000 90.000 10.000 60.755 70.806 90.661 40.572 130.350 90.181 70.660 120.300 140.000 30.000 70.000 10.023 120.000 40.042 140.930 40.000 10.000 100.077 70.584 90.392 100.339 90.185 100.171 120.308 20.006 130.563 30.256 80.150 40.000 40.002 160.345 120.000 30.045 140.197 50.063 110.323 110.453 40.600 80.163 110.037 150.349 40.000 10.672 30.679 40.753 50.000 10.000 110.000 120.117 60.000 70.000 100.291 80.000 120.000 80.039 70.000 10.000 50.899 20.000 10.374 110.000 10.000 120.545 50.000 10.634 50.000 10.000 10.074 130.223 80.914 60.000 90.021 90.000 10.000 90.000 10.112 60.498 100.649 10.383 100.095 20.135 120.449 110.432 120.008 90.000 10.518 70.000 20.000 20.000 110.796 50.000 30.000 10.000 10.138 130.000 70.000 30.000 110.000 1
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
LGroundpermissive0.272 150.485 150.184 150.106 150.778 150.676 110.932 150.479 170.572 150.718 140.399 120.265 150.453 160.085 30.745 150.446 150.726 130.232 150.622 150.901 150.512 110.826 150.786 160.178 160.549 120.277 150.659 150.381 150.518 140.295 170.323 140.777 120.599 100.028 100.321 110.363 160.000 10.708 150.858 140.746 100.063 150.022 50.457 150.077 100.476 110.243 150.402 140.397 170.233 100.077 150.720 170.610 160.103 60.629 120.437 170.626 110.446 140.702 60.190 130.005 10.058 160.322 140.702 160.244 150.768 140.000 70.134 120.552 150.279 160.395 140.147 160.000 10.207 150.612 130.000 40.000 90.000 10.000 60.658 110.566 140.323 150.525 150.229 120.179 80.467 170.154 160.000 30.002 50.000 10.051 10.000 40.127 40.703 120.000 10.000 100.216 10.112 160.358 110.547 20.187 90.092 160.156 170.055 100.296 150.252 90.143 50.000 40.014 140.398 70.000 30.028 160.173 70.000 150.265 160.348 140.415 160.179 80.019 160.218 80.000 10.597 80.274 160.565 130.000 10.012 80.000 120.039 160.022 30.000 100.117 150.000 120.000 80.000 110.000 10.000 50.324 160.000 10.384 90.000 10.000 120.251 170.000 10.566 110.000 10.000 10.066 140.404 40.886 130.199 20.000 110.000 10.059 70.000 10.136 10.540 50.127 170.295 110.085 70.143 60.514 70.413 150.000 120.000 10.498 80.000 20.000 20.000 110.623 120.000 30.000 10.000 10.132 150.000 70.000 30.000 110.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
GSTran0.334 100.533 120.250 120.179 80.799 110.684 70.940 100.554 90.633 110.741 100.405 110.337 120.560 90.060 50.794 80.517 130.732 110.274 50.647 120.948 70.459 160.849 110.864 90.306 90.648 50.282 140.717 120.496 70.624 90.533 80.363 90.821 40.573 140.009 150.411 40.593 90.000 10.841 50.873 90.704 140.242 50.000 70.495 110.041 160.487 80.304 80.439 130.613 130.133 170.055 160.853 80.634 120.075 120.791 50.601 90.574 160.483 130.669 110.217 100.000 30.198 80.518 60.782 140.345 110.914 60.273 50.193 30.598 140.440 90.499 80.570 10.000 10.381 110.775 40.000 40.063 50.000 10.000 60.712 80.752 130.507 120.512 160.158 160.036 130.773 20.361 110.000 30.000 70.000 10.032 70.000 40.032 150.651 150.000 10.000 100.000 100.831 50.595 40.273 160.229 70.200 90.191 100.000 140.425 90.233 120.125 110.000 40.279 50.213 150.003 10.608 30.044 120.138 90.321 120.408 110.593 100.198 50.205 80.139 130.000 10.614 70.609 70.838 40.000 10.014 60.260 60.080 120.010 50.000 100.136 130.136 40.047 60.000 110.000 10.787 30.797 100.000 10.354 140.000 10.372 40.357 140.000 10.507 160.000 10.000 10.121 110.423 30.903 80.028 40.089 70.000 10.252 40.000 10.072 170.465 120.340 120.189 160.020 160.011 160.320 160.606 70.060 30.000 10.496 90.000 20.000 20.070 90.618 130.000 30.000 10.000 10.139 110.047 40.000 30.558 80.000 1
IMFSegNet0.334 90.532 130.251 110.179 70.799 110.683 80.940 100.555 80.631 120.740 110.406 100.336 130.560 90.062 40.795 70.518 120.733 100.274 50.646 130.947 80.458 170.848 130.862 100.305 100.649 40.284 130.713 130.495 80.626 80.527 90.363 90.820 50.574 130.010 140.411 40.597 70.000 10.842 40.873 90.704 140.246 40.000 70.495 110.041 160.486 90.305 70.444 120.604 150.134 160.055 160.852 90.633 130.076 90.792 40.612 80.573 170.484 120.668 120.216 120.000 30.197 90.518 60.784 130.344 120.908 70.283 40.190 40.599 130.439 100.496 100.569 20.000 10.392 90.776 30.000 40.064 40.000 10.000 60.710 90.756 120.508 110.512 160.159 150.034 140.773 20.363 100.000 30.000 70.000 10.032 70.000 40.029 160.648 160.000 10.000 100.000 100.830 60.595 40.274 150.228 80.206 80.188 120.000 140.425 90.237 110.123 120.000 40.277 60.214 140.003 10.610 20.044 120.124 100.320 140.408 110.594 90.196 70.213 70.139 130.000 10.615 60.618 60.839 30.000 10.014 60.260 60.080 120.025 20.000 100.139 120.135 50.035 70.000 110.000 10.793 20.799 90.000 10.357 130.000 10.369 50.359 130.000 10.512 150.000 10.000 10.120 120.424 20.903 80.027 50.091 60.000 10.245 50.000 10.073 160.457 140.340 120.191 150.021 150.009 170.322 150.608 60.060 30.000 10.494 100.000 20.000 20.068 100.624 110.000 30.000 10.000 10.139 110.047 40.000 30.561 70.000 1
PonderV2 ScanNet2000.346 60.552 80.270 80.175 90.810 70.682 90.950 50.560 70.641 100.761 30.398 130.357 100.570 80.113 20.804 50.603 60.750 70.283 40.681 70.952 50.548 50.874 40.852 130.290 120.700 20.356 110.792 50.445 120.545 130.436 120.351 120.787 100.611 80.050 80.290 140.519 120.000 10.825 100.888 50.842 30.259 30.100 20.558 70.070 120.497 70.247 140.457 110.889 30.248 90.106 100.817 130.691 60.094 70.729 60.636 60.620 120.503 110.660 130.243 70.000 30.212 70.590 50.860 80.400 50.881 90.000 70.202 20.622 100.408 110.499 80.261 100.000 10.385 100.636 100.000 40.000 90.000 10.000 60.433 160.843 60.660 60.574 120.481 40.336 40.677 90.486 60.000 30.030 30.000 10.034 60.000 40.080 80.869 100.000 10.000 100.000 100.540 100.727 30.232 170.115 110.186 100.193 90.000 140.403 110.326 60.103 140.000 40.290 40.392 90.000 30.346 100.062 100.424 50.375 70.431 60.667 40.115 140.082 120.239 70.000 10.504 120.606 80.584 120.000 10.002 90.186 100.104 100.000 70.394 50.384 60.083 80.000 80.007 90.000 10.000 50.880 40.000 10.377 100.000 10.263 60.565 30.000 10.608 90.000 10.000 10.304 70.009 110.924 20.000 90.000 110.000 10.000 90.000 10.128 30.584 20.475 70.412 80.076 110.269 30.621 60.509 90.010 70.000 10.491 110.063 10.000 20.472 40.880 40.000 30.000 10.000 10.179 50.125 20.000 30.441 100.000 1
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
OA-CNN-L_ScanNet2000.333 110.558 50.269 90.124 130.821 50.703 30.946 60.569 50.662 40.748 90.487 30.455 40.572 70.000 140.789 90.534 90.736 90.271 80.713 40.949 60.498 140.877 30.860 110.332 70.706 10.474 30.788 70.406 130.637 60.495 110.355 110.805 70.592 120.015 130.396 80.602 60.000 10.799 110.876 70.713 130.276 20.000 70.493 130.080 90.448 140.363 50.661 40.833 60.262 60.125 70.823 120.665 90.076 90.720 80.557 100.637 90.517 90.672 100.227 80.000 30.158 120.496 80.843 110.352 100.835 130.000 70.103 140.711 50.527 40.526 60.320 80.000 10.568 60.625 110.067 10.000 90.000 10.001 50.806 60.836 70.621 100.591 80.373 80.314 50.668 100.398 90.003 20.000 70.000 10.016 160.024 20.043 130.906 60.000 10.052 60.000 100.384 120.330 120.342 80.100 120.223 70.183 130.112 70.476 60.313 70.130 90.196 30.112 120.370 110.000 30.234 120.071 90.160 70.403 60.398 130.492 140.197 60.076 130.272 50.000 10.200 160.560 100.735 70.000 10.000 110.000 120.110 80.002 60.021 80.412 50.000 120.000 80.000 110.000 10.000 50.794 110.000 10.445 50.000 10.022 100.509 70.000 10.517 130.000 10.000 10.001 170.245 70.915 50.024 60.089 70.000 10.262 30.000 10.103 110.524 70.392 110.515 40.013 170.251 40.411 130.662 40.001 110.000 10.473 120.000 20.000 20.150 50.699 90.000 30.000 10.000 10.166 60.000 70.024 20.000 110.000 1
OctFormer ScanNet200permissive0.326 130.539 100.265 100.131 120.806 80.670 120.943 90.535 120.662 40.705 160.423 90.407 60.505 130.003 110.765 130.582 70.686 150.227 160.680 80.943 100.601 20.854 100.892 60.335 60.417 170.357 100.724 100.453 110.632 70.596 50.432 30.783 110.512 160.021 120.244 150.637 20.000 10.787 120.873 90.743 110.000 170.000 70.534 90.110 40.499 60.289 100.626 70.620 120.168 150.204 40.849 100.679 80.117 50.633 110.684 30.650 80.552 50.684 90.312 30.000 30.175 110.429 110.865 50.413 40.837 120.000 70.145 80.626 90.451 80.487 110.513 30.000 10.529 70.613 120.000 40.033 60.000 10.000 60.828 50.871 30.622 90.587 90.411 70.137 100.645 140.343 120.000 30.000 70.000 10.022 130.000 40.026 170.829 110.000 10.022 80.089 60.842 40.253 140.318 110.296 20.178 110.291 30.224 30.584 20.200 140.132 80.000 40.128 110.227 130.000 30.230 130.047 110.149 80.331 100.412 90.618 70.164 100.102 110.522 30.000 10.655 40.378 120.469 150.000 10.000 110.000 120.105 90.000 70.000 100.483 30.000 120.000 80.028 80.000 10.000 50.906 10.000 10.339 150.000 10.000 120.457 90.000 10.612 80.000 10.000 10.408 40.000 150.900 100.000 90.000 110.000 10.029 80.000 10.074 150.455 150.479 60.427 70.079 90.140 80.496 80.414 140.022 60.000 10.471 130.000 20.000 20.000 110.722 70.000 30.000 10.000 10.138 130.000 70.000 30.000 110.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
AWCS0.305 140.508 140.225 140.142 110.782 140.634 170.937 140.489 150.578 140.721 120.364 150.355 110.515 120.023 90.764 140.523 110.707 140.264 110.633 140.922 140.507 130.886 10.804 150.179 150.436 160.300 120.656 160.529 30.501 150.394 130.296 160.820 50.603 90.131 30.179 170.619 30.000 10.707 160.865 130.773 60.171 70.010 60.484 140.063 130.463 130.254 130.332 160.649 110.220 110.100 110.729 150.613 150.071 130.582 140.628 70.702 40.424 150.749 20.137 150.000 30.142 130.360 130.863 60.305 140.877 100.000 70.173 50.606 120.337 140.478 120.154 150.000 10.253 140.664 80.000 40.000 90.000 10.000 60.626 130.782 100.302 160.602 70.185 130.282 60.651 130.317 130.000 30.000 70.000 10.022 130.000 40.154 20.876 90.000 10.014 90.063 90.029 170.553 70.467 30.084 130.124 140.157 160.049 120.373 130.252 90.097 150.000 40.219 70.542 30.000 30.392 70.172 80.000 150.339 90.417 80.533 130.093 150.115 100.195 90.000 10.516 100.288 150.741 60.000 10.001 100.233 90.056 140.000 70.159 60.334 70.077 90.000 80.000 110.000 10.000 50.749 130.000 10.411 80.000 10.008 110.452 100.000 10.595 100.000 10.000 10.220 100.006 120.894 120.006 80.000 110.000 10.000 90.000 10.112 60.504 80.404 100.551 30.093 40.129 140.484 100.381 170.000 120.000 10.396 140.000 20.000 20.620 30.402 170.000 30.000 10.000 10.142 90.000 70.000 30.512 90.000 1
: Long-Tailed 3D Semantic Segmentation with Adaptive Weight Constraint and Sampling. ICRA 2024
Minkowski 34Dpermissive0.253 160.463 160.154 170.102 160.771 160.650 160.932 150.483 160.571 160.710 150.331 160.250 160.492 140.044 60.703 160.419 170.606 170.227 160.621 160.865 170.531 80.771 170.813 140.291 110.484 150.242 160.612 170.282 170.440 170.351 150.299 150.622 160.593 110.027 110.293 130.310 170.000 10.757 140.858 140.737 120.150 90.164 10.368 170.084 80.381 160.142 170.357 150.720 100.214 120.092 140.724 160.596 170.056 140.655 90.525 140.581 150.352 170.594 150.056 170.000 30.014 170.224 150.772 150.205 170.720 160.000 70.159 70.531 160.163 170.294 160.136 170.000 10.169 160.589 140.000 40.000 90.000 10.002 40.663 100.466 170.265 170.582 100.337 100.016 150.559 150.084 170.000 30.000 70.000 10.036 50.000 40.125 50.670 130.000 10.102 30.071 80.164 150.406 90.386 70.046 160.068 170.159 150.117 60.284 160.111 160.094 160.000 40.000 170.197 160.000 30.044 150.013 150.002 140.228 170.307 170.588 110.025 170.545 50.134 150.000 10.655 40.302 140.282 170.000 10.060 20.000 120.035 170.000 70.000 100.097 170.000 120.000 80.005 100.000 10.000 50.096 170.000 10.334 160.000 10.000 120.274 160.000 10.513 140.000 10.000 10.280 80.194 90.897 110.000 90.000 110.000 10.000 90.000 10.108 90.279 170.189 160.141 170.059 140.272 20.307 170.445 100.003 100.000 10.353 150.000 20.026 10.000 110.581 150.001 20.000 10.000 10.093 170.002 60.000 30.000 110.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrainpermissive0.249 170.455 170.171 160.079 170.766 170.659 150.930 170.494 140.542 170.700 170.314 170.215 170.430 170.121 10.697 170.441 160.683 160.235 140.609 170.895 160.476 150.816 160.770 170.186 140.634 60.216 170.734 90.340 160.471 160.307 160.293 170.591 170.542 150.076 70.205 160.464 140.000 10.484 170.832 160.766 70.052 160.000 70.413 160.059 140.418 150.222 160.318 170.609 140.206 130.112 90.743 140.625 140.076 90.579 150.548 130.590 140.371 160.552 170.081 160.003 20.142 130.201 160.638 170.233 160.686 170.000 70.142 90.444 170.375 130.247 170.198 140.000 10.128 170.454 170.019 20.097 10.000 10.000 60.553 140.557 150.373 130.545 140.164 140.014 160.547 160.174 150.000 30.002 50.000 10.037 40.000 40.063 110.664 140.000 10.000 100.130 20.170 140.152 160.335 100.079 140.110 150.175 140.098 90.175 170.166 150.045 170.207 20.014 140.465 50.000 30.001 170.001 170.046 120.299 150.327 160.537 120.033 160.012 170.186 100.000 10.205 150.377 130.463 160.000 10.058 30.000 120.055 150.041 10.000 100.105 160.000 120.000 80.000 110.000 10.000 50.398 150.000 10.308 170.000 10.000 120.319 150.000 10.543 120.000 10.000 10.062 150.004 130.862 150.000 90.000 110.000 10.000 90.000 10.123 50.316 160.225 150.250 130.094 30.180 50.332 140.441 110.000 120.000 10.310 160.000 20.000 20.000 110.592 140.000 30.000 10.000 10.203 30.000 70.000 30.000 110.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
ODIN - Sem200permissive0.368 40.562 40.297 40.207 40.800 100.669 130.940 100.575 30.654 90.749 80.487 30.589 10.609 20.001 120.769 120.561 80.752 60.274 50.682 60.926 130.554 40.833 140.921 40.389 20.599 100.591 10.787 80.550 20.657 50.610 40.334 130.803 80.661 40.090 60.408 70.373 150.000 10.912 20.796 170.501 170.169 80.000 70.641 40.196 10.380 170.397 30.641 50.740 90.862 10.213 30.857 60.685 70.216 10.578 160.557 100.685 50.523 80.581 160.312 30.000 30.065 150.000 170.871 30.359 80.988 20.321 20.090 160.704 60.631 20.393 150.246 110.000 10.482 80.565 150.000 40.000 90.000 10.181 10.913 10.468 160.632 80.642 50.259 110.000 170.832 10.663 10.000 30.081 10.000 10.048 20.000 40.376 10.898 70.000 10.157 10.000 100.870 30.000 170.400 50.265 40.242 50.227 60.539 10.370 140.214 130.129 100.000 40.131 100.054 170.000 30.358 90.491 10.462 40.434 30.346 150.454 150.316 20.814 10.828 20.000 10.000 170.220 170.612 110.000 10.000 110.373 20.378 20.000 70.429 40.152 110.077 90.166 40.202 50.000 10.000 50.441 140.000 10.440 60.000 10.000 120.655 10.000 10.626 70.000 10.000 10.228 90.487 10.784 160.000 90.301 30.000 10.426 20.000 10.108 90.460 130.590 40.775 10.088 60.119 150.485 90.791 10.000 120.000 10.256 170.000 20.000 20.000 110.885 30.303 10.000 10.000 10.127 160.000 70.000 30.894 20.000 1
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024


ScanNet200 3D Semantic Instance Benchmark

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




Method Infoavgchairtabledoorcouchcabinetshelfdeskoffice 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 bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 by
ODIN - Ins200permissive0.381 20.507 20.375 10.237 10.653 60.614 30.780 10.744 60.566 10.328 10.446 30.003 30.853 20.496 20.582 30.448 60.434 30.938 50.682 20.782 30.494 50.274 20.723 50.269 10.694 60.393 50.511 20.695 10.227 10.550 50.795 30.039 20.602 10.638 10.000 30.734 10.585 30.667 40.163 10.500 30.769 10.108 10.484 40.569 10.688 11.000 10.665 10.093 21.000 10.863 10.049 10.667 50.887 10.778 10.422 10.786 50.550 10.000 30.542 30.028 50.667 30.428 21.000 10.125 10.208 50.530 40.406 20.337 20.000 50.000 20.585 10.742 20.500 10.000 20.000 10.472 11.000 10.417 40.563 10.631 30.275 10.000 30.800 10.841 10.000 20.083 10.000 30.174 30.000 10.055 20.667 10.000 30.000 30.250 31.000 10.286 30.058 40.391 30.209 10.313 10.167 10.278 60.200 30.083 10.000 10.200 30.264 20.000 10.250 20.714 10.500 10.196 20.333 10.500 40.750 10.668 10.500 10.000 10.500 40.333 41.000 10.000 10.000 30.438 10.500 10.000 21.000 10.333 20.226 20.250 30.250 10.000 30.000 10.668 20.000 10.174 50.000 10.000 30.750 10.000 10.667 30.000 10.000 10.638 30.333 20.579 20.000 10.333 10.000 11.000 10.000 10.063 30.385 20.600 10.647 20.066 30.264 40.469 30.246 20.000 20.000 10.264 10.000 10.000 10.000 21.000 10.125 10.000 20.000 20.200 20.000 20.000 21.000 10.000 1
TD3D Scannet200permissive0.320 30.501 30.264 30.164 30.841 10.679 10.716 30.879 20.280 40.192 20.634 10.231 10.733 40.459 30.565 40.498 50.560 21.000 10.686 10.890 20.708 10.123 50.820 10.152 30.967 10.456 10.458 30.387 30.194 20.435 60.906 10.077 10.396 30.509 20.217 20.715 20.619 21.000 10.099 30.792 10.513 30.062 30.506 30.549 20.605 21.000 10.123 50.106 11.000 10.744 50.000 31.000 10.504 60.525 30.185 30.790 40.101 30.008 20.587 20.356 10.817 10.083 61.000 10.000 20.621 10.842 10.415 10.268 50.083 40.000 20.098 40.881 10.125 30.000 20.000 10.000 30.000 40.125 50.332 40.448 60.202 30.196 10.798 20.264 30.000 20.000 20.017 20.233 20.000 10.063 10.333 30.038 10.111 10.250 30.000 30.516 10.208 10.470 20.094 40.218 20.000 20.667 20.033 60.000 30.000 10.400 10.156 30.000 10.267 10.226 20.000 20.104 30.159 30.299 60.095 40.458 20.500 10.000 11.000 10.472 10.792 40.000 10.022 10.061 30.250 20.008 10.250 30.333 20.143 30.396 20.049 30.012 10.000 10.283 50.000 10.241 40.000 10.101 20.331 50.000 10.629 40.000 10.000 10.857 20.222 40.677 10.000 10.003 30.000 10.000 30.000 10.076 20.252 40.400 20.431 30.061 40.328 30.331 50.500 10.000 20.000 10.167 20.000 10.000 10.000 20.500 30.000 20.000 21.000 10.542 10.000 20.063 10.000 30.000 1
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
LGround Inst.permissive0.246 40.413 40.170 40.130 40.754 30.541 40.682 50.903 10.264 50.164 30.234 40.000 40.681 50.452 40.464 60.541 40.399 41.000 10.637 30.772 40.588 40.190 30.589 60.081 40.857 30.426 30.373 40.318 40.135 30.690 20.653 50.000 40.159 50.500 30.000 30.581 40.387 51.000 10.046 40.000 40.402 40.003 60.455 60.196 50.571 31.000 10.270 40.003 60.530 60.748 40.000 30.744 40.575 40.511 40.112 40.815 20.067 40.000 30.400 40.167 30.667 30.241 31.000 10.000 20.208 40.660 30.125 50.317 30.000 50.000 20.100 30.561 50.000 40.000 20.000 10.000 31.000 10.500 10.344 30.568 50.167 40.000 30.706 40.068 40.000 20.000 20.000 30.063 40.000 10.000 40.056 50.000 30.000 30.500 20.000 30.143 60.017 50.125 40.097 30.164 40.000 20.582 40.400 10.000 30.000 10.000 50.083 50.000 10.000 40.000 40.000 20.025 40.156 40.533 30.250 30.200 30.500 10.000 11.000 10.333 41.000 10.000 10.000 30.000 40.000 40.000 20.000 40.333 20.000 40.000 40.000 40.000 30.000 10.400 40.000 10.364 20.000 10.000 30.500 40.000 10.511 50.000 10.000 10.286 40.333 20.000 60.000 10.000 40.000 10.000 30.000 10.034 40.111 60.000 40.333 50.031 60.000 50.750 10.125 30.000 20.000 10.151 30.000 10.000 10.000 20.500 30.000 20.000 20.000 20.000 60.000 20.000 20.000 30.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
Mask3D Scannet2000.388 10.542 10.357 20.237 20.808 20.676 20.741 20.832 40.496 20.151 40.628 20.021 20.955 10.578 10.753 10.612 10.591 10.822 60.609 40.926 10.614 30.291 10.725 40.163 20.890 20.380 60.615 10.517 20.130 40.806 10.857 20.024 30.511 20.412 60.226 10.597 30.756 11.000 10.111 20.792 10.736 20.091 20.610 10.527 30.323 51.000 10.504 20.063 31.000 10.853 20.010 20.974 30.839 20.667 20.301 20.883 10.266 20.039 10.640 10.311 20.739 20.463 11.000 10.000 20.287 20.715 20.313 30.600 11.000 10.027 10.076 50.502 60.500 10.409 10.000 10.194 20.125 30.500 10.491 20.748 10.050 50.042 20.776 30.352 20.008 10.000 20.033 10.254 10.000 10.005 30.552 20.008 20.020 20.750 10.500 20.409 20.065 30.511 10.107 20.178 30.000 21.000 10.400 10.016 20.000 10.400 10.571 10.000 10.060 30.044 30.000 20.514 10.278 21.000 10.258 20.017 40.125 60.000 10.792 30.399 31.000 10.000 10.013 20.265 20.018 30.000 21.000 10.335 10.381 10.500 10.250 10.004 20.000 10.727 10.000 10.497 10.000 10.188 10.677 30.000 10.708 20.000 10.000 10.945 10.391 10.123 50.000 10.028 20.000 11.000 10.000 10.099 10.451 10.400 20.668 10.573 10.606 10.077 60.003 50.004 10.000 10.042 40.000 10.000 11.000 11.000 10.000 20.042 10.000 20.200 20.302 10.000 21.000 10.000 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
CSC-Pretrain Inst.permissive0.209 50.361 60.157 50.085 50.700 50.248 60.634 60.776 50.322 30.135 60.103 60.000 40.524 60.364 60.618 20.592 30.381 60.997 30.589 50.747 50.340 60.109 60.768 20.059 60.702 50.448 20.188 60.149 60.091 60.636 30.573 60.000 40.246 40.500 30.000 30.450 60.405 40.667 40.006 60.000 40.356 50.007 40.506 20.420 40.340 40.667 60.294 30.004 50.571 50.748 30.000 31.000 10.573 50.502 50.094 50.807 30.000 50.000 30.400 40.000 60.278 60.228 41.000 10.000 20.115 60.432 50.198 40.050 60.125 20.000 20.000 60.573 40.000 40.000 20.000 10.000 30.000 40.125 50.312 50.610 40.221 20.000 30.667 50.050 50.000 20.000 20.000 30.032 60.000 10.000 40.083 40.000 30.000 30.000 50.000 30.220 50.000 60.125 40.000 60.111 60.000 20.667 20.200 30.000 30.000 10.000 50.110 40.000 10.000 40.000 40.000 20.000 50.053 60.500 40.000 60.000 50.500 10.000 10.500 40.333 40.500 50.000 10.000 30.000 40.000 40.000 20.000 40.000 60.000 40.000 40.000 40.000 30.000 10.600 30.000 10.364 20.000 10.000 30.750 10.000 10.833 10.000 10.000 10.143 60.000 60.396 30.000 10.000 40.000 10.000 30.000 10.021 60.221 50.000 40.093 60.055 50.451 20.677 20.125 30.000 20.000 10.028 50.000 10.000 10.000 20.500 30.000 20.000 20.000 20.050 50.000 20.000 20.000 30.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34D Inst.permissive0.203 60.369 50.134 60.078 60.706 40.382 50.693 40.845 30.221 60.150 50.158 50.000 40.746 30.369 50.545 50.595 20.387 50.997 30.413 60.720 60.636 20.165 40.732 30.070 50.851 40.402 40.251 50.313 50.123 50.583 40.696 40.000 40.051 60.500 30.000 30.500 50.372 60.667 40.009 50.000 40.307 60.003 50.479 50.107 60.226 60.903 50.109 60.031 40.981 40.726 60.000 30.522 60.669 30.282 60.052 60.778 60.000 50.000 30.400 40.074 40.333 50.218 51.000 10.000 20.250 30.406 60.118 60.317 30.100 30.000 20.191 20.596 30.000 40.000 20.000 10.000 30.000 40.500 10.178 60.701 20.000 60.000 30.522 60.018 60.000 20.000 20.000 30.060 50.000 10.000 40.033 60.000 30.000 30.000 50.000 30.281 40.100 20.000 60.090 50.133 50.000 20.422 50.050 50.000 30.000 10.200 30.000 60.000 10.000 40.000 40.000 20.000 50.123 50.677 20.021 50.000 50.500 10.000 10.500 40.442 20.125 60.000 10.000 30.000 40.000 40.000 20.000 40.056 50.000 40.000 40.000 40.000 30.000 10.200 60.000 10.143 60.000 10.000 30.250 60.000 10.511 50.000 10.000 10.286 40.083 50.396 30.000 10.000 40.000 10.000 30.000 10.025 50.300 30.000 40.371 40.070 20.000 50.385 40.000 60.000 20.000 10.000 60.000 10.000 10.000 20.500 30.000 20.000 20.000 20.200 20.000 20.000 20.000 30.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


ScanNet Benchmark

3D Semantic Label 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
PTv3-PPT-ALCcopyleft0.798 10.911 110.812 230.854 80.770 120.856 150.555 170.943 10.660 260.735 20.979 10.606 70.492 10.792 40.934 40.841 20.819 60.716 90.947 100.906 10.822 1
Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum: ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding. CVPR 2025
DITR ScanNet0.797 20.727 770.869 10.882 10.785 60.868 70.578 50.943 10.744 10.727 30.979 10.627 20.364 90.824 10.949 20.779 150.844 10.757 10.982 10.905 20.802 3
Karim Abou Zeid, Kadir Yilmaz, Daan de Geus, Alexander Hermans, David Adrian, Timm Linder, Bastian Leibe: DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation.
PTv3 ScanNet0.794 30.941 30.813 220.851 110.782 70.890 20.597 10.916 60.696 110.713 50.979 10.635 10.384 30.793 30.907 100.821 50.790 370.696 140.967 40.903 30.805 2
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
PonderV20.785 40.978 10.800 310.833 300.788 40.853 200.545 210.910 90.713 30.705 60.979 10.596 90.390 20.769 150.832 450.821 50.792 360.730 20.975 20.897 60.785 7
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
Mix3Dpermissive0.781 50.964 20.855 20.843 200.781 80.858 130.575 80.831 400.685 170.714 40.979 10.594 100.310 310.801 20.892 190.841 20.819 60.723 60.940 150.887 80.725 29
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 60.861 240.818 170.836 270.790 30.875 40.576 70.905 100.704 70.739 10.969 120.611 30.349 120.756 250.958 10.702 520.805 200.708 100.916 390.898 50.801 4
TTT-KD0.773 70.646 980.818 170.809 420.774 100.878 30.581 30.943 10.687 150.704 70.978 60.607 60.336 200.775 110.912 80.838 40.823 40.694 150.967 40.899 40.794 6
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ResLFE_HDS0.772 80.939 40.824 70.854 80.771 110.840 350.564 130.900 120.686 160.677 140.961 180.537 360.348 130.769 150.903 120.785 130.815 90.676 260.939 160.880 130.772 11
PPT-SpUNet-Joint0.766 90.932 50.794 370.829 320.751 260.854 180.540 250.903 110.630 390.672 180.963 160.565 260.357 100.788 50.900 140.737 310.802 210.685 200.950 80.887 80.780 8
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormerpermissive0.766 90.925 70.808 270.849 130.786 50.846 300.566 120.876 190.690 130.674 170.960 190.576 220.226 740.753 270.904 110.777 160.815 90.722 70.923 310.877 170.776 10
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net0.764 110.924 80.819 140.840 230.757 210.853 200.580 40.848 320.709 50.643 280.958 240.587 160.295 390.753 270.884 230.758 230.815 90.725 50.927 270.867 280.743 20
OccuSeg+Semantic0.764 110.758 620.796 350.839 240.746 300.907 10.562 140.850 310.680 190.672 180.978 60.610 40.335 220.777 90.819 490.847 10.830 30.691 170.972 30.885 100.727 27
O-CNNpermissive0.762 130.924 80.823 80.844 190.770 120.852 220.577 60.847 340.711 40.640 320.958 240.592 110.217 800.762 200.888 200.758 230.813 130.726 40.932 250.868 270.744 19
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
DiffSegNet0.758 140.725 790.789 420.843 200.762 170.856 150.562 140.920 40.657 290.658 220.958 240.589 140.337 190.782 60.879 240.787 110.779 420.678 220.926 290.880 130.799 5
DTC0.757 150.843 300.820 120.847 160.791 20.862 110.511 390.870 230.707 60.652 240.954 410.604 80.279 500.760 210.942 30.734 320.766 510.701 130.884 620.874 230.736 21
OA-CNN-L_ScanNet200.756 160.783 480.826 60.858 60.776 90.837 400.548 200.896 150.649 310.675 160.962 170.586 170.335 220.771 140.802 540.770 190.787 390.691 170.936 200.880 130.761 14
PNE0.755 170.786 460.835 50.834 290.758 190.849 250.570 100.836 390.648 320.668 200.978 60.581 200.367 70.683 400.856 330.804 80.801 250.678 220.961 60.889 70.716 36
P. Hermosilla: Point Neighborhood Embeddings.
LSK3DNetpermissive0.755 170.899 170.823 80.843 200.764 160.838 380.584 20.845 350.717 20.638 340.956 310.580 210.229 730.640 500.900 140.750 260.813 130.729 30.920 350.872 250.757 15
Tuo Feng, Wenguan Wang, Fan Ma, Yi Yang: LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels. CVPR 2024
ConDaFormer0.755 170.927 60.822 100.836 270.801 10.849 250.516 360.864 280.651 300.680 130.958 240.584 190.282 470.759 230.855 350.728 340.802 210.678 220.880 670.873 240.756 17
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
DMF-Net0.752 200.906 150.793 390.802 480.689 470.825 530.556 160.867 240.681 180.602 510.960 190.555 320.365 80.779 80.859 300.747 270.795 330.717 80.917 380.856 360.764 13
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
PointTransformerV20.752 200.742 690.809 260.872 20.758 190.860 120.552 180.891 170.610 460.687 80.960 190.559 300.304 340.766 180.926 60.767 200.797 290.644 390.942 130.876 200.722 32
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer0.749 220.793 440.790 400.807 440.750 280.856 150.524 320.881 180.588 590.642 310.977 100.591 120.274 530.781 70.929 50.804 80.796 300.642 400.947 100.885 100.715 37
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 220.909 130.818 170.811 400.752 240.839 370.485 540.842 360.673 210.644 270.957 290.528 430.305 330.773 120.859 300.788 100.818 80.693 160.916 390.856 360.723 31
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 240.623 1010.804 290.859 50.745 310.824 550.501 430.912 80.690 130.685 100.956 310.567 250.320 280.768 170.918 70.720 390.802 210.676 260.921 330.881 120.779 9
StratifiedFormerpermissive0.747 250.901 160.803 300.845 180.757 210.846 300.512 380.825 430.696 110.645 260.956 310.576 220.262 640.744 330.861 290.742 290.770 490.705 110.899 510.860 330.734 22
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 MVFusion0.746 260.771 560.819 140.848 150.702 430.865 100.397 920.899 130.699 90.664 210.948 630.588 150.330 240.746 320.851 390.764 210.796 300.704 120.935 210.866 290.728 25
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNetpermissive0.746 260.870 220.838 30.858 60.729 360.850 240.501 430.874 200.587 600.658 220.956 310.564 270.299 360.765 190.900 140.716 420.812 150.631 450.939 160.858 340.709 38
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)
DiffSeg3D20.745 280.725 790.814 210.837 250.751 260.831 470.514 370.896 150.674 200.684 110.960 190.564 270.303 350.773 120.820 480.713 450.798 280.690 190.923 310.875 210.757 15
ODINpermissive0.744 290.658 940.752 650.870 30.714 400.843 330.569 110.919 50.703 80.622 410.949 600.591 120.343 150.736 340.784 560.816 70.838 20.672 310.918 370.854 400.725 29
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024
Retro-FPN0.744 290.842 310.800 310.767 620.740 320.836 420.541 230.914 70.672 220.626 380.958 240.552 330.272 550.777 90.886 220.696 530.801 250.674 290.941 140.858 340.717 34
Peng Xiang*, Xin Wen*, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
EQ-Net0.743 310.620 1020.799 340.849 130.730 350.822 570.493 510.897 140.664 230.681 120.955 350.562 290.378 40.760 210.903 120.738 300.801 250.673 300.907 430.877 170.745 18
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT0.742 320.860 250.765 560.819 350.769 140.848 270.533 270.829 410.663 240.631 370.955 350.586 170.274 530.753 270.896 170.729 330.760 570.666 330.921 330.855 380.733 23
LRPNet0.742 320.816 390.806 280.807 440.752 240.828 510.575 80.839 380.699 90.637 350.954 410.520 470.320 280.755 260.834 430.760 220.772 460.676 260.915 410.862 310.717 34
LargeKernel3D0.739 340.909 130.820 120.806 460.740 320.852 220.545 210.826 420.594 580.643 280.955 350.541 350.263 630.723 380.858 320.775 180.767 500.678 220.933 230.848 440.694 43
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN0.736 350.776 520.790 400.851 110.754 230.854 180.491 530.866 260.596 570.686 90.955 350.536 370.342 160.624 570.869 260.787 110.802 210.628 460.927 270.875 210.704 40
MinkowskiNetpermissive0.736 350.859 260.818 170.832 310.709 410.840 350.521 340.853 300.660 260.643 280.951 520.544 340.286 450.731 360.893 180.675 620.772 460.683 210.874 740.852 420.727 27
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 370.890 180.837 40.864 40.726 370.873 50.530 310.824 440.489 940.647 250.978 60.609 50.336 200.624 570.733 640.758 230.776 440.570 720.949 90.877 170.728 25
MS-SFA-net0.730 380.910 120.819 140.837 250.698 440.838 380.532 290.872 210.605 500.676 150.959 230.535 390.341 170.649 460.598 880.708 470.810 160.664 350.895 540.879 160.771 12
online3d0.727 390.715 840.777 490.854 80.748 290.858 130.497 480.872 210.572 670.639 330.957 290.523 440.297 380.750 300.803 530.744 280.810 160.587 680.938 180.871 260.719 33
SparseConvNet0.725 400.647 970.821 110.846 170.721 380.869 60.533 270.754 650.603 530.614 430.955 350.572 240.325 260.710 390.870 250.724 370.823 40.628 460.934 220.865 300.683 46
PointTransformer++0.725 400.727 770.811 250.819 350.765 150.841 340.502 420.814 490.621 420.623 400.955 350.556 310.284 460.620 590.866 270.781 140.757 610.648 370.932 250.862 310.709 38
MatchingNet0.724 420.812 410.812 230.810 410.735 340.834 440.495 500.860 290.572 670.602 510.954 410.512 490.280 490.757 240.845 410.725 360.780 410.606 560.937 190.851 430.700 42
INS-Conv-semantic0.717 430.751 650.759 590.812 390.704 420.868 70.537 260.842 360.609 480.608 470.953 450.534 400.293 400.616 600.864 280.719 410.793 340.640 410.933 230.845 480.663 52
PointMetaBase0.714 440.835 320.785 440.821 330.684 490.846 300.531 300.865 270.614 430.596 550.953 450.500 520.246 690.674 410.888 200.692 540.764 530.624 480.849 890.844 490.675 48
contrastBoundarypermissive0.705 450.769 590.775 500.809 420.687 480.820 600.439 800.812 500.661 250.591 570.945 710.515 480.171 990.633 540.856 330.720 390.796 300.668 320.889 590.847 450.689 44
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 460.774 540.800 310.793 530.760 180.847 290.471 580.802 530.463 1010.634 360.968 140.491 550.271 570.726 370.910 90.706 480.815 90.551 840.878 680.833 500.570 84
RFCR0.702 470.889 190.745 710.813 380.672 520.818 640.493 510.815 480.623 400.610 450.947 650.470 640.249 680.594 640.848 400.705 490.779 420.646 380.892 570.823 560.611 67
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 Click0.701 480.825 360.796 350.723 690.716 390.832 460.433 820.816 460.634 370.609 460.969 120.418 900.344 140.559 760.833 440.715 430.808 190.560 780.902 480.847 450.680 47
JSENetpermissive0.699 490.881 210.762 570.821 330.667 530.800 770.522 330.792 560.613 440.607 480.935 910.492 540.205 860.576 690.853 370.691 560.758 590.652 360.872 770.828 530.649 56
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
One-Thing-One-Click0.693 500.743 680.794 370.655 920.684 490.822 570.497 480.719 750.622 410.617 420.977 100.447 770.339 180.750 300.664 810.703 510.790 370.596 610.946 120.855 380.647 57
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 510.732 730.772 510.786 540.677 510.866 90.517 350.848 320.509 870.626 380.952 500.536 370.225 760.545 820.704 710.689 590.810 160.564 770.903 470.854 400.729 24
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 520.884 200.754 630.795 510.647 600.818 640.422 840.802 530.612 450.604 490.945 710.462 670.189 940.563 750.853 370.726 350.765 520.632 440.904 450.821 590.606 71
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 530.704 860.741 750.754 660.656 550.829 490.501 430.741 700.609 480.548 650.950 560.522 460.371 50.633 540.756 590.715 430.771 480.623 490.861 850.814 620.658 53
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 540.866 230.748 680.819 350.645 620.794 800.450 700.802 530.587 600.604 490.945 710.464 660.201 890.554 780.840 420.723 380.732 720.602 590.907 430.822 580.603 74
VACNN++0.684 550.728 760.757 620.776 590.690 450.804 750.464 630.816 460.577 660.587 580.945 710.508 510.276 520.671 420.710 690.663 670.750 650.589 660.881 650.832 520.653 55
KP-FCNN0.684 550.847 290.758 610.784 560.647 600.814 670.473 570.772 590.605 500.594 560.935 910.450 750.181 970.587 650.805 520.690 570.785 400.614 520.882 640.819 600.632 63
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DGNet0.684 550.712 850.784 450.782 580.658 540.835 430.499 470.823 450.641 340.597 540.950 560.487 570.281 480.575 700.619 850.647 750.764 530.620 510.871 800.846 470.688 45
PointContrast_LA_SEM0.683 580.757 630.784 450.786 540.639 640.824 550.408 870.775 580.604 520.541 670.934 950.532 410.269 590.552 790.777 570.645 780.793 340.640 410.913 420.824 550.671 49
Superpoint Network0.683 580.851 280.728 790.800 500.653 570.806 730.468 600.804 510.572 670.602 510.946 680.453 740.239 720.519 870.822 460.689 590.762 560.595 630.895 540.827 540.630 64
VI-PointConv0.676 600.770 580.754 630.783 570.621 680.814 670.552 180.758 630.571 700.557 630.954 410.529 420.268 610.530 850.682 750.675 620.719 750.603 580.888 600.833 500.665 51
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 610.789 450.748 680.763 640.635 660.814 670.407 890.747 670.581 640.573 600.950 560.484 580.271 570.607 610.754 600.649 720.774 450.596 610.883 630.823 560.606 71
SALANet0.670 620.816 390.770 540.768 610.652 580.807 720.451 670.747 670.659 280.545 660.924 1010.473 630.149 1090.571 720.811 510.635 820.746 660.623 490.892 570.794 760.570 84
O3DSeg0.668 630.822 370.771 530.496 1130.651 590.833 450.541 230.761 620.555 760.611 440.966 150.489 560.370 60.388 1060.580 890.776 170.751 630.570 720.956 70.817 610.646 58
PointConvpermissive0.666 640.781 490.759 590.699 770.644 630.822 570.475 560.779 570.564 730.504 840.953 450.428 840.203 880.586 670.754 600.661 680.753 620.588 670.902 480.813 640.642 59
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 640.703 870.781 470.751 680.655 560.830 480.471 580.769 600.474 970.537 690.951 520.475 620.279 500.635 520.698 740.675 620.751 630.553 830.816 960.806 660.703 41
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PPCNN++permissive0.663 660.746 660.708 820.722 700.638 650.820 600.451 670.566 1030.599 550.541 670.950 560.510 500.313 300.648 480.819 490.616 870.682 900.590 650.869 810.810 650.656 54
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
MVF-GNN0.658 670.558 1090.751 660.655 920.690 450.722 1020.453 660.867 240.579 650.576 590.893 1130.523 440.293 400.733 350.571 910.692 540.659 970.606 560.875 710.804 680.668 50
DCM-Net0.658 670.778 500.702 850.806 460.619 690.813 700.468 600.693 830.494 900.524 750.941 830.449 760.298 370.510 890.821 470.675 620.727 740.568 750.826 940.803 690.637 61
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 690.698 890.743 730.650 940.564 860.820 600.505 410.758 630.631 380.479 880.945 710.480 600.226 740.572 710.774 580.690 570.735 700.614 520.853 880.776 910.597 77
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 700.752 640.734 770.664 900.583 810.815 660.399 910.754 650.639 350.535 710.942 810.470 640.309 320.665 430.539 930.650 710.708 800.635 430.857 870.793 780.642 59
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 710.778 500.731 780.699 770.577 820.829 490.446 720.736 710.477 960.523 770.945 710.454 710.269 590.484 960.749 630.618 850.738 680.599 600.827 930.792 810.621 66
PointConv-SFPN0.641 720.776 520.703 840.721 710.557 890.826 520.451 670.672 880.563 740.483 870.943 800.425 870.162 1040.644 490.726 650.659 690.709 790.572 710.875 710.786 860.559 90
MVPNetpermissive0.641 720.831 330.715 800.671 870.590 770.781 860.394 930.679 850.642 330.553 640.937 880.462 670.256 650.649 460.406 1060.626 830.691 870.666 330.877 690.792 810.608 70
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 740.717 830.701 860.692 800.576 830.801 760.467 620.716 760.563 740.459 940.953 450.429 830.169 1010.581 680.854 360.605 880.710 770.550 850.894 560.793 780.575 82
FPConvpermissive0.639 750.785 470.760 580.713 750.603 720.798 780.392 950.534 1080.603 530.524 750.948 630.457 690.250 670.538 830.723 670.598 920.696 850.614 520.872 770.799 710.567 87
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 760.797 430.769 550.641 990.590 770.820 600.461 640.537 1070.637 360.536 700.947 650.388 970.206 850.656 440.668 790.647 750.732 720.585 690.868 820.793 780.473 110
PointSPNet0.637 770.734 720.692 930.714 740.576 830.797 790.446 720.743 690.598 560.437 990.942 810.403 930.150 1080.626 560.800 550.649 720.697 840.557 810.846 900.777 900.563 88
SConv0.636 780.830 340.697 890.752 670.572 850.780 880.445 740.716 760.529 800.530 720.951 520.446 780.170 1000.507 910.666 800.636 810.682 900.541 910.886 610.799 710.594 78
Supervoxel-CNN0.635 790.656 950.711 810.719 720.613 700.757 970.444 770.765 610.534 790.566 610.928 990.478 610.272 550.636 510.531 950.664 660.645 1010.508 990.864 840.792 810.611 67
joint point-basedpermissive0.634 800.614 1030.778 480.667 890.633 670.825 530.420 850.804 510.467 990.561 620.951 520.494 530.291 420.566 730.458 1010.579 980.764 530.559 800.838 910.814 620.598 76
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 810.731 740.688 960.675 840.591 760.784 850.444 770.565 1040.610 460.492 850.949 600.456 700.254 660.587 650.706 700.599 910.665 960.612 550.868 820.791 840.579 81
PointNet2-SFPN0.631 820.771 560.692 930.672 850.524 950.837 400.440 790.706 810.538 780.446 960.944 770.421 890.219 790.552 790.751 620.591 940.737 690.543 900.901 500.768 930.557 91
APCF-Net0.631 820.742 690.687 980.672 850.557 890.792 830.408 870.665 900.545 770.508 810.952 500.428 840.186 950.634 530.702 720.620 840.706 810.555 820.873 750.798 730.581 80
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
3DSM_DMMF0.631 820.626 1000.745 710.801 490.607 710.751 980.506 400.729 740.565 720.491 860.866 1160.434 790.197 920.595 630.630 840.709 460.705 820.560 780.875 710.740 1010.491 105
FusionAwareConv0.630 850.604 1050.741 750.766 630.590 770.747 990.501 430.734 720.503 890.527 730.919 1050.454 710.323 270.550 810.420 1050.678 610.688 880.544 880.896 530.795 750.627 65
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 860.800 420.625 1080.719 720.545 920.806 730.445 740.597 980.448 1040.519 790.938 870.481 590.328 250.489 950.499 1000.657 700.759 580.592 640.881 650.797 740.634 62
SegGroup_sempermissive0.627 870.818 380.747 700.701 760.602 730.764 940.385 990.629 950.490 920.508 810.931 980.409 920.201 890.564 740.725 660.618 850.692 860.539 920.873 750.794 760.548 94
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 880.830 340.694 910.757 650.563 870.772 920.448 710.647 930.520 830.509 800.949 600.431 820.191 930.496 930.614 860.647 750.672 940.535 950.876 700.783 870.571 83
dtc_net0.625 880.703 870.751 660.794 520.535 930.848 270.480 550.676 870.528 810.469 910.944 770.454 710.004 1210.464 980.636 830.704 500.758 590.548 870.924 300.787 850.492 104
Weakly-Openseg v30.625 880.924 80.787 430.620 1010.555 910.811 710.393 940.666 890.382 1120.520 780.953 450.250 1160.208 830.604 620.670 770.644 790.742 670.538 930.919 360.803 690.513 102
HPEIN0.618 910.729 750.668 990.647 960.597 750.766 930.414 860.680 840.520 830.525 740.946 680.432 800.215 810.493 940.599 870.638 800.617 1060.570 720.897 520.806 660.605 73
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-GCNpermissive0.610 920.858 270.772 510.489 1140.532 940.792 830.404 900.643 940.570 710.507 830.935 910.414 910.046 1180.510 890.702 720.602 900.705 820.549 860.859 860.773 920.534 97
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 930.760 610.667 1000.649 950.521 960.793 810.457 650.648 920.528 810.434 1010.947 650.401 940.153 1070.454 990.721 680.648 740.717 760.536 940.904 450.765 940.485 106
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 940.634 990.743 730.697 790.601 740.781 860.437 810.585 1010.493 910.446 960.933 960.394 950.011 1200.654 450.661 820.603 890.733 710.526 960.832 920.761 960.480 107
LAP-D0.594 950.720 810.692 930.637 1000.456 1050.773 910.391 970.730 730.587 600.445 980.940 850.381 980.288 430.434 1020.453 1030.591 940.649 990.581 700.777 1000.749 1000.610 69
DPC0.592 960.720 810.700 870.602 1050.480 1010.762 960.380 1000.713 790.585 630.437 990.940 850.369 1000.288 430.434 1020.509 990.590 960.639 1040.567 760.772 1010.755 980.592 79
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 970.766 600.659 1030.683 820.470 1040.740 1010.387 980.620 970.490 920.476 890.922 1030.355 1030.245 700.511 880.511 980.571 990.643 1020.493 1030.872 770.762 950.600 75
ROSMRF0.580 980.772 550.707 830.681 830.563 870.764 940.362 1020.515 1090.465 1000.465 930.936 900.427 860.207 840.438 1000.577 900.536 1020.675 930.486 1040.723 1070.779 880.524 99
SD-DETR0.576 990.746 660.609 1120.445 1180.517 970.643 1130.366 1010.714 780.456 1020.468 920.870 1150.432 800.264 620.558 770.674 760.586 970.688 880.482 1050.739 1050.733 1030.537 96
SQN_0.1%0.569 1000.676 910.696 900.657 910.497 980.779 890.424 830.548 1050.515 850.376 1060.902 1120.422 880.357 100.379 1070.456 1020.596 930.659 970.544 880.685 1100.665 1140.556 92
TextureNetpermissive0.566 1010.672 930.664 1010.671 870.494 990.719 1030.445 740.678 860.411 1100.396 1040.935 910.356 1020.225 760.412 1040.535 940.565 1000.636 1050.464 1070.794 990.680 1110.568 86
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 1020.648 960.700 870.770 600.586 800.687 1070.333 1060.650 910.514 860.475 900.906 1090.359 1010.223 780.340 1090.442 1040.422 1130.668 950.501 1000.708 1080.779 880.534 97
Pointnet++ & Featurepermissive0.557 1030.735 710.661 1020.686 810.491 1000.744 1000.392 950.539 1060.451 1030.375 1070.946 680.376 990.205 860.403 1050.356 1090.553 1010.643 1020.497 1010.824 950.756 970.515 100
GMLPs0.538 1040.495 1140.693 920.647 960.471 1030.793 810.300 1090.477 1100.505 880.358 1080.903 1110.327 1060.081 1150.472 970.529 960.448 1110.710 770.509 970.746 1030.737 1020.554 93
PanopticFusion-label0.529 1050.491 1150.688 960.604 1040.386 1100.632 1140.225 1200.705 820.434 1070.293 1140.815 1180.348 1040.241 710.499 920.669 780.507 1040.649 990.442 1130.796 980.602 1180.561 89
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 1060.676 910.591 1150.609 1020.442 1060.774 900.335 1050.597 980.422 1090.357 1090.932 970.341 1050.094 1140.298 1110.528 970.473 1090.676 920.495 1020.602 1160.721 1060.349 118
Online SegFusion0.515 1070.607 1040.644 1060.579 1070.434 1070.630 1150.353 1030.628 960.440 1050.410 1020.762 1210.307 1080.167 1020.520 860.403 1070.516 1030.565 1090.447 1110.678 1110.701 1080.514 101
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 1080.558 1090.608 1130.424 1200.478 1020.690 1060.246 1160.586 1000.468 980.450 950.911 1070.394 950.160 1050.438 1000.212 1160.432 1120.541 1140.475 1060.742 1040.727 1040.477 108
PCNN0.498 1090.559 1080.644 1060.560 1090.420 1090.711 1050.229 1180.414 1110.436 1060.352 1100.941 830.324 1070.155 1060.238 1160.387 1080.493 1050.529 1150.509 970.813 970.751 990.504 103
3DMV0.484 1100.484 1160.538 1180.643 980.424 1080.606 1180.310 1070.574 1020.433 1080.378 1050.796 1190.301 1090.214 820.537 840.208 1170.472 1100.507 1180.413 1160.693 1090.602 1180.539 95
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 1110.577 1070.611 1110.356 1220.321 1180.715 1040.299 1110.376 1150.328 1180.319 1120.944 770.285 1110.164 1030.216 1190.229 1140.484 1070.545 1130.456 1090.755 1020.709 1070.475 109
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 1120.679 900.604 1140.578 1080.380 1110.682 1080.291 1120.106 1220.483 950.258 1200.920 1040.258 1150.025 1190.231 1180.325 1100.480 1080.560 1110.463 1080.725 1060.666 1130.231 122
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 1130.474 1170.623 1090.463 1160.366 1130.651 1110.310 1070.389 1140.349 1160.330 1110.937 880.271 1130.126 1110.285 1120.224 1150.350 1180.577 1080.445 1120.625 1140.723 1050.394 114
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
PNET20.442 1140.548 1110.548 1170.597 1060.363 1140.628 1160.300 1090.292 1170.374 1130.307 1130.881 1140.268 1140.186 950.238 1160.204 1180.407 1140.506 1190.449 1100.667 1120.620 1170.462 112
SurfaceConvPF0.442 1140.505 1130.622 1100.380 1210.342 1160.654 1100.227 1190.397 1130.367 1140.276 1160.924 1010.240 1170.198 910.359 1080.262 1120.366 1150.581 1070.435 1140.640 1130.668 1120.398 113
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 1160.437 1190.646 1050.474 1150.369 1120.645 1120.353 1030.258 1190.282 1210.279 1150.918 1060.298 1100.147 1100.283 1130.294 1110.487 1060.562 1100.427 1150.619 1150.633 1160.352 117
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1170.525 1120.647 1040.522 1100.324 1170.488 1220.077 1230.712 800.353 1150.401 1030.636 1230.281 1120.176 980.340 1090.565 920.175 1220.551 1120.398 1170.370 1230.602 1180.361 116
SPLAT Netcopyleft0.393 1180.472 1180.511 1190.606 1030.311 1190.656 1090.245 1170.405 1120.328 1180.197 1210.927 1000.227 1190.000 1230.001 1240.249 1130.271 1210.510 1160.383 1190.593 1170.699 1090.267 120
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 1190.297 1210.491 1200.432 1190.358 1150.612 1170.274 1140.116 1210.411 1100.265 1170.904 1100.229 1180.079 1160.250 1140.185 1190.320 1190.510 1160.385 1180.548 1180.597 1210.394 114
PointNet++permissive0.339 1200.584 1060.478 1210.458 1170.256 1210.360 1230.250 1150.247 1200.278 1220.261 1190.677 1220.183 1200.117 1120.212 1200.145 1210.364 1160.346 1230.232 1230.548 1180.523 1220.252 121
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
GrowSP++0.323 1210.114 1230.589 1160.499 1120.147 1230.555 1190.290 1130.336 1160.290 1200.262 1180.865 1170.102 1230.000 1230.037 1220.000 1240.000 1240.462 1200.381 1200.389 1220.664 1150.473 110
SSC-UNetpermissive0.308 1220.353 1200.290 1230.278 1230.166 1220.553 1200.169 1220.286 1180.147 1230.148 1230.908 1080.182 1210.064 1170.023 1230.018 1230.354 1170.363 1210.345 1210.546 1200.685 1100.278 119
ScanNetpermissive0.306 1230.203 1220.366 1220.501 1110.311 1190.524 1210.211 1210.002 1240.342 1170.189 1220.786 1200.145 1220.102 1130.245 1150.152 1200.318 1200.348 1220.300 1220.460 1210.437 1230.182 123
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 1240.000 1240.041 1240.172 1240.030 1240.062 1240.001 1240.035 1230.004 1240.051 1240.143 1240.019 1240.003 1220.041 1210.050 1220.003 1230.054 1240.018 1240.005 1240.264 1240.082 124


3D Semantic Instance Benchmark

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




Method Infoavg ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Competitor-MAFT0.816 11.000 10.983 40.872 110.718 60.941 20.588 50.652 410.819 30.776 30.720 60.780 60.769 121.000 10.797 110.813 310.798 91.000 10.659 5
PointRel0.816 11.000 10.971 90.908 60.743 20.923 90.573 90.714 220.695 200.734 110.747 20.725 130.809 11.000 10.814 90.899 50.820 41.000 10.610 19
: Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation. CVPR 2025
Spherical Mask(CtoF)0.812 31.000 10.973 80.852 160.718 70.917 110.574 70.677 310.748 130.729 150.715 90.795 30.809 11.000 10.831 40.854 110.787 131.000 10.638 8
PointComp0.811 40.850 600.969 100.864 140.739 30.946 10.539 150.671 340.835 10.700 190.742 30.817 10.766 131.000 10.755 220.909 10.808 71.000 10.687 2
EV3D0.811 41.000 10.968 110.852 160.717 80.921 100.574 80.677 310.748 130.730 140.703 150.795 30.809 11.000 10.831 40.854 110.778 171.000 10.638 9
VDG-Uni3DSeg0.804 61.000 10.990 10.886 90.688 210.912 130.602 20.703 260.786 80.771 40.708 120.700 180.669 270.981 410.789 170.903 20.772 201.000 10.609 20
SIM3D0.803 71.000 10.967 120.863 150.692 200.924 80.552 130.732 210.667 250.732 130.662 190.796 20.789 91.000 10.803 100.864 80.766 231.000 10.643 7
OneFormer3Dcopyleft0.801 81.000 10.973 70.909 50.698 160.928 60.582 60.668 370.685 210.780 20.687 170.698 220.702 161.000 10.794 130.900 40.784 150.986 550.635 10
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
Competitor-SPFormer0.800 91.000 10.986 30.845 180.705 140.915 120.532 160.733 200.757 120.733 120.708 110.698 210.648 390.981 410.890 10.830 210.796 100.997 420.644 6
UniPerception0.800 91.000 10.930 140.872 110.727 50.862 270.454 220.764 130.820 20.746 80.706 130.750 80.772 100.926 490.764 200.818 290.826 20.997 420.660 4
InsSSM0.799 111.000 10.915 160.710 440.729 40.925 70.664 10.670 350.770 90.766 50.739 40.737 90.700 171.000 10.792 140.829 230.815 50.997 420.625 12
Lei Yao, Yi Wang, Moyun Liu, Lap-Pui Chau: SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation. TCSVT, 2024
DCD0.798 121.000 10.878 230.792 300.693 190.936 30.596 30.685 300.663 270.736 90.717 70.788 50.693 221.000 10.825 70.840 170.837 11.000 10.689 1
TST3D0.795 131.000 10.929 150.918 40.709 110.884 220.596 40.704 250.769 100.734 100.644 240.699 200.751 141.000 10.794 120.876 70.757 260.997 420.550 36
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
MG-Former0.791 141.000 10.980 60.837 210.626 290.897 150.543 140.759 150.800 70.766 60.659 200.769 70.697 201.000 10.791 150.707 520.791 121.000 10.610 18
ExtMask3D0.789 151.000 10.988 20.756 370.706 130.912 140.429 230.647 430.806 60.755 70.673 180.689 230.772 111.000 10.789 160.852 130.811 61.000 10.617 15
Queryformer0.787 161.000 10.933 130.601 540.754 10.886 200.558 120.661 390.767 110.665 220.716 80.639 290.808 51.000 10.844 30.897 60.804 81.000 10.624 13
MAFT0.786 171.000 10.894 210.807 250.694 180.893 180.486 180.674 330.740 150.786 10.704 140.727 120.739 151.000 10.707 280.849 150.756 271.000 10.685 3
KmaxOneFormerNetpermissive0.783 180.903 580.981 50.794 290.706 120.931 50.561 110.701 270.706 180.727 160.697 160.731 110.689 241.000 10.856 20.750 430.761 251.000 10.599 24
Mask3D0.780 191.000 10.786 470.716 420.696 170.885 210.500 170.714 220.810 50.672 210.715 90.679 240.809 11.000 10.831 40.833 200.787 131.000 10.602 22
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SPFormerpermissive0.770 200.903 580.903 180.806 260.609 360.886 190.568 100.815 60.705 190.711 170.655 210.652 280.685 251.000 10.789 180.809 320.776 191.000 10.583 28
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SoftGroup++0.769 211.000 10.803 400.937 10.684 220.865 240.213 390.870 20.664 260.571 290.758 10.702 170.807 61.000 10.653 350.902 30.792 111.000 10.626 11
SoftGrouppermissive0.761 221.000 10.808 360.845 180.716 90.862 260.243 360.824 40.655 290.620 230.734 50.699 190.791 80.981 410.716 250.844 160.769 211.000 10.594 26
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
ISBNetpermissive0.757 231.000 10.904 170.731 400.678 230.895 160.458 200.644 450.670 240.710 180.620 290.732 100.650 291.000 10.756 210.778 350.779 161.000 10.614 16
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
TD3Dpermissive0.751 241.000 10.774 480.867 130.621 310.934 40.404 240.706 240.812 40.605 260.633 270.626 300.690 231.000 10.640 370.820 260.777 181.000 10.612 17
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
PBNetpermissive0.747 251.000 10.818 320.837 220.713 100.844 290.457 210.647 430.711 170.614 240.617 310.657 270.650 291.000 10.692 290.822 250.765 241.000 10.595 25
Weiguang Zhao, Yuyao Yan, Chaolong Yang, Jianan Ye, Xi Yang, Kaizhu Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
GraphCut0.732 261.000 10.788 450.724 410.642 280.859 280.248 350.787 110.618 320.596 270.653 230.722 150.583 511.000 10.766 190.861 90.825 31.000 10.504 42
IPCA-Inst0.731 271.000 10.788 460.884 100.698 150.788 450.252 340.760 140.646 300.511 370.637 260.665 260.804 71.000 10.644 360.778 360.747 291.000 10.561 32
TopoSeg0.725 281.000 10.806 390.933 20.668 250.758 500.272 330.734 190.630 310.549 330.654 220.606 310.697 210.966 460.612 410.839 180.754 281.000 10.573 29
DKNet0.718 291.000 10.814 330.782 310.619 330.872 230.224 370.751 170.569 360.677 200.585 360.724 140.633 410.981 410.515 510.819 270.736 301.000 10.617 14
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
SSEC0.707 301.000 10.850 250.924 30.648 260.747 530.162 410.862 30.572 350.520 350.624 280.549 340.649 381.000 10.560 460.706 530.768 221.000 10.591 27
HAISpermissive0.699 311.000 10.849 260.820 230.675 240.808 390.279 310.757 160.465 420.517 360.596 330.559 330.600 451.000 10.654 340.767 380.676 340.994 510.560 33
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNetpermissive0.698 321.000 10.697 640.888 80.556 430.803 400.387 250.626 470.417 470.556 320.585 370.702 160.600 451.000 10.824 80.720 510.692 321.000 10.509 41
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
DualGroup0.694 331.000 10.799 420.811 240.622 300.817 340.376 260.805 90.590 340.487 410.568 400.525 380.650 290.835 590.600 420.829 220.655 371.000 10.526 38
ODIN - Inspermissive0.693 341.000 10.880 220.647 490.620 320.779 470.336 280.501 620.681 220.577 280.595 340.679 250.683 261.000 10.709 270.816 300.637 410.770 710.557 34
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024
DANCENET0.680 351.000 10.807 370.733 390.600 370.768 490.375 270.543 550.538 370.610 250.599 320.498 390.632 430.981 410.739 240.856 100.633 440.882 660.454 51
SphereSeg0.680 351.000 10.856 240.744 380.618 340.893 170.151 420.651 420.713 160.537 340.579 390.430 480.651 281.000 10.389 620.744 460.697 310.991 530.601 23
Box2Mask0.677 371.000 10.847 270.771 330.509 520.816 350.277 320.558 540.482 390.562 310.640 250.448 440.700 171.000 10.666 300.852 140.578 510.997 420.488 46
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
OccuSeg+instance0.672 381.000 10.758 560.682 460.576 410.842 300.477 190.504 610.524 380.567 300.585 380.451 430.557 531.000 10.751 230.797 330.563 541.000 10.467 50
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group0.664 391.000 10.822 310.764 360.616 350.815 360.139 460.694 290.597 330.459 450.566 410.599 320.600 450.516 690.715 260.819 280.635 421.000 10.603 21
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
INS-Conv-instance0.657 401.000 10.760 540.667 480.581 390.863 250.323 290.655 400.477 400.473 430.549 430.432 470.650 291.000 10.655 330.738 470.585 500.944 580.472 49
CSC-Pretrained0.648 411.000 10.810 340.768 340.523 500.813 370.143 450.819 50.389 500.422 540.511 470.443 450.650 291.000 10.624 390.732 480.634 431.000 10.375 58
PE0.645 421.000 10.773 500.798 280.538 450.786 460.088 540.799 100.350 540.435 520.547 440.545 350.646 400.933 480.562 450.761 410.556 590.997 420.501 44
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN0.643 431.000 10.758 550.582 600.539 440.826 330.046 590.765 120.372 520.436 510.588 350.539 370.650 291.000 10.577 430.750 440.653 390.997 420.495 45
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
Dyco3Dcopyleft0.641 441.000 10.841 280.893 70.531 470.802 410.115 510.588 520.448 440.438 490.537 460.430 490.550 540.857 510.534 490.764 400.657 360.987 540.568 30
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN0.638 451.000 10.895 200.800 270.480 560.676 580.144 440.737 180.354 530.447 460.400 600.365 550.700 171.000 10.569 440.836 190.599 461.000 10.473 48
PointGroup0.636 461.000 10.765 510.624 510.505 540.797 420.116 500.696 280.384 510.441 470.559 420.476 410.596 481.000 10.666 300.756 420.556 580.997 420.513 40
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
DD-UNet+Group0.635 470.667 620.797 440.714 430.562 420.774 480.146 430.810 80.429 460.476 420.546 450.399 510.633 411.000 10.632 380.722 500.609 451.000 10.514 39
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
Mask3D_evaluation0.631 481.000 10.829 300.606 530.646 270.836 310.068 550.511 590.462 430.507 380.619 300.389 530.610 441.000 10.432 570.828 240.673 350.788 700.552 35
DENet0.629 491.000 10.797 430.608 520.589 380.627 620.219 380.882 10.310 560.402 590.383 620.396 520.650 291.000 10.663 320.543 700.691 331.000 10.568 31
3D-MPA0.611 501.000 10.833 290.765 350.526 490.756 510.136 480.588 520.470 410.438 500.432 560.358 570.650 290.857 510.429 580.765 390.557 571.000 10.430 53
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
OSIS0.605 511.000 10.801 410.599 550.535 460.728 550.286 300.436 660.679 230.491 390.433 540.256 590.404 660.857 510.620 400.724 490.510 641.000 10.539 37
AOIA0.601 521.000 10.761 530.687 450.485 550.828 320.008 660.663 380.405 490.405 580.425 570.490 400.596 480.714 620.553 480.779 340.597 470.992 520.424 55
PCJC0.578 531.000 10.810 350.583 590.449 590.813 380.042 600.603 500.341 550.490 400.465 510.410 500.650 290.835 590.264 680.694 570.561 550.889 630.504 43
SSEN0.575 541.000 10.761 520.473 620.477 570.795 430.066 560.529 570.658 280.460 440.461 520.380 540.331 680.859 500.401 610.692 590.653 381.000 10.348 60
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RWSeg0.567 550.528 720.708 630.626 500.580 400.745 540.063 570.627 460.240 600.400 600.497 480.464 420.515 551.000 10.475 530.745 450.571 521.000 10.429 54
NeuralBF0.555 560.667 620.896 190.843 200.517 510.751 520.029 610.519 580.414 480.439 480.465 500.000 780.484 570.857 510.287 660.693 580.651 401.000 10.485 47
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
MTML0.549 571.000 10.807 380.588 580.327 640.647 600.004 680.815 70.180 630.418 550.364 640.182 620.445 601.000 10.442 560.688 600.571 531.000 10.396 56
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
ClickSeg_Instance0.539 581.000 10.621 670.300 650.530 480.698 560.127 490.533 560.222 610.430 530.400 590.365 550.574 520.938 470.472 540.659 620.543 600.944 580.347 61
One_Thing_One_Clickpermissive0.529 590.667 620.718 590.777 320.399 600.683 570.000 710.669 360.138 660.391 610.374 630.539 360.360 670.641 660.556 470.774 370.593 480.997 420.251 66
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Sparse R-CNN0.515 601.000 10.538 720.282 660.468 580.790 440.173 400.345 680.429 450.413 570.484 490.176 630.595 500.591 670.522 500.668 610.476 650.986 560.327 62
Occipital-SCS0.512 611.000 10.716 600.509 610.506 530.611 630.092 530.602 510.177 640.346 640.383 610.165 640.442 610.850 580.386 630.618 660.543 610.889 630.389 57
3D-BoNet0.488 621.000 10.672 660.590 570.301 660.484 730.098 520.620 480.306 570.341 650.259 680.125 660.434 630.796 610.402 600.499 720.513 630.909 620.439 52
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
PanopticFusion-inst0.478 630.667 620.712 620.595 560.259 690.550 690.000 710.613 490.175 650.250 700.434 530.437 460.411 650.857 510.485 520.591 690.267 750.944 580.359 59
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
SPG_WSIS0.470 640.667 620.685 650.677 470.372 620.562 670.000 710.482 630.244 590.316 670.298 650.052 730.442 620.857 510.267 670.702 540.559 561.000 10.287 64
SALoss-ResNet0.459 651.000 10.737 580.159 760.259 680.587 650.138 470.475 640.217 620.416 560.408 580.128 650.315 690.714 620.411 590.536 710.590 490.873 670.304 63
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
MASCpermissive0.447 660.528 720.555 700.381 630.382 610.633 610.002 690.509 600.260 580.361 630.432 550.327 580.451 590.571 680.367 640.639 640.386 660.980 570.276 65
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_inspermissive0.445 670.667 620.773 490.185 730.317 650.656 590.000 710.407 670.134 670.381 620.267 670.217 610.476 580.714 620.452 550.629 650.514 621.000 10.222 69
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
3D-SISpermissive0.382 681.000 10.432 750.245 680.190 700.577 660.013 650.263 700.033 730.320 660.240 690.075 690.422 640.857 510.117 730.699 550.271 740.883 650.235 68
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3Dcopyleft0.323 690.667 620.542 710.264 670.157 730.550 680.000 710.205 730.009 750.270 690.218 700.075 690.500 560.688 650.007 790.698 560.301 710.459 760.200 70
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone0.319 700.667 620.715 610.233 690.189 710.479 740.008 660.218 710.067 720.201 720.173 710.107 670.123 740.438 700.150 700.615 670.355 670.916 610.093 78
R-PointNet0.306 710.500 740.405 760.311 640.348 630.589 640.054 580.068 760.126 680.283 680.290 660.028 740.219 720.214 730.331 650.396 760.275 720.821 690.245 67
Region-18class0.284 720.250 780.751 570.228 710.270 670.521 700.000 710.468 650.008 770.205 710.127 720.000 780.068 760.070 770.262 690.652 630.323 690.740 720.173 71
SemRegionNet-20cls0.250 730.333 750.613 680.229 700.163 720.493 710.000 710.304 690.107 690.147 750.100 740.052 720.231 700.119 750.039 750.445 740.325 680.654 730.141 74
tmp0.248 740.667 620.437 740.188 720.153 740.491 720.000 710.208 720.094 710.153 740.099 750.057 710.217 730.119 750.039 750.466 730.302 700.640 740.140 75
3D-BEVIS0.248 740.667 620.566 690.076 770.035 790.394 770.027 630.035 780.098 700.099 770.030 780.025 750.098 750.375 720.126 720.604 680.181 770.854 680.171 72
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sem_Recon_ins0.227 760.764 610.486 730.069 780.098 760.426 760.017 640.067 770.015 740.172 730.100 730.096 680.054 780.183 740.135 710.366 770.260 760.614 750.168 73
ASIS0.199 770.333 750.253 780.167 750.140 750.438 750.000 710.177 740.008 760.121 760.069 760.004 770.231 710.429 710.036 770.445 750.273 730.333 780.119 77
Sgpn_scannet0.143 780.208 790.390 770.169 740.065 770.275 780.029 620.069 750.000 780.087 780.043 770.014 760.027 790.000 780.112 740.351 780.168 780.438 770.138 76
MaskRCNN 2d->3d Proj0.058 790.333 750.002 790.000 790.053 780.002 790.002 700.021 790.000 780.045 790.024 790.238 600.065 770.000 780.014 780.107 790.020 790.110 790.006 79


2D Semantic Label Benchmark

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 20.512 10.422 190.898 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 30.481 20.451 150.769 50.656 30.567 40.931 30.395 60.390 60.700 40.534 40.689 110.770 20.574 30.865 110.831 30.675 6
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MVF-GNN（2D）0.636 30.606 160.794 40.434 170.688 10.337 80.464 140.798 40.632 50.589 30.908 90.420 20.329 140.743 20.594 20.738 20.676 50.527 40.906 20.818 60.715 3
CU-Hybrid-2D Net0.636 30.825 20.820 20.179 250.648 40.463 30.549 20.742 90.676 20.628 20.961 10.420 20.379 70.684 80.381 200.732 30.723 30.599 20.827 180.851 20.634 9
DVEFormer0.626 50.616 120.764 60.690 50.583 110.322 140.540 30.809 30.593 70.502 120.900 140.374 90.433 30.660 90.528 50.665 190.663 60.491 90.871 100.810 90.705 4
CMX0.613 60.681 90.725 130.502 130.634 60.297 190.478 120.830 20.651 40.537 70.924 40.375 70.315 160.686 70.451 150.714 50.543 230.504 60.894 70.823 50.688 5
DMMF_3d0.605 70.651 100.744 110.782 30.637 50.387 40.536 50.732 100.590 80.540 60.856 230.359 120.306 170.596 160.539 30.627 220.706 40.497 80.785 230.757 210.476 24
EMSANet0.600 80.716 40.746 100.395 200.614 90.382 50.523 60.713 130.571 120.503 100.922 70.404 50.397 50.655 100.400 170.626 230.663 60.469 140.900 40.827 40.577 16
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
MCA-Net0.595 90.533 220.756 90.746 40.590 100.334 100.506 90.670 170.587 90.500 130.905 110.366 110.352 100.601 150.506 90.669 170.648 100.501 70.839 170.769 170.516 23
RFBNet0.592 100.616 120.758 80.659 60.581 120.330 110.469 130.655 200.543 150.524 80.924 40.355 140.336 120.572 190.479 110.671 150.648 100.480 110.814 210.814 70.614 12
FAN_NV_RVC0.586 110.510 230.764 60.079 280.620 80.330 110.494 100.753 70.573 100.556 50.884 180.405 40.303 180.718 30.452 140.672 140.658 80.509 50.898 50.813 80.727 2
WSGFormer0.585 120.706 50.708 180.434 170.574 140.283 220.538 40.759 60.542 170.482 170.924 40.351 160.333 130.614 120.393 180.692 100.551 220.461 150.874 90.809 100.673 7
DCRedNet0.583 130.682 80.723 140.542 120.510 220.310 160.451 150.668 180.549 140.520 90.920 80.375 70.446 20.528 220.417 160.670 160.577 190.478 120.862 120.806 110.628 11
MIX6D_RVC0.582 140.695 60.687 190.225 230.632 70.328 130.550 10.748 80.623 60.494 160.890 160.350 170.254 250.688 60.454 130.716 40.597 180.489 100.881 80.768 180.575 17
SSMAcopyleft0.577 150.695 60.716 160.439 150.563 160.314 150.444 170.719 110.551 130.503 100.887 170.346 180.348 110.603 140.353 220.709 60.600 160.457 160.901 30.786 130.599 15
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DMMF0.567 160.623 110.767 50.238 220.571 150.347 60.413 210.719 110.472 220.418 240.895 150.357 130.260 240.696 50.523 80.666 180.642 120.437 200.895 60.793 120.603 14
UNIV_CNP_RVC_UE0.566 170.569 210.686 210.435 160.524 190.294 200.421 200.712 140.543 150.463 190.872 190.320 190.363 90.611 130.477 120.686 120.627 130.443 190.862 120.775 160.639 8
EMSAFormer0.564 180.581 180.736 120.564 110.546 180.219 250.517 70.675 160.486 210.427 230.904 120.352 150.320 150.589 170.528 50.708 70.464 260.413 240.847 160.786 130.611 13
SN_RN152pyrx8_RVCcopyleft0.546 190.572 190.663 230.638 80.518 200.298 180.366 260.633 230.510 190.446 210.864 210.296 220.267 210.542 210.346 230.704 80.575 200.431 210.853 150.766 190.630 10
UDSSEG_RVC0.545 200.610 150.661 240.588 90.556 170.268 230.482 110.642 220.572 110.475 180.836 250.312 200.367 80.630 110.189 250.639 210.495 250.452 170.826 190.756 220.541 19
segfomer with 6d0.542 210.594 170.687 190.146 260.579 130.308 170.515 80.703 150.472 220.498 140.868 200.369 100.282 190.589 170.390 190.701 90.556 210.416 230.860 140.759 200.539 21
FuseNetpermissive0.535 220.570 200.681 220.182 240.512 210.290 210.431 180.659 190.504 200.495 150.903 130.308 210.428 40.523 230.365 210.676 130.621 150.470 130.762 240.779 150.541 19
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 230.613 140.722 150.418 190.358 280.337 80.370 250.479 260.443 240.368 260.907 100.207 250.213 270.464 260.525 70.618 240.657 90.450 180.788 220.721 250.408 27
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 240.481 260.612 250.579 100.456 240.343 70.384 230.623 240.525 180.381 250.845 240.254 240.264 230.557 200.182 260.581 260.598 170.429 220.760 250.661 270.446 26
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 250.505 240.709 170.092 270.427 250.241 240.411 220.654 210.385 280.457 200.861 220.053 280.279 200.503 240.481 100.645 200.626 140.365 260.748 260.725 240.529 22
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 260.490 250.581 260.289 210.507 230.067 280.379 240.610 250.417 260.435 220.822 270.278 230.267 210.503 240.228 240.616 250.533 240.375 250.820 200.729 230.560 18
Enet (reimpl)0.376 270.264 280.452 280.452 140.365 260.181 260.143 280.456 270.409 270.346 270.769 280.164 260.218 260.359 270.123 280.403 280.381 280.313 280.571 270.685 260.472 25
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)permissive0.330 280.293 270.521 270.657 70.361 270.161 270.250 270.004 280.440 250.183 280.836 250.125 270.060 280.319 280.132 270.417 270.412 270.344 270.541 280.427 280.109 28
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17


2D Semantic Instance Benchmark

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
EMSANet (Instance)0.241 10.401 10.439 10.085 10.242 10.220 10.081 10.289 20.117 20.121 10.182 10.126 10.346 10.181 20.181 20.358 10.156 10.675 20.131 1
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
UniDet_RVC0.205 20.381 20.323 30.037 30.226 30.177 30.063 20.277 30.120 10.067 30.131 30.074 30.317 20.080 30.235 10.289 30.141 30.678 10.080 3
FKNet0.204 30.334 30.358 20.038 20.234 20.184 20.025 30.318 10.042 40.088 20.141 20.053 40.300 30.207 10.171 30.292 20.149 20.636 30.109 2
MaskRCNN_ScanNetpermissive0.119 40.129 40.212 40.002 40.112 40.148 40.014 40.205 40.044 30.066 40.078 40.095 20.142 40.030 40.128 40.139 40.080 40.459 40.057 4
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17


Scene Type Classification Benchmark

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
LAST-PCL-type0.780 10.250 31.000 11.000 11.000 11.000 11.000 10.500 21.000 10.500 20.889 10.000 21.000 11.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, and Jian Zhang: Language-Assisted 3D Scene Understanding. arxiv23.12
multi-taskpermissive0.700 20.500 11.000 10.882 30.500 31.000 11.000 10.500 21.000 11.000 10.778 20.000 20.938 20.000 3
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
3DASPP-SCE0.691 30.500 10.938 30.824 41.000 11.000 10.500 31.000 10.857 30.500 20.556 40.000 20.812 30.500 2
SE-ResNeXt-SSMA0.498 40.000 50.812 40.941 20.500 30.500 40.500 30.500 20.429 50.500 20.667 30.500 10.625 40.000 3
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
resnet50_scannet0.353 50.250 30.812 40.529 50.500 30.500 40.000 50.500 20.571 40.000 50.556 40.000 20.375 50.000 3