Presenting the ScanNet200 Benchmark

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

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

ScanNet200 Benchmark

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




Method Infoavg iouhead ioucommon ioutail iouwallchairfloortabledoorcouchcabinetshelfdeskoffice chairbedpillowsinkpicturewindowtoiletbookshelfmonitorcurtainbookarmchaircoffee tableboxrefrigeratorlampkitchen cabinettowelclothestvnightstandcounterdresserstoolcushionplantceilingbathtubend tabledining tablekeyboardbagbackpacktoilet paperprintertv standwhiteboardblanketshower curtaintrash canclosetstairsmicrowavestoveshoecomputer towerbottlebinottomanbenchboardwashing machinemirrorcopierbasketsofa chairfile cabinetfanlaptopshowerpaperpersonpaper towel dispenserovenblindsrackplateblackboardpianosuitcaserailradiatorrecycling bincontainerwardrobesoap dispensertelephonebucketclockstandlightlaundry basketpipeclothes dryerguitartoilet paper holderseatspeakercolumnbicycleladderbathroom stallshower wallcupjacketstorage bincoffee makerdishwasherpaper towel rollmachinematwindowsillbartoasterbulletin boardironing boardfireplacesoap dishkitchen counterdoorframetoilet paper dispensermini fridgefire extinguisherballhatshower curtain rodwater coolerpaper cuttertrayshower doorpillarledgetoaster ovenmousetoilet seat cover dispenserfurniturecartstorage containerscaletissue boxlight switchcratepower outletdecorationsignprojectorcloset doorvacuum cleanercandleplungerstuffed animalheadphonesdish rackbroomguitar caserange hooddustpanhair dryerwater bottlehandicap barpurseventshower floorwater pitchermailboxbowlpaper bagalarm clockmusic standprojector screendividerlaundry detergentbathroom counterobjectbathroom vanitycloset walllaundry hamperbathroom stall doorceiling lighttrash bindumbbellstair railtubebathroom cabinetcd casecloset rodcoffee kettlestructureshower headkeyboard pianocase of water bottlescoat rackstorage organizerfolded chairfire alarmpower stripcalendarposterpotted plantluggagemattress
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PTv3 ScanNet2000.393 10.592 10.330 10.216 10.851 10.687 30.971 10.586 10.755 10.752 40.505 10.404 40.575 20.000 90.848 10.616 10.761 10.349 10.738 10.978 10.546 30.860 60.926 10.346 10.654 30.384 40.828 10.523 30.699 10.583 30.387 50.822 10.688 10.118 40.474 10.603 40.000 10.832 20.903 10.753 70.140 60.000 70.650 10.109 20.520 10.457 10.497 60.871 30.281 10.192 20.887 20.748 10.168 10.727 20.733 10.740 10.644 10.714 30.190 70.000 30.256 20.449 50.914 10.514 10.759 90.337 10.172 30.692 30.617 10.636 10.325 30.000 10.641 10.782 10.000 40.065 20.000 10.000 30.842 10.903 10.661 10.662 20.612 10.405 20.731 10.566 10.000 30.000 40.000 10.017 90.301 10.088 40.941 10.000 10.077 20.000 70.717 20.790 10.310 90.026 110.264 20.349 10.220 20.397 70.366 10.115 70.000 30.337 10.463 40.000 10.531 10.218 10.593 10.455 10.469 10.708 10.210 10.592 20.108 100.000 10.728 10.682 20.671 40.000 10.000 60.407 10.136 10.022 20.575 10.436 40.259 10.428 10.048 20.000 10.000 10.879 50.000 10.480 10.000 10.133 40.597 10.000 10.690 10.000 10.000 10.009 100.000 90.921 20.000 50.151 10.000 10.000 50.000 10.109 60.494 80.622 20.394 60.073 90.141 70.798 10.528 20.026 10.000 10.551 20.000 20.000 20.134 50.717 40.000 20.000 10.000 10.188 20.000 40.000 20.791 10.000 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.
PonderV2 ScanNet2000.346 20.552 40.270 40.175 30.810 40.682 40.950 20.560 40.641 60.761 10.398 70.357 60.570 50.113 20.804 30.603 30.750 30.283 20.681 40.952 20.548 20.874 30.852 70.290 60.700 20.356 70.792 30.445 60.545 70.436 60.351 70.787 50.611 50.050 60.290 80.519 80.000 10.825 40.888 20.842 30.259 20.100 20.558 30.070 80.497 50.247 80.457 70.889 20.248 50.106 60.817 70.691 30.094 40.729 10.636 30.620 80.503 70.660 90.243 40.000 30.212 50.590 30.860 60.400 30.881 30.000 30.202 10.622 60.408 50.499 60.261 60.000 10.385 50.636 50.000 40.000 60.000 10.000 30.433 110.843 40.660 30.574 80.481 20.336 30.677 30.486 20.000 30.030 10.000 10.034 40.000 30.080 50.869 70.000 10.000 70.000 70.540 40.727 20.232 110.115 50.186 50.193 50.000 100.403 60.326 30.103 80.000 30.290 30.392 60.000 10.346 40.062 70.424 20.375 40.431 30.667 20.115 80.082 70.239 40.000 10.504 80.606 40.584 60.000 10.002 40.186 40.104 60.000 50.394 20.384 60.083 40.000 40.007 50.000 10.000 10.880 40.000 10.377 60.000 10.263 20.565 20.000 10.608 60.000 10.000 10.304 40.009 50.924 10.000 50.000 50.000 10.000 50.000 10.128 20.584 10.475 40.412 50.076 80.269 30.621 30.509 30.010 30.000 10.491 60.063 10.000 20.472 30.880 10.000 20.000 10.000 10.179 30.125 10.000 20.441 50.000 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 50.558 20.269 50.124 70.821 20.703 10.946 30.569 20.662 20.748 50.487 20.455 10.572 40.000 90.789 40.534 50.736 50.271 30.713 20.949 30.498 100.877 20.860 50.332 30.706 10.474 10.788 50.406 70.637 30.495 50.355 60.805 30.592 90.015 100.396 20.602 50.000 10.799 50.876 40.713 110.276 10.000 70.493 70.080 50.448 90.363 20.661 20.833 50.262 30.125 30.823 60.665 50.076 60.720 30.557 50.637 60.517 50.672 80.227 50.000 30.158 70.496 40.843 80.352 60.835 70.000 30.103 90.711 20.527 20.526 40.320 40.000 10.568 30.625 60.067 10.000 60.000 10.001 20.806 30.836 50.621 60.591 40.373 50.314 40.668 40.398 50.003 20.000 40.000 10.016 100.024 20.043 90.906 40.000 10.052 40.000 70.384 60.330 80.342 50.100 60.223 40.183 70.112 40.476 40.313 40.130 60.196 20.112 60.370 80.000 10.234 60.071 60.160 30.403 30.398 80.492 90.197 20.076 80.272 30.000 10.200 110.560 50.735 30.000 10.000 60.000 60.110 40.002 40.021 50.412 50.000 60.000 40.000 70.000 10.000 10.794 60.000 10.445 20.000 10.022 50.509 50.000 10.517 100.000 10.000 10.001 110.245 20.915 40.024 20.089 20.000 10.262 20.000 10.103 80.524 40.392 70.515 20.013 110.251 40.411 90.662 10.001 70.000 10.473 70.000 20.000 20.150 40.699 50.000 20.000 10.000 10.166 40.000 40.024 10.000 60.000 1
PPT-SpUNet-F.T.0.332 60.556 30.270 30.123 80.816 30.682 40.946 30.549 50.657 50.756 30.459 40.376 50.550 60.001 80.807 20.616 10.727 60.267 40.691 30.942 60.530 60.872 40.874 40.330 40.542 80.374 50.792 30.400 80.673 20.572 40.433 10.793 40.623 40.008 110.351 40.594 60.000 10.783 70.876 40.833 40.213 30.000 70.537 40.091 30.519 20.304 40.620 50.942 10.264 20.124 40.855 30.695 20.086 50.646 50.506 100.658 40.535 30.715 20.314 10.000 30.241 30.608 20.897 20.359 50.858 50.000 30.076 110.611 70.392 60.509 50.378 20.000 10.579 20.565 100.000 40.000 60.000 10.000 30.755 40.806 70.661 10.572 90.350 60.181 60.660 60.300 80.000 30.000 40.000 10.023 60.000 30.042 100.930 20.000 10.000 70.077 40.584 30.392 60.339 60.185 40.171 70.308 20.006 90.563 30.256 50.150 10.000 30.002 100.345 90.000 10.045 80.197 20.063 50.323 80.453 20.600 50.163 60.037 90.349 20.000 10.672 20.679 30.753 10.000 10.000 60.000 60.117 20.000 50.000 60.291 80.000 60.000 40.039 30.000 10.000 10.899 20.000 10.374 70.000 10.000 70.545 40.000 10.634 30.000 10.000 10.074 70.223 30.914 50.000 50.021 30.000 10.000 50.000 10.112 40.498 70.649 10.383 70.095 10.135 100.449 70.432 60.008 50.000 10.518 40.000 20.000 20.000 70.796 20.000 20.000 10.000 10.138 80.000 40.000 20.000 60.000 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.
AWCS0.305 80.508 80.225 80.142 50.782 80.634 110.937 80.489 90.578 80.721 60.364 90.355 70.515 70.023 60.764 80.523 70.707 80.264 50.633 80.922 80.507 90.886 10.804 90.179 90.436 100.300 80.656 100.529 20.501 90.394 70.296 100.820 20.603 60.131 30.179 110.619 20.000 10.707 100.865 80.773 50.171 40.010 60.484 80.063 90.463 80.254 70.332 100.649 80.220 70.100 70.729 90.613 90.071 80.582 90.628 40.702 20.424 90.749 10.137 90.000 30.142 80.360 80.863 40.305 80.877 40.000 30.173 20.606 80.337 80.478 80.154 90.000 10.253 80.664 40.000 40.000 60.000 10.000 30.626 80.782 80.302 100.602 30.185 90.282 50.651 70.317 70.000 30.000 40.000 10.022 70.000 30.154 10.876 60.000 10.014 60.063 60.029 110.553 30.467 20.084 70.124 80.157 100.049 80.373 80.252 60.097 90.000 30.219 40.542 20.000 10.392 20.172 50.000 90.339 60.417 50.533 80.093 90.115 50.195 60.000 10.516 60.288 100.741 20.000 10.001 50.233 30.056 80.000 50.159 30.334 70.077 50.000 40.000 70.000 10.000 10.749 80.000 10.411 40.000 10.008 60.452 70.000 10.595 70.000 10.000 10.220 60.006 60.894 80.006 40.000 50.000 10.000 50.000 10.112 40.504 50.404 60.551 10.093 30.129 110.484 60.381 110.000 80.000 10.396 90.000 20.000 20.620 20.402 110.000 20.000 10.000 10.142 70.000 40.000 20.512 40.000 1
L3DETR-ScanNet_2000.336 40.533 70.279 20.155 40.801 60.689 20.946 30.539 60.660 40.759 20.380 80.333 80.583 10.000 90.788 50.529 60.740 40.261 60.679 60.940 70.525 70.860 60.883 30.226 70.613 60.397 30.720 80.512 40.565 60.620 10.417 30.775 80.629 30.158 20.298 60.579 70.000 10.835 10.883 30.927 10.114 70.079 40.511 60.073 70.508 30.312 30.629 30.861 40.192 100.098 90.908 10.636 70.032 110.563 110.514 90.664 30.505 60.697 50.225 60.000 30.264 10.411 70.860 60.321 70.960 10.058 20.109 80.776 10.526 30.557 20.303 50.000 10.339 60.712 30.000 40.014 40.000 10.000 30.638 70.856 30.641 40.579 70.107 110.119 90.661 50.416 30.000 30.000 40.000 10.007 110.000 30.067 70.910 30.000 10.000 70.000 70.463 50.448 40.294 100.324 10.293 10.211 40.108 50.448 50.068 110.141 30.000 30.330 20.699 10.000 10.256 50.192 30.000 90.355 50.418 40.209 110.146 70.679 10.101 110.000 10.503 90.687 10.671 40.000 10.000 60.174 50.117 20.000 50.122 40.515 20.104 20.259 20.312 10.000 10.000 10.765 70.000 10.369 80.000 10.183 30.422 80.000 10.646 20.000 10.000 10.565 10.001 80.125 110.010 30.002 40.000 10.487 10.000 10.075 100.548 20.420 50.233 100.082 60.138 90.430 80.427 70.000 80.000 10.549 30.000 20.000 20.074 60.409 100.000 20.000 10.000 10.152 50.051 20.000 20.598 30.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
CeCo0.340 30.551 50.247 70.181 20.784 70.661 80.939 70.564 30.624 70.721 60.484 30.429 20.575 20.027 50.774 60.503 80.753 20.242 70.656 70.945 40.534 40.865 50.860 50.177 110.616 50.400 20.818 20.579 10.615 50.367 80.408 40.726 90.633 20.162 10.360 30.619 20.000 10.828 30.873 60.924 20.109 80.083 30.564 20.057 110.475 70.266 60.781 10.767 60.257 40.100 70.825 50.663 60.048 100.620 80.551 60.595 90.532 40.692 60.246 30.000 30.213 40.615 10.861 50.376 40.900 20.000 30.102 100.660 40.321 90.547 30.226 70.000 10.311 70.742 20.011 30.006 50.000 10.000 30.546 100.824 60.345 80.665 10.450 30.435 10.683 20.411 40.338 10.000 40.000 10.030 50.000 30.068 60.892 50.000 10.063 30.000 70.257 70.304 90.387 30.079 80.228 30.190 60.000 100.586 10.347 20.133 40.000 30.037 70.377 70.000 10.384 30.006 100.003 70.421 20.410 70.643 30.171 40.121 40.142 80.000 10.510 70.447 60.474 80.000 10.000 60.286 20.083 70.000 50.000 60.603 10.096 30.063 30.000 70.000 10.000 10.898 30.000 10.429 30.000 10.400 10.550 30.000 10.633 40.000 10.000 10.377 30.000 90.916 30.000 50.000 50.000 10.000 50.000 10.102 90.499 60.296 80.463 30.089 40.304 10.740 20.401 100.010 30.000 10.560 10.000 20.000 20.709 10.652 60.000 20.000 10.000 10.143 60.000 40.000 20.609 20.000 1
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
CSC-Pretrainpermissive0.249 110.455 110.171 100.079 110.766 110.659 90.930 110.494 80.542 110.700 110.314 110.215 110.430 110.121 10.697 110.441 100.683 100.235 80.609 110.895 100.476 110.816 100.770 110.186 80.634 40.216 110.734 60.340 100.471 100.307 100.293 110.591 110.542 100.076 50.205 100.464 90.000 10.484 110.832 110.766 60.052 100.000 70.413 100.059 100.418 100.222 100.318 110.609 100.206 90.112 50.743 80.625 80.076 60.579 100.548 70.590 100.371 100.552 110.081 100.003 20.142 80.201 110.638 110.233 100.686 110.000 30.142 60.444 110.375 70.247 110.198 80.000 10.128 110.454 110.019 20.097 10.000 10.000 30.553 90.557 100.373 70.545 100.164 100.014 110.547 100.174 90.000 30.002 20.000 10.037 20.000 30.063 80.664 110.000 10.000 70.130 20.170 80.152 110.335 70.079 80.110 90.175 80.098 60.175 110.166 90.045 110.207 10.014 80.465 30.000 10.001 110.001 110.046 60.299 90.327 100.537 70.033 100.012 110.186 70.000 10.205 100.377 80.463 100.000 10.058 20.000 60.055 90.041 10.000 60.105 100.000 60.000 40.000 70.000 10.000 10.398 90.000 10.308 110.000 10.000 70.319 90.000 10.543 90.000 10.000 10.062 90.004 70.862 100.000 50.000 50.000 10.000 50.000 10.123 30.316 100.225 90.250 90.094 20.180 50.332 100.441 50.000 80.000 10.310 110.000 20.000 20.000 70.592 80.000 20.000 10.000 10.203 10.000 40.000 20.000 60.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGroundpermissive0.272 90.485 90.184 90.106 90.778 90.676 60.932 90.479 110.572 90.718 80.399 60.265 90.453 100.085 30.745 90.446 90.726 70.232 90.622 90.901 90.512 80.826 90.786 100.178 100.549 70.277 90.659 90.381 90.518 80.295 110.323 80.777 70.599 70.028 70.321 50.363 100.000 10.708 90.858 90.746 80.063 90.022 50.457 90.077 60.476 60.243 90.402 80.397 110.233 60.077 110.720 110.610 100.103 30.629 70.437 110.626 70.446 80.702 40.190 70.005 10.058 100.322 90.702 100.244 90.768 80.000 30.134 70.552 90.279 100.395 90.147 100.000 10.207 90.612 80.000 40.000 60.000 10.000 30.658 60.566 90.323 90.525 110.229 80.179 70.467 110.154 100.000 30.002 20.000 10.051 10.000 30.127 20.703 90.000 10.000 70.216 10.112 100.358 70.547 10.187 30.092 100.156 110.055 70.296 90.252 60.143 20.000 30.014 80.398 50.000 10.028 100.173 40.000 90.265 100.348 90.415 100.179 30.019 100.218 50.000 10.597 50.274 110.565 70.000 10.012 30.000 60.039 100.022 20.000 60.117 90.000 60.000 40.000 70.000 10.000 10.324 100.000 10.384 50.000 10.000 70.251 110.000 10.566 80.000 10.000 10.066 80.404 10.886 90.199 10.000 50.000 10.059 30.000 10.136 10.540 30.127 110.295 80.085 50.143 60.514 40.413 90.000 80.000 10.498 50.000 20.000 20.000 70.623 70.000 20.000 10.000 10.132 100.000 40.000 20.000 60.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
OctFormer ScanNet200permissive0.326 70.539 60.265 60.131 60.806 50.670 70.943 60.535 70.662 20.705 100.423 50.407 30.505 80.003 70.765 70.582 40.686 90.227 100.680 50.943 50.601 10.854 80.892 20.335 20.417 110.357 60.724 70.453 50.632 40.596 20.432 20.783 60.512 110.021 90.244 90.637 10.000 10.787 60.873 60.743 90.000 110.000 70.534 50.110 10.499 40.289 50.626 40.620 90.168 110.204 10.849 40.679 40.117 20.633 60.684 20.650 50.552 20.684 70.312 20.000 30.175 60.429 60.865 30.413 20.837 60.000 30.145 50.626 50.451 40.487 70.513 10.000 10.529 40.613 70.000 40.033 30.000 10.000 30.828 20.871 20.622 50.587 50.411 40.137 80.645 80.343 60.000 30.000 40.000 10.022 70.000 30.026 110.829 80.000 10.022 50.089 30.842 10.253 100.318 80.296 20.178 60.291 30.224 10.584 20.200 80.132 50.000 30.128 50.227 100.000 10.230 70.047 80.149 40.331 70.412 60.618 40.164 50.102 60.522 10.000 10.655 30.378 70.469 90.000 10.000 60.000 60.105 50.000 50.000 60.483 30.000 60.000 40.028 40.000 10.000 10.906 10.000 10.339 90.000 10.000 70.457 60.000 10.612 50.000 10.000 10.408 20.000 90.900 60.000 50.000 50.000 10.029 40.000 10.074 110.455 90.479 30.427 40.079 70.140 80.496 50.414 80.022 20.000 10.471 80.000 20.000 20.000 70.722 30.000 20.000 10.000 10.138 80.000 40.000 20.000 60.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
Minkowski 34Dpermissive0.253 100.463 100.154 110.102 100.771 100.650 100.932 90.483 100.571 100.710 90.331 100.250 100.492 90.044 40.703 100.419 110.606 110.227 100.621 100.865 110.531 50.771 110.813 80.291 50.484 90.242 100.612 110.282 110.440 110.351 90.299 90.622 100.593 80.027 80.293 70.310 110.000 10.757 80.858 90.737 100.150 50.164 10.368 110.084 40.381 110.142 110.357 90.720 70.214 80.092 100.724 100.596 110.056 90.655 40.525 80.581 110.352 110.594 100.056 110.000 30.014 110.224 100.772 90.205 110.720 100.000 30.159 40.531 100.163 110.294 100.136 110.000 10.169 100.589 90.000 40.000 60.000 10.002 10.663 50.466 110.265 110.582 60.337 70.016 100.559 90.084 110.000 30.000 40.000 10.036 30.000 30.125 30.670 100.000 10.102 10.071 50.164 90.406 50.386 40.046 100.068 110.159 90.117 30.284 100.111 100.094 100.000 30.000 110.197 110.000 10.044 90.013 90.002 80.228 110.307 110.588 60.025 110.545 30.134 90.000 10.655 30.302 90.282 110.000 10.060 10.000 60.035 110.000 50.000 60.097 110.000 60.000 40.005 60.000 10.000 10.096 110.000 10.334 100.000 10.000 70.274 100.000 10.513 110.000 10.000 10.280 50.194 40.897 70.000 50.000 50.000 10.000 50.000 10.108 70.279 110.189 100.141 110.059 100.272 20.307 110.445 40.003 60.000 10.353 100.000 20.026 10.000 70.581 90.001 10.000 10.000 10.093 110.002 30.000 20.000 60.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


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




Method 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 bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mask3D Scannet2000.388 10.542 10.357 10.237 10.808 20.676 20.741 10.832 40.496 10.151 30.628 20.021 20.955 10.578 10.753 10.612 10.591 10.822 50.609 30.926 10.614 30.291 10.725 40.163 10.890 20.380 50.615 10.517 10.130 30.806 10.857 20.024 20.511 10.412 50.226 10.597 20.756 11.000 10.111 10.792 10.736 10.091 10.610 10.527 20.323 41.000 10.504 10.063 21.000 10.853 10.010 10.974 30.839 10.667 10.301 10.883 10.266 10.039 10.640 10.311 20.739 20.463 11.000 10.000 10.287 20.715 20.313 20.600 11.000 10.027 10.076 40.502 50.500 10.409 10.000 10.194 10.125 20.500 10.491 10.748 10.050 40.042 20.776 20.352 10.008 10.000 10.033 10.254 10.000 10.005 20.552 10.008 20.020 20.750 10.500 10.409 20.065 30.511 10.107 10.178 20.000 11.000 10.400 10.016 10.000 10.400 10.571 10.000 10.060 20.044 20.000 10.514 10.278 11.000 10.258 10.017 30.125 50.000 10.792 30.399 31.000 10.000 10.013 20.265 10.018 20.000 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 20.000 10.708 20.000 10.000 10.945 10.391 10.123 40.000 10.028 10.000 11.000 10.000 10.099 10.451 10.400 10.668 10.573 10.606 10.077 50.003 40.004 10.000 10.042 30.000 10.000 11.000 11.000 10.000 10.042 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
Minkowski 34D Inst.permissive0.203 50.369 40.134 50.078 50.706 40.382 40.693 30.845 30.221 50.150 40.158 40.000 30.746 20.369 40.545 40.595 20.387 40.997 30.413 50.720 50.636 20.165 30.732 30.070 40.851 40.402 40.251 40.313 40.123 40.583 40.696 30.000 30.051 50.500 20.000 30.500 40.372 50.667 40.009 40.000 30.307 50.003 40.479 40.107 50.226 50.903 40.109 50.031 30.981 30.726 50.000 20.522 50.669 20.282 50.052 50.778 50.000 40.000 30.400 30.074 40.333 40.218 41.000 10.000 10.250 30.406 50.118 50.317 20.100 30.000 20.191 10.596 20.000 30.000 20.000 10.000 20.000 30.500 10.178 50.701 20.000 50.000 30.522 50.018 50.000 20.000 10.000 30.060 40.000 10.000 30.033 50.000 30.000 30.000 40.000 20.281 30.100 20.000 50.090 40.133 40.000 10.422 50.050 40.000 20.000 10.200 30.000 50.000 10.000 30.000 30.000 10.000 40.123 40.677 20.021 40.000 40.500 10.000 10.500 40.442 20.125 50.000 10.000 30.000 30.000 30.000 20.000 30.056 40.000 30.000 30.000 30.000 30.000 10.200 50.000 10.143 50.000 10.000 30.250 50.000 10.511 40.000 10.000 10.286 30.083 40.396 20.000 10.000 30.000 10.000 20.000 10.025 40.300 20.000 30.371 30.070 20.000 40.385 30.000 50.000 20.000 10.000 50.000 10.000 10.000 20.500 20.000 10.000 20.000 20.200 20.000 20.000 20.000 20.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.209 40.361 50.157 40.085 40.700 50.248 50.634 50.776 50.322 20.135 50.103 50.000 30.524 50.364 50.618 20.592 30.381 50.997 30.589 40.747 40.340 50.109 50.768 20.059 50.702 50.448 20.188 50.149 50.091 50.636 30.573 50.000 30.246 30.500 20.000 30.450 50.405 30.667 40.006 50.000 30.356 40.007 30.506 20.420 30.340 30.667 50.294 20.004 40.571 40.748 20.000 21.000 10.573 40.502 40.094 40.807 30.000 40.000 30.400 30.000 50.278 50.228 31.000 10.000 10.115 50.432 40.198 30.050 50.125 20.000 20.000 50.573 30.000 30.000 20.000 10.000 20.000 30.125 40.312 40.610 30.221 10.000 30.667 40.050 40.000 20.000 10.000 30.032 50.000 10.000 30.083 30.000 30.000 30.000 40.000 20.220 40.000 50.125 30.000 50.111 50.000 10.667 20.200 30.000 20.000 10.000 40.110 30.000 10.000 30.000 30.000 10.000 40.053 50.500 40.000 50.000 40.500 10.000 10.500 40.333 40.500 40.000 10.000 30.000 30.000 30.000 20.000 30.000 50.000 30.000 30.000 30.000 30.000 10.600 20.000 10.364 20.000 10.000 30.750 10.000 10.833 10.000 10.000 10.143 50.000 50.396 20.000 10.000 30.000 10.000 20.000 10.021 50.221 40.000 30.093 50.055 40.451 20.677 20.125 20.000 20.000 10.028 40.000 10.000 10.000 20.500 20.000 10.000 20.000 20.050 40.000 20.000 20.000 20.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.246 30.413 30.170 30.130 30.754 30.541 30.682 40.903 10.264 40.164 20.234 30.000 30.681 40.452 30.464 50.541 40.399 31.000 10.637 20.772 30.588 40.190 20.589 50.081 30.857 30.426 30.373 30.318 30.135 20.690 20.653 40.000 30.159 40.500 20.000 30.581 30.387 41.000 10.046 30.000 30.402 30.003 50.455 50.196 40.571 21.000 10.270 30.003 50.530 50.748 30.000 20.744 40.575 30.511 30.112 30.815 20.067 30.000 30.400 30.167 30.667 30.241 21.000 10.000 10.208 40.660 30.125 40.317 20.000 50.000 20.100 20.561 40.000 30.000 20.000 10.000 21.000 10.500 10.344 20.568 40.167 30.000 30.706 30.068 30.000 20.000 10.000 30.063 30.000 10.000 30.056 40.000 30.000 30.500 20.000 20.143 50.017 40.125 30.097 20.164 30.000 10.582 40.400 10.000 20.000 10.000 40.083 40.000 10.000 30.000 30.000 10.025 30.156 30.533 30.250 20.200 20.500 10.000 11.000 10.333 41.000 10.000 10.000 30.000 30.000 30.000 20.000 30.333 20.000 30.000 30.000 30.000 30.000 10.400 30.000 10.364 20.000 10.000 30.500 30.000 10.511 40.000 10.000 10.286 30.333 20.000 50.000 10.000 30.000 10.000 20.000 10.034 30.111 50.000 30.333 40.031 50.000 40.750 10.125 20.000 20.000 10.151 20.000 10.000 10.000 20.500 20.000 10.000 20.000 20.000 50.000 20.000 20.000 20.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.
TD3D Scannet200permissive0.320 20.501 20.264 20.164 20.841 10.679 10.716 20.879 20.280 30.192 10.634 10.231 10.733 30.459 20.565 30.498 50.560 21.000 10.686 10.890 20.708 10.123 40.820 10.152 20.967 10.456 10.458 20.387 20.194 10.435 50.906 10.077 10.396 20.509 10.217 20.715 10.619 21.000 10.099 20.792 10.513 20.062 20.506 30.549 10.605 11.000 10.123 40.106 11.000 10.744 40.000 21.000 10.504 50.525 20.185 20.790 40.101 20.008 20.587 20.356 10.817 10.083 51.000 10.000 10.621 10.842 10.415 10.268 40.083 40.000 20.098 30.881 10.125 20.000 20.000 10.000 20.000 30.125 40.332 30.448 50.202 20.196 10.798 10.264 20.000 20.000 10.017 20.233 20.000 10.063 10.333 20.038 10.111 10.250 30.000 20.516 10.208 10.470 20.094 30.218 10.000 10.667 20.033 50.000 20.000 10.400 10.156 20.000 10.267 10.226 10.000 10.104 20.159 20.299 50.095 30.458 10.500 10.000 11.000 10.472 10.792 30.000 10.022 10.061 20.250 10.008 10.250 20.333 20.143 20.396 20.049 20.012 10.000 10.283 40.000 10.241 40.000 10.101 20.331 40.000 10.629 30.000 10.000 10.857 20.222 30.677 10.000 10.003 20.000 10.000 20.000 10.076 20.252 30.400 10.431 20.061 30.328 30.331 40.500 10.000 20.000 10.167 10.000 10.000 10.000 20.500 20.000 10.000 21.000 10.542 10.000 20.063 10.000 20.000 1
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024


ScanNet Benchmark

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PTv3 ScanNet0.794 10.941 30.813 160.851 70.782 50.890 20.597 10.916 10.696 70.713 30.979 10.635 10.384 20.793 20.907 60.821 30.790 290.696 100.967 30.903 10.805 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.
PonderV20.785 20.978 10.800 240.833 210.788 30.853 140.545 150.910 40.713 10.705 40.979 10.596 50.390 10.769 100.832 390.821 30.792 280.730 10.975 10.897 30.785 3
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 30.964 20.855 10.843 150.781 60.858 100.575 50.831 300.685 120.714 20.979 10.594 60.310 240.801 10.892 140.841 20.819 30.723 40.940 110.887 50.725 21
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 40.861 200.818 130.836 180.790 20.875 30.576 40.905 50.704 40.739 10.969 90.611 20.349 90.756 190.958 10.702 410.805 130.708 70.916 290.898 20.801 2
ResLFE_HDS0.772 50.939 40.824 60.854 60.771 80.840 280.564 90.900 70.686 110.677 100.961 140.537 280.348 100.769 100.903 80.785 90.815 50.676 190.939 120.880 100.772 7
PPT-SpUNet-Joint0.766 60.932 50.794 300.829 230.751 200.854 120.540 180.903 60.630 310.672 130.963 120.565 190.357 70.788 30.900 100.737 230.802 140.685 140.950 50.887 50.780 4
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.
OctFormerpermissive0.766 60.925 70.808 200.849 90.786 40.846 240.566 80.876 130.690 90.674 120.960 150.576 150.226 630.753 210.904 70.777 110.815 50.722 50.923 250.877 120.776 6
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net0.764 80.924 80.819 110.840 160.757 150.853 140.580 20.848 230.709 30.643 210.958 180.587 100.295 300.753 210.884 180.758 170.815 50.725 30.927 220.867 190.743 13
OccuSeg+Semantic0.764 80.758 560.796 280.839 170.746 220.907 10.562 100.850 220.680 140.672 130.978 40.610 30.335 150.777 60.819 420.847 10.830 10.691 120.972 20.885 70.727 19
O-CNNpermissive0.762 100.924 80.823 70.844 140.770 90.852 160.577 30.847 250.711 20.640 250.958 180.592 70.217 690.762 150.888 150.758 170.813 90.726 20.932 200.868 180.744 12
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
OA-CNN-L_ScanNet200.756 110.783 420.826 50.858 40.776 70.837 310.548 140.896 100.649 230.675 110.962 130.586 110.335 150.771 90.802 460.770 130.787 310.691 120.936 150.880 100.761 9
PNE0.755 120.786 400.835 40.834 200.758 130.849 190.570 70.836 290.648 240.668 150.978 40.581 140.367 50.683 320.856 270.804 50.801 180.678 160.961 40.889 40.716 26
P. Hermosilla: Point Neighborhood Embeddings.
ConDaFormer0.755 120.927 60.822 80.836 180.801 10.849 190.516 280.864 190.651 220.680 90.958 180.584 130.282 380.759 170.855 290.728 250.802 140.678 160.880 550.873 170.756 10
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-Net0.752 140.906 120.793 320.802 380.689 370.825 420.556 110.867 150.681 130.602 400.960 150.555 240.365 60.779 50.859 240.747 200.795 250.717 60.917 280.856 270.764 8
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
PointTransformerV20.752 140.742 630.809 190.872 10.758 130.860 90.552 120.891 110.610 380.687 50.960 150.559 220.304 270.766 130.926 30.767 140.797 210.644 300.942 90.876 150.722 23
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer0.749 160.793 380.790 330.807 340.750 210.856 110.524 240.881 120.588 500.642 240.977 70.591 80.274 430.781 40.929 20.804 50.796 220.642 310.947 70.885 70.715 27
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 160.909 100.818 130.811 310.752 180.839 300.485 430.842 260.673 150.644 200.957 220.528 340.305 260.773 80.859 240.788 70.818 40.693 110.916 290.856 270.723 22
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 180.623 890.804 220.859 30.745 230.824 440.501 330.912 30.690 90.685 70.956 230.567 180.320 210.768 120.918 40.720 300.802 140.676 190.921 260.881 90.779 5
StratifiedFormerpermissive0.747 190.901 130.803 230.845 130.757 150.846 240.512 290.825 330.696 70.645 190.956 230.576 150.262 540.744 260.861 230.742 210.770 400.705 80.899 410.860 240.734 14
Xin Lai*, Jianhui Liu*, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
VMNetpermissive0.746 200.870 180.838 20.858 40.729 280.850 180.501 330.874 140.587 510.658 170.956 230.564 200.299 280.765 140.900 100.716 330.812 100.631 360.939 120.858 250.709 28
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
Virtual MVFusion0.746 200.771 500.819 110.848 110.702 340.865 80.397 810.899 80.699 50.664 160.948 510.588 90.330 170.746 250.851 330.764 150.796 220.704 90.935 160.866 200.728 17
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
Retro-FPN0.744 220.842 260.800 240.767 520.740 240.836 330.541 170.914 20.672 160.626 290.958 180.552 250.272 450.777 60.886 170.696 420.801 180.674 220.941 100.858 250.717 24
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-Net0.743 230.620 900.799 270.849 90.730 270.822 460.493 400.897 90.664 170.681 80.955 260.562 210.378 30.760 160.903 80.738 220.801 180.673 230.907 330.877 120.745 11
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet0.742 240.816 330.806 210.807 340.752 180.828 400.575 50.839 280.699 50.637 260.954 320.520 370.320 210.755 200.834 370.760 160.772 370.676 190.915 310.862 220.717 24
SAT0.742 240.860 210.765 450.819 260.769 100.848 210.533 200.829 310.663 180.631 280.955 260.586 110.274 430.753 210.896 120.729 240.760 470.666 250.921 260.855 290.733 15
LargeKernel3D0.739 260.909 100.820 100.806 360.740 240.852 160.545 150.826 320.594 490.643 210.955 260.541 270.263 530.723 300.858 260.775 120.767 410.678 160.933 180.848 340.694 33
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
MinkowskiNetpermissive0.736 270.859 220.818 130.832 220.709 320.840 280.521 260.853 210.660 200.643 210.951 410.544 260.286 360.731 280.893 130.675 510.772 370.683 150.874 620.852 320.727 19
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
RPN0.736 270.776 460.790 330.851 70.754 170.854 120.491 420.866 170.596 480.686 60.955 260.536 290.342 120.624 470.869 200.787 80.802 140.628 370.927 220.875 160.704 30
IPCA0.731 290.890 140.837 30.864 20.726 290.873 40.530 230.824 340.489 830.647 180.978 40.609 40.336 140.624 470.733 550.758 170.776 350.570 620.949 60.877 120.728 17
SparseConvNet0.725 300.647 860.821 90.846 120.721 300.869 50.533 200.754 540.603 440.614 330.955 260.572 170.325 190.710 310.870 190.724 280.823 20.628 370.934 170.865 210.683 36
PointTransformer++0.725 300.727 710.811 180.819 260.765 110.841 270.502 320.814 390.621 340.623 310.955 260.556 230.284 370.620 490.866 210.781 100.757 510.648 280.932 200.862 220.709 28
MatchingNet0.724 320.812 350.812 170.810 320.735 260.834 350.495 390.860 200.572 580.602 400.954 320.512 390.280 400.757 180.845 350.725 270.780 330.606 470.937 140.851 330.700 32
INS-Conv-semantic0.717 330.751 590.759 480.812 300.704 330.868 60.537 190.842 260.609 400.608 360.953 350.534 310.293 310.616 500.864 220.719 320.793 260.640 320.933 180.845 380.663 42
PointMetaBase0.714 340.835 270.785 350.821 240.684 390.846 240.531 220.865 180.614 350.596 440.953 350.500 420.246 590.674 330.888 150.692 430.764 430.624 390.849 770.844 390.675 38
contrastBoundarypermissive0.705 350.769 530.775 400.809 330.687 380.820 490.439 690.812 400.661 190.591 460.945 590.515 380.171 870.633 440.856 270.720 300.796 220.668 240.889 480.847 350.689 34
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 360.774 480.800 240.793 430.760 120.847 230.471 470.802 430.463 900.634 270.968 110.491 450.271 470.726 290.910 50.706 370.815 50.551 730.878 560.833 400.570 73
RFCR0.702 370.889 150.745 590.813 290.672 420.818 530.493 400.815 380.623 320.610 340.947 530.470 530.249 580.594 530.848 340.705 380.779 340.646 290.892 460.823 460.611 56
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 Click0.701 380.825 310.796 280.723 590.716 310.832 360.433 710.816 360.634 290.609 350.969 90.418 790.344 110.559 650.833 380.715 340.808 120.560 670.902 380.847 350.680 37
JSENetpermissive0.699 390.881 170.762 460.821 240.667 430.800 650.522 250.792 460.613 360.607 370.935 790.492 440.205 740.576 580.853 310.691 450.758 490.652 270.872 650.828 430.649 46
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-Click0.693 400.743 620.794 300.655 820.684 390.822 460.497 380.719 640.622 330.617 320.977 70.447 660.339 130.750 240.664 710.703 400.790 290.596 520.946 80.855 290.647 47
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 410.732 670.772 410.786 440.677 410.866 70.517 270.848 230.509 760.626 290.952 390.536 290.225 650.545 710.704 620.689 480.810 110.564 660.903 370.854 310.729 16
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 420.884 160.754 520.795 410.647 490.818 530.422 730.802 430.612 370.604 380.945 590.462 560.189 820.563 640.853 310.726 260.765 420.632 350.904 350.821 490.606 60
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 430.704 760.741 630.754 560.656 450.829 380.501 330.741 590.609 400.548 540.950 450.522 360.371 40.633 440.756 500.715 340.771 390.623 400.861 730.814 510.658 43
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 440.866 190.748 560.819 260.645 510.794 680.450 590.802 430.587 510.604 380.945 590.464 550.201 770.554 670.840 360.723 290.732 600.602 500.907 330.822 480.603 63
DGNet0.684 450.712 750.784 360.782 480.658 440.835 340.499 370.823 350.641 260.597 430.950 450.487 460.281 390.575 590.619 750.647 640.764 430.620 420.871 680.846 370.688 35
KP-FCNN0.684 450.847 250.758 500.784 460.647 490.814 560.473 460.772 490.605 420.594 450.935 790.450 640.181 850.587 540.805 450.690 460.785 320.614 430.882 520.819 500.632 52
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 450.728 700.757 510.776 490.690 350.804 630.464 520.816 360.577 570.587 470.945 590.508 410.276 420.671 340.710 600.663 560.750 540.589 570.881 530.832 420.653 45
Superpoint Network0.683 480.851 240.728 670.800 400.653 470.806 610.468 490.804 410.572 580.602 400.946 560.453 630.239 620.519 760.822 400.689 480.762 460.595 540.895 440.827 440.630 53
PointContrast_LA_SEM0.683 480.757 570.784 360.786 440.639 530.824 440.408 760.775 480.604 430.541 560.934 830.532 320.269 490.552 680.777 480.645 670.793 260.640 320.913 320.824 450.671 39
VI-PointConv0.676 500.770 520.754 520.783 470.621 570.814 560.552 120.758 520.571 600.557 520.954 320.529 330.268 510.530 740.682 660.675 510.719 630.603 490.888 490.833 400.665 41
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 510.789 390.748 560.763 540.635 550.814 560.407 780.747 560.581 550.573 490.950 450.484 470.271 470.607 510.754 510.649 610.774 360.596 520.883 510.823 460.606 60
SALANet0.670 520.816 330.770 430.768 510.652 480.807 600.451 560.747 560.659 210.545 550.924 890.473 520.149 970.571 610.811 440.635 700.746 550.623 400.892 460.794 640.570 73
PointConvpermissive0.666 530.781 430.759 480.699 670.644 520.822 460.475 450.779 470.564 630.504 720.953 350.428 730.203 760.586 560.754 510.661 570.753 520.588 580.902 380.813 530.642 48
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 530.703 770.781 380.751 580.655 460.830 370.471 470.769 500.474 860.537 580.951 410.475 510.279 410.635 420.698 650.675 510.751 530.553 720.816 840.806 550.703 31
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++permissive0.663 550.746 600.708 700.722 600.638 540.820 490.451 560.566 910.599 460.541 560.950 450.510 400.313 230.648 390.819 420.616 750.682 780.590 560.869 690.810 540.656 44
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
MVF-GNN0.658 560.558 970.751 540.655 820.690 350.722 900.453 550.867 150.579 560.576 480.893 1010.523 350.293 310.733 270.571 790.692 430.659 850.606 470.875 590.804 570.668 40
DCM-Net0.658 560.778 440.702 730.806 360.619 580.813 590.468 490.693 720.494 790.524 640.941 710.449 650.298 290.510 780.821 410.675 510.727 620.568 640.826 820.803 580.637 50
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 580.698 790.743 610.650 840.564 750.820 490.505 310.758 520.631 300.479 760.945 590.480 490.226 630.572 600.774 490.690 460.735 580.614 430.853 760.776 790.597 66
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 590.752 580.734 650.664 800.583 700.815 550.399 800.754 540.639 270.535 600.942 690.470 530.309 250.665 350.539 810.650 600.708 680.635 340.857 750.793 660.642 48
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 600.778 440.731 660.699 670.577 710.829 380.446 610.736 600.477 850.523 660.945 590.454 600.269 490.484 850.749 540.618 730.738 560.599 510.827 810.792 690.621 55
PointConv-SFPN0.641 610.776 460.703 720.721 610.557 780.826 410.451 560.672 770.563 640.483 750.943 680.425 760.162 920.644 400.726 560.659 580.709 670.572 610.875 590.786 740.559 79
MVPNetpermissive0.641 610.831 280.715 680.671 770.590 660.781 740.394 820.679 740.642 250.553 530.937 760.462 560.256 550.649 380.406 940.626 710.691 750.666 250.877 570.792 690.608 59
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 630.717 740.701 740.692 700.576 720.801 640.467 510.716 650.563 640.459 820.953 350.429 720.169 890.581 570.854 300.605 760.710 650.550 740.894 450.793 660.575 71
FPConvpermissive0.639 640.785 410.760 470.713 650.603 610.798 660.392 830.534 960.603 440.524 640.948 510.457 580.250 570.538 720.723 580.598 800.696 730.614 430.872 650.799 590.567 76
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 650.797 370.769 440.641 890.590 660.820 490.461 530.537 950.637 280.536 590.947 530.388 860.206 730.656 360.668 690.647 640.732 600.585 590.868 700.793 660.473 98
PointSPNet0.637 660.734 660.692 810.714 640.576 720.797 670.446 610.743 580.598 470.437 870.942 690.403 820.150 960.626 460.800 470.649 610.697 720.557 700.846 780.777 780.563 77
SConv0.636 670.830 290.697 770.752 570.572 740.780 760.445 630.716 650.529 690.530 610.951 410.446 670.170 880.507 800.666 700.636 690.682 780.541 800.886 500.799 590.594 67
Supervoxel-CNN0.635 680.656 840.711 690.719 620.613 590.757 850.444 660.765 510.534 680.566 500.928 870.478 500.272 450.636 410.531 830.664 550.645 890.508 870.864 720.792 690.611 56
joint point-basedpermissive0.634 690.614 910.778 390.667 790.633 560.825 420.420 740.804 410.467 880.561 510.951 410.494 430.291 330.566 620.458 890.579 860.764 430.559 690.838 790.814 510.598 65
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 700.731 680.688 840.675 740.591 650.784 730.444 660.565 920.610 380.492 730.949 490.456 590.254 560.587 540.706 610.599 790.665 840.612 460.868 700.791 720.579 70
PointNet2-SFPN0.631 710.771 500.692 810.672 750.524 830.837 310.440 680.706 700.538 670.446 840.944 650.421 780.219 680.552 680.751 530.591 820.737 570.543 790.901 400.768 810.557 80
APCF-Net0.631 710.742 630.687 860.672 750.557 780.792 710.408 760.665 780.545 660.508 690.952 390.428 730.186 830.634 430.702 630.620 720.706 690.555 710.873 630.798 610.581 69
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
3DSM_DMMF0.631 710.626 880.745 590.801 390.607 600.751 860.506 300.729 630.565 620.491 740.866 1040.434 680.197 800.595 520.630 740.709 360.705 700.560 670.875 590.740 890.491 93
FusionAwareConv0.630 740.604 930.741 630.766 530.590 660.747 870.501 330.734 610.503 780.527 620.919 930.454 600.323 200.550 700.420 930.678 500.688 760.544 770.896 430.795 630.627 54
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 750.800 360.625 960.719 620.545 800.806 610.445 630.597 860.448 930.519 670.938 750.481 480.328 180.489 840.499 880.657 590.759 480.592 550.881 530.797 620.634 51
SegGroup_sempermissive0.627 760.818 320.747 580.701 660.602 620.764 820.385 870.629 830.490 810.508 690.931 860.409 810.201 770.564 630.725 570.618 730.692 740.539 810.873 630.794 640.548 83
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
dtc_net0.625 770.703 770.751 540.794 420.535 810.848 210.480 440.676 760.528 700.469 790.944 650.454 600.004 1090.464 870.636 730.704 390.758 490.548 760.924 240.787 730.492 92
SIConv0.625 770.830 290.694 790.757 550.563 760.772 800.448 600.647 810.520 720.509 680.949 490.431 710.191 810.496 820.614 760.647 640.672 820.535 830.876 580.783 750.571 72
HPEIN0.618 790.729 690.668 870.647 860.597 640.766 810.414 750.680 730.520 720.525 630.946 560.432 690.215 700.493 830.599 770.638 680.617 940.570 620.897 420.806 550.605 62
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-GCNpermissive0.610 800.858 230.772 410.489 1010.532 820.792 710.404 790.643 820.570 610.507 710.935 790.414 800.046 1060.510 780.702 630.602 780.705 700.549 750.859 740.773 800.534 86
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 810.760 550.667 880.649 850.521 840.793 690.457 540.648 800.528 700.434 890.947 530.401 830.153 950.454 880.721 590.648 630.717 640.536 820.904 350.765 820.485 94
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 820.634 870.743 610.697 690.601 630.781 740.437 700.585 890.493 800.446 840.933 840.394 840.011 1080.654 370.661 720.603 770.733 590.526 840.832 800.761 840.480 95
LAP-D0.594 830.720 720.692 810.637 900.456 930.773 790.391 850.730 620.587 510.445 860.940 730.381 870.288 340.434 910.453 910.591 820.649 870.581 600.777 880.749 880.610 58
DPC0.592 840.720 720.700 750.602 940.480 890.762 840.380 880.713 680.585 540.437 870.940 730.369 890.288 340.434 910.509 870.590 840.639 920.567 650.772 890.755 860.592 68
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 850.766 540.659 910.683 720.470 920.740 890.387 860.620 850.490 810.476 770.922 910.355 920.245 600.511 770.511 860.571 870.643 900.493 910.872 650.762 830.600 64
ROSMRF0.580 860.772 490.707 710.681 730.563 760.764 820.362 900.515 970.465 890.465 810.936 780.427 750.207 720.438 890.577 780.536 900.675 810.486 920.723 950.779 760.524 88
SD-DETR0.576 870.746 600.609 1000.445 1050.517 850.643 1010.366 890.714 670.456 910.468 800.870 1030.432 690.264 520.558 660.674 670.586 850.688 760.482 930.739 930.733 910.537 85
SQN_0.1%0.569 880.676 810.696 780.657 810.497 860.779 770.424 720.548 930.515 740.376 940.902 1000.422 770.357 70.379 950.456 900.596 810.659 850.544 770.685 980.665 1020.556 81
TextureNetpermissive0.566 890.672 830.664 890.671 770.494 870.719 910.445 630.678 750.411 990.396 920.935 790.356 910.225 650.412 930.535 820.565 880.636 930.464 950.794 870.680 990.568 75
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
DVVNet0.562 900.648 850.700 750.770 500.586 690.687 950.333 940.650 790.514 750.475 780.906 970.359 900.223 670.340 970.442 920.422 1010.668 830.501 880.708 960.779 760.534 86
Pointnet++ & Featurepermissive0.557 910.735 650.661 900.686 710.491 880.744 880.392 830.539 940.451 920.375 950.946 560.376 880.205 740.403 940.356 970.553 890.643 900.497 890.824 830.756 850.515 89
GMLPs0.538 920.495 1020.693 800.647 860.471 910.793 690.300 970.477 980.505 770.358 960.903 990.327 950.081 1030.472 860.529 840.448 990.710 650.509 850.746 910.737 900.554 82
PanopticFusion-label0.529 930.491 1030.688 840.604 930.386 980.632 1020.225 1070.705 710.434 960.293 1020.815 1050.348 930.241 610.499 810.669 680.507 920.649 870.442 1010.796 860.602 1050.561 78
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_weak0.516 940.676 810.591 1030.609 910.442 940.774 780.335 930.597 860.422 980.357 970.932 850.341 940.094 1020.298 990.528 850.473 970.676 800.495 900.602 1040.721 940.349 105
Online SegFusion0.515 950.607 920.644 940.579 960.434 950.630 1030.353 910.628 840.440 940.410 900.762 1080.307 970.167 900.520 750.403 950.516 910.565 970.447 990.678 990.701 960.514 90
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, FTSDF0.501 960.558 970.608 1010.424 1070.478 900.690 940.246 1030.586 880.468 870.450 830.911 950.394 840.160 930.438 890.212 1040.432 1000.541 1020.475 940.742 920.727 920.477 96
PCNN0.498 970.559 960.644 940.560 980.420 970.711 930.229 1050.414 990.436 950.352 980.941 710.324 960.155 940.238 1040.387 960.493 930.529 1030.509 850.813 850.751 870.504 91
3DMV0.484 980.484 1040.538 1050.643 880.424 960.606 1060.310 950.574 900.433 970.378 930.796 1060.301 980.214 710.537 730.208 1050.472 980.507 1060.413 1040.693 970.602 1050.539 84
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 990.577 950.611 990.356 1090.321 1060.715 920.299 990.376 1030.328 1060.319 1000.944 650.285 1000.164 910.216 1070.229 1020.484 950.545 1010.456 970.755 900.709 950.475 97
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 1000.679 800.604 1020.578 970.380 990.682 960.291 1000.106 1090.483 840.258 1070.920 920.258 1040.025 1070.231 1060.325 980.480 960.560 990.463 960.725 940.666 1010.231 109
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 1010.474 1050.623 970.463 1030.366 1010.651 990.310 950.389 1020.349 1040.330 990.937 760.271 1020.126 990.285 1000.224 1030.350 1060.577 960.445 1000.625 1020.723 930.394 101
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
SurfaceConvPF0.442 1020.505 1010.622 980.380 1080.342 1040.654 980.227 1060.397 1010.367 1020.276 1040.924 890.240 1050.198 790.359 960.262 1000.366 1030.581 950.435 1020.640 1010.668 1000.398 100
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET20.442 1020.548 990.548 1040.597 950.363 1020.628 1040.300 970.292 1040.374 1010.307 1010.881 1020.268 1030.186 830.238 1040.204 1060.407 1020.506 1070.449 980.667 1000.620 1040.462 99
Tangent Convolutionspermissive0.438 1040.437 1070.646 930.474 1020.369 1000.645 1000.353 910.258 1060.282 1080.279 1030.918 940.298 990.147 980.283 1010.294 990.487 940.562 980.427 1030.619 1030.633 1030.352 104
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1050.525 1000.647 920.522 990.324 1050.488 1090.077 1100.712 690.353 1030.401 910.636 1100.281 1010.176 860.340 970.565 800.175 1100.551 1000.398 1050.370 1100.602 1050.361 103
SPLAT Netcopyleft0.393 1060.472 1060.511 1060.606 920.311 1070.656 970.245 1040.405 1000.328 1060.197 1080.927 880.227 1070.000 1110.001 1110.249 1010.271 1090.510 1040.383 1070.593 1050.699 970.267 107
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 1070.297 1090.491 1070.432 1060.358 1030.612 1050.274 1010.116 1080.411 990.265 1050.904 980.229 1060.079 1040.250 1020.185 1070.320 1070.510 1040.385 1060.548 1060.597 1080.394 101
PointNet++permissive0.339 1080.584 940.478 1080.458 1040.256 1090.360 1100.250 1020.247 1070.278 1090.261 1060.677 1090.183 1080.117 1000.212 1080.145 1090.364 1040.346 1100.232 1100.548 1060.523 1090.252 108
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 1090.353 1080.290 1100.278 1100.166 1100.553 1070.169 1090.286 1050.147 1100.148 1100.908 960.182 1090.064 1050.023 1100.018 1110.354 1050.363 1080.345 1080.546 1080.685 980.278 106
ScanNetpermissive0.306 1100.203 1100.366 1090.501 1000.311 1070.524 1080.211 1080.002 1110.342 1050.189 1090.786 1070.145 1100.102 1010.245 1030.152 1080.318 1080.348 1090.300 1090.460 1090.437 1100.182 110
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 1110.000 1110.041 1110.172 1110.030 1110.062 1110.001 1110.035 1100.004 1110.051 1110.143 1110.019 1110.003 1100.041 1090.050 1100.003 1110.054 1110.018 1110.005 1110.264 1110.082 111


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
Spherical Mask(CtoF)0.812 11.000 10.973 30.852 100.718 30.917 30.574 20.677 240.748 60.729 60.715 40.795 10.809 11.000 10.831 30.854 60.787 71.000 10.638 3
OneFormer3Dcopyleft0.801 21.000 10.973 20.909 40.698 80.928 20.582 10.668 270.685 110.780 20.687 80.698 100.702 111.000 10.794 60.900 20.784 90.986 440.635 4
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
UniPerception0.800 31.000 10.930 60.872 80.727 20.862 160.454 110.764 130.820 10.746 50.706 60.750 20.772 80.926 370.764 100.818 200.826 10.997 340.660 2
ExtMask3D0.789 41.000 10.988 10.756 260.706 60.912 40.429 120.647 320.806 40.755 40.673 100.689 110.772 91.000 10.789 70.852 70.811 31.000 10.617 9
Queryformer0.787 51.000 10.933 50.601 410.754 10.886 90.558 40.661 290.767 50.665 110.716 30.639 170.808 31.000 10.844 10.897 30.804 41.000 10.624 6
MAFT0.786 61.000 10.894 110.807 160.694 100.893 70.486 70.674 250.740 70.786 10.704 70.727 40.739 101.000 10.707 160.849 90.756 161.000 10.685 1
Mask3D0.780 71.000 10.786 350.716 310.696 90.885 100.500 60.714 190.810 30.672 100.715 40.679 130.809 11.000 10.831 30.833 130.787 71.000 10.602 13
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SPFormerpermissive0.770 80.903 480.903 80.806 170.609 230.886 80.568 30.815 60.705 100.711 70.655 110.652 160.685 161.000 10.789 80.809 210.776 121.000 10.583 18
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SoftGroup++0.769 91.000 10.803 280.937 10.684 110.865 130.213 270.870 20.664 140.571 170.758 10.702 80.807 41.000 10.653 230.902 10.792 61.000 10.626 5
SIM3D0.766 101.000 10.948 40.582 470.599 250.882 110.510 50.701 210.632 180.772 30.685 90.687 120.782 71.000 10.833 20.756 310.798 51.000 10.622 7
SoftGrouppermissive0.761 111.000 10.808 240.845 110.716 40.862 150.243 240.824 40.655 160.620 120.734 20.699 90.791 60.981 310.716 140.844 100.769 131.000 10.594 16
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
ISBNetpermissive0.757 121.000 10.904 70.731 290.678 120.895 50.458 90.644 340.670 130.710 80.620 180.732 30.650 181.000 10.756 110.778 240.779 101.000 10.614 10
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
TD3Dpermissive0.751 131.000 10.774 360.867 90.621 190.934 10.404 130.706 200.812 20.605 150.633 160.626 180.690 151.000 10.640 250.820 170.777 111.000 10.612 11
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
PBNetpermissive0.747 141.000 10.818 200.837 130.713 50.844 180.457 100.647 320.711 90.614 130.617 200.657 150.650 181.000 10.692 170.822 160.765 151.000 10.595 15
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
GraphCut0.732 151.000 10.788 330.724 300.642 170.859 170.248 230.787 110.618 200.596 160.653 130.722 60.583 391.000 10.766 90.861 40.825 21.000 10.504 30
IPCA-Inst0.731 161.000 10.788 340.884 70.698 70.788 340.252 220.760 140.646 170.511 250.637 150.665 140.804 51.000 10.644 240.778 250.747 181.000 10.561 22
TopoSeg0.725 171.000 10.806 270.933 20.668 140.758 380.272 210.734 180.630 190.549 210.654 120.606 190.697 140.966 340.612 290.839 110.754 171.000 10.573 19
DKNet0.718 181.000 10.814 210.782 200.619 200.872 120.224 250.751 160.569 240.677 90.585 240.724 50.633 290.981 310.515 390.819 180.736 191.000 10.617 8
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
SSEC0.707 191.000 10.850 130.924 30.648 150.747 410.162 290.862 30.572 230.520 230.624 170.549 220.649 271.000 10.560 340.706 410.768 141.000 10.591 17
HAISpermissive0.699 201.000 10.849 140.820 140.675 130.808 280.279 190.757 150.465 300.517 240.596 220.559 210.600 331.000 10.654 220.767 270.676 230.994 400.560 23
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
SSTNetpermissive0.698 211.000 10.697 520.888 60.556 310.803 290.387 140.626 360.417 350.556 200.585 250.702 70.600 331.000 10.824 50.720 400.692 211.000 10.509 29
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
DualGroup0.694 221.000 10.799 300.811 150.622 180.817 230.376 150.805 90.590 220.487 290.568 280.525 260.650 180.835 470.600 300.829 140.655 261.000 10.526 26
SphereSeg0.680 231.000 10.856 120.744 270.618 210.893 60.151 300.651 310.713 80.537 220.579 270.430 360.651 171.000 10.389 500.744 350.697 200.991 420.601 14
DANCENET0.680 231.000 10.807 250.733 280.600 240.768 370.375 160.543 440.538 250.610 140.599 210.498 270.632 310.981 310.739 130.856 50.633 320.882 550.454 39
Box2Mask0.677 251.000 10.847 150.771 220.509 400.816 240.277 200.558 430.482 270.562 190.640 140.448 320.700 121.000 10.666 180.852 80.578 390.997 340.488 34
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
OccuSeg+instance0.672 261.000 10.758 440.682 340.576 290.842 190.477 80.504 500.524 260.567 180.585 260.451 310.557 411.000 10.751 120.797 220.563 421.000 10.467 38
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
Mask-Group0.664 271.000 10.822 190.764 250.616 220.815 250.139 340.694 230.597 210.459 330.566 290.599 200.600 330.516 570.715 150.819 190.635 301.000 10.603 12
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
INS-Conv-instance0.657 281.000 10.760 420.667 360.581 270.863 140.323 170.655 300.477 280.473 310.549 310.432 350.650 181.000 10.655 210.738 360.585 380.944 470.472 37
CSC-Pretrained0.648 291.000 10.810 220.768 230.523 380.813 260.143 330.819 50.389 380.422 420.511 350.443 330.650 181.000 10.624 270.732 370.634 311.000 10.375 46
PE0.645 301.000 10.773 380.798 190.538 330.786 350.088 420.799 100.350 420.435 400.547 320.545 230.646 280.933 360.562 330.761 300.556 470.997 340.501 32
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
RPGN0.643 311.000 10.758 430.582 480.539 320.826 220.046 470.765 120.372 400.436 390.588 230.539 250.650 181.000 10.577 310.750 330.653 280.997 340.495 33
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
Dyco3Dcopyleft0.641 321.000 10.841 160.893 50.531 350.802 300.115 390.588 410.448 320.438 370.537 340.430 370.550 420.857 390.534 370.764 290.657 250.987 430.568 20
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
GICN0.638 331.000 10.895 100.800 180.480 440.676 460.144 320.737 170.354 410.447 340.400 480.365 430.700 121.000 10.569 320.836 120.599 341.000 10.473 36
PointGroup0.636 341.000 10.765 390.624 380.505 420.797 310.116 380.696 220.384 390.441 350.559 300.476 290.596 361.000 10.666 180.756 320.556 460.997 340.513 28
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+Group0.635 350.667 500.797 320.714 320.562 300.774 360.146 310.810 80.429 340.476 300.546 330.399 390.633 291.000 10.632 260.722 390.609 331.000 10.514 27
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_evaluation0.631 361.000 10.829 180.606 400.646 160.836 200.068 430.511 480.462 310.507 260.619 190.389 410.610 321.000 10.432 450.828 150.673 240.788 590.552 24
DENet0.629 371.000 10.797 310.608 390.589 260.627 500.219 260.882 10.310 440.402 470.383 500.396 400.650 181.000 10.663 200.543 580.691 221.000 10.568 21
3D-MPA0.611 381.000 10.833 170.765 240.526 370.756 390.136 360.588 410.470 290.438 380.432 440.358 450.650 180.857 390.429 460.765 280.557 451.000 10.430 41
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
OSIS0.605 391.000 10.801 290.599 420.535 340.728 430.286 180.436 540.679 120.491 270.433 420.256 470.404 540.857 390.620 280.724 380.510 521.000 10.539 25
AOIA0.601 401.000 10.761 410.687 330.485 430.828 210.008 540.663 280.405 370.405 460.425 450.490 280.596 360.714 500.553 360.779 230.597 350.992 410.424 43
PCJC0.578 411.000 10.810 230.583 460.449 470.813 270.042 480.603 390.341 430.490 280.465 390.410 380.650 180.835 470.264 560.694 450.561 430.889 520.504 31
SSEN0.575 421.000 10.761 400.473 500.477 450.795 320.066 440.529 460.658 150.460 320.461 400.380 420.331 560.859 380.401 490.692 470.653 271.000 10.348 48
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
RWSeg0.567 430.528 600.708 510.626 370.580 280.745 420.063 450.627 350.240 480.400 480.497 360.464 300.515 431.000 10.475 410.745 340.571 401.000 10.429 42
NeuralBF0.555 440.667 500.896 90.843 120.517 390.751 400.029 490.519 470.414 360.439 360.465 380.000 660.484 450.857 390.287 540.693 460.651 291.000 10.485 35
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
MTML0.549 451.000 10.807 260.588 450.327 520.647 480.004 560.815 70.180 510.418 430.364 520.182 500.445 481.000 10.442 440.688 480.571 411.000 10.396 44
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
ClickSeg_Instance0.539 461.000 10.621 550.300 530.530 360.698 440.127 370.533 450.222 490.430 410.400 470.365 430.574 400.938 350.472 420.659 500.543 480.944 470.347 49
One_Thing_One_Clickpermissive0.529 470.667 500.718 470.777 210.399 480.683 450.000 590.669 260.138 540.391 490.374 510.539 240.360 550.641 540.556 350.774 260.593 360.997 340.251 54
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-CNN0.515 481.000 10.538 600.282 540.468 460.790 330.173 280.345 560.429 330.413 450.484 370.176 510.595 380.591 550.522 380.668 490.476 530.986 450.327 50
Occipital-SCS0.512 491.000 10.716 480.509 490.506 410.611 510.092 410.602 400.177 520.346 520.383 490.165 520.442 490.850 460.386 510.618 540.543 490.889 520.389 45
3D-BoNet0.488 501.000 10.672 540.590 440.301 540.484 610.098 400.620 370.306 450.341 530.259 560.125 540.434 510.796 490.402 480.499 600.513 510.909 510.439 40
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-inst0.478 510.667 500.712 500.595 430.259 570.550 570.000 590.613 380.175 530.250 580.434 410.437 340.411 530.857 390.485 400.591 570.267 630.944 470.359 47
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_WSIS0.470 520.667 500.685 530.677 350.372 500.562 550.000 590.482 510.244 470.316 550.298 530.052 610.442 500.857 390.267 550.702 420.559 441.000 10.287 52
SALoss-ResNet0.459 531.000 10.737 460.159 640.259 560.587 530.138 350.475 520.217 500.416 440.408 460.128 530.315 570.714 500.411 470.536 590.590 370.873 560.304 51
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)
MASCpermissive0.447 540.528 600.555 580.381 510.382 490.633 490.002 570.509 490.260 460.361 510.432 430.327 460.451 470.571 560.367 520.639 520.386 540.980 460.276 53
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
SegGroup_inspermissive0.445 550.667 500.773 370.185 610.317 530.656 470.000 590.407 550.134 550.381 500.267 550.217 490.476 460.714 500.452 430.629 530.514 501.000 10.222 57
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
3D-SISpermissive0.382 561.000 10.432 630.245 560.190 580.577 540.013 530.263 580.033 610.320 540.240 570.075 570.422 520.857 390.117 610.699 430.271 620.883 540.235 56
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
Hier3Dcopyleft0.323 570.667 500.542 590.264 550.157 610.550 560.000 590.205 610.009 630.270 570.218 580.075 570.500 440.688 530.007 670.698 440.301 590.459 640.200 58
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
UNet-backbone0.319 580.667 500.715 490.233 570.189 590.479 620.008 540.218 590.067 600.201 600.173 590.107 550.123 620.438 580.150 580.615 550.355 550.916 500.093 66
R-PointNet0.306 590.500 620.405 640.311 520.348 510.589 520.054 460.068 640.126 560.283 560.290 540.028 620.219 600.214 610.331 530.396 640.275 600.821 580.245 55
Region-18class0.284 600.250 660.751 450.228 590.270 550.521 580.000 590.468 530.008 650.205 590.127 600.000 660.068 640.070 650.262 570.652 510.323 570.740 600.173 59
SemRegionNet-20cls0.250 610.333 630.613 560.229 580.163 600.493 590.000 590.304 570.107 570.147 630.100 620.052 600.231 580.119 630.039 630.445 620.325 560.654 610.141 62
tmp0.248 620.667 500.437 620.188 600.153 620.491 600.000 590.208 600.094 590.153 620.099 630.057 590.217 610.119 630.039 630.466 610.302 580.640 620.140 63
3D-BEVIS0.248 620.667 500.566 570.076 650.035 670.394 650.027 510.035 660.098 580.099 650.030 660.025 630.098 630.375 600.126 600.604 560.181 650.854 570.171 60
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sem_Recon_ins0.227 640.764 490.486 610.069 660.098 640.426 640.017 520.067 650.015 620.172 610.100 610.096 560.054 660.183 620.135 590.366 650.260 640.614 630.168 61
ASIS0.199 650.333 630.253 660.167 630.140 630.438 630.000 590.177 620.008 640.121 640.069 640.004 650.231 590.429 590.036 650.445 630.273 610.333 660.119 65
Sgpn_scannet0.143 660.208 670.390 650.169 620.065 650.275 660.029 500.069 630.000 660.087 660.043 650.014 640.027 670.000 660.112 620.351 660.168 660.438 650.138 64
MaskRCNN 2d->3d Proj0.058 670.333 630.002 670.000 670.053 660.002 670.002 580.021 670.000 660.045 670.024 670.238 480.065 650.000 660.014 660.107 670.020 670.110 670.006 67


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 10.422 170.898 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 F