Presenting the ScanNet200 Benchmark

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

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

ScanNet200 Benchmark

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




Method Infoavg iouhead ioucommon ioutail ioualarm clockarmchairbackpackbagballbarbasketbathroom cabinetbathroom counterbathroom stallbathroom stall doorbathroom vanitybathtubbedbenchbicyclebinblackboardblanketblindsboardbookbookshelfbottlebowlboxbroombucketbulletin boardcabinetcalendarcandlecartcase of water bottlescd caseceilingceiling lightchairclockclosetcloset doorcloset rodcloset wallclothesclothes dryercoat rackcoffee kettlecoffee makercoffee tablecolumncomputer towercontainercopiercouchcountercratecupcurtaincushiondecorationdeskdining tabledish rackdishwasherdividerdoordoorframedresserdumbbelldustpanend tablefanfile cabinetfire alarmfire extinguisherfireplacefloorfolded chairfurnitureguitarguitar casehair dryerhandicap barhatheadphonesironing boardjacketkeyboardkeyboard pianokitchen cabinetkitchen counterladderlamplaptoplaundry basketlaundry detergentlaundry hamperledgelightlight switchluggagemachinemailboxmatmattressmicrowavemini fridgemirrormonitormousemusic standnightstandobjectoffice chairottomanovenpaperpaper bagpaper cutterpaper towel dispenserpaper towel rollpersonpianopicturepillarpillowpipeplantplateplungerposterpotted plantpower outletpower stripprinterprojectorprojector screenpurserackradiatorrailrange hoodrecycling binrefrigeratorscaleseatshelfshoeshowershower curtainshower curtain rodshower doorshower floorshower headshower wallsignsinksoap dishsoap dispensersofa chairspeakerstair railstairsstandstoolstorage binstorage containerstorage organizerstovestructurestuffed animalsuitcasetabletelephonetissue boxtoastertoaster oventoilettoilet papertoilet paper dispensertoilet paper holdertoilet seat cover dispensertoweltrash bintrash cantraytubetvtv standvacuum cleanerventwallwardrobewashing machinewater bottlewater coolerwater pitcherwhiteboardwindowwindowsill
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PTv3 ScanNet2000.393 10.592 10.330 10.216 10.520 10.109 20.108 100.000 10.337 10.000 10.310 90.394 60.494 80.753 70.848 10.256 20.717 20.000 30.842 10.192 20.065 20.449 50.346 10.546 30.190 70.000 50.384 40.000 10.000 30.218 10.505 10.791 10.000 10.136 10.000 20.903 10.073 90.687 30.000 40.168 10.551 20.387 50.941 10.000 10.000 20.397 70.654 30.000 70.714 30.759 90.752 40.118 40.264 20.926 10.000 10.048 20.575 20.000 70.597 10.366 10.755 10.469 10.474 10.798 10.140 60.617 10.692 30.000 40.592 20.971 10.188 20.000 10.133 40.593 10.349 10.650 10.717 40.699 10.455 10.790 10.523 30.636 10.301 10.000 10.622 20.000 60.017 90.259 10.000 30.921 20.337 10.733 10.210 10.514 10.860 60.407 10.000 10.688 10.109 60.000 90.000 40.000 10.151 10.671 40.782 10.115 70.641 10.903 10.349 10.616 10.088 40.832 20.000 30.480 10.000 10.428 10.000 20.497 60.000 10.000 50.000 10.662 20.690 10.612 10.828 10.575 10.000 10.404 40.644 10.325 30.887 20.728 10.009 100.134 50.026 110.000 10.761 10.731 10.172 30.077 20.528 20.727 20.000 10.603 40.220 20.022 20.000 10.740 10.000 20.000 10.661 10.586 10.566 10.436 40.531 10.978 10.457 10.708 10.583 30.141 70.748 10.000 10.026 10.822 10.871 30.879 50.000 10.851 10.405 20.914 10.000 10.682 20.000 90.281 10.738 10.463 4
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)
PonderV2 ScanNet2000.346 20.552 40.270 40.175 30.497 50.070 80.239 40.000 10.000 30.000 10.232 110.412 50.584 10.842 30.804 30.212 50.540 40.000 30.433 110.106 60.000 60.590 30.290 60.548 20.243 40.000 50.356 70.000 10.000 30.062 70.398 70.441 50.000 10.104 60.000 20.888 20.076 80.682 40.030 10.094 40.491 60.351 70.869 70.000 10.063 10.403 60.700 20.000 70.660 90.881 30.761 10.050 60.186 50.852 70.000 10.007 50.570 50.100 20.565 20.326 30.641 60.431 30.290 80.621 30.259 20.408 50.622 60.125 10.082 70.950 20.179 30.000 10.263 20.424 20.193 50.558 30.880 10.545 70.375 40.727 20.445 60.499 60.000 30.000 10.475 40.002 40.034 40.083 40.000 30.924 10.290 30.636 30.115 80.400 30.874 30.186 40.000 10.611 50.128 20.113 20.000 40.000 10.000 50.584 60.636 50.103 80.385 50.843 40.283 20.603 30.080 50.825 40.000 30.377 60.000 10.000 40.000 20.457 70.000 10.000 50.000 10.574 80.608 60.481 20.792 30.394 20.000 10.357 60.503 70.261 60.817 70.504 80.304 40.472 30.115 50.000 10.750 30.677 30.202 10.000 70.509 30.729 10.000 10.519 80.000 100.000 50.000 10.620 80.000 20.000 10.660 30.560 40.486 20.384 60.346 40.952 20.247 80.667 20.436 60.269 30.691 30.000 10.010 30.787 50.889 20.880 40.000 10.810 40.336 30.860 60.000 10.606 40.009 50.248 50.681 40.392 6
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.
CeCo0.340 30.551 50.247 70.181 20.475 70.057 110.142 80.000 10.000 30.000 10.387 30.463 30.499 60.924 20.774 60.213 40.257 70.000 30.546 100.100 70.006 50.615 10.177 110.534 40.246 30.000 50.400 20.000 10.338 10.006 100.484 30.609 20.000 10.083 70.000 20.873 60.089 40.661 80.000 40.048 100.560 10.408 40.892 50.000 10.000 20.586 10.616 50.000 70.692 60.900 20.721 60.162 10.228 30.860 50.000 10.000 70.575 20.083 30.550 30.347 20.624 70.410 70.360 30.740 20.109 80.321 90.660 40.000 40.121 40.939 70.143 60.000 10.400 10.003 70.190 60.564 20.652 60.615 50.421 20.304 90.579 10.547 30.000 30.000 10.296 80.000 60.030 50.096 30.000 30.916 30.037 70.551 60.171 40.376 40.865 50.286 20.000 10.633 20.102 90.027 50.011 30.000 10.000 50.474 80.742 20.133 40.311 70.824 60.242 70.503 80.068 60.828 30.000 30.429 30.000 10.063 30.000 20.781 10.000 10.000 50.000 10.665 10.633 40.450 30.818 20.000 60.000 10.429 20.532 40.226 70.825 50.510 70.377 30.709 10.079 80.000 10.753 20.683 20.102 100.063 30.401 100.620 80.000 10.619 20.000 100.000 50.000 10.595 90.000 20.000 10.345 80.564 30.411 40.603 10.384 30.945 40.266 60.643 30.367 80.304 10.663 60.000 10.010 30.726 90.767 60.898 30.000 10.784 70.435 10.861 50.000 10.447 60.000 90.257 40.656 70.377 7
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
OctFormer ScanNet200permissive0.326 70.539 60.265 60.131 60.499 40.110 10.522 10.000 10.000 30.000 10.318 80.427 40.455 90.743 90.765 70.175 60.842 10.000 30.828 20.204 10.033 30.429 60.335 20.601 10.312 20.000 50.357 60.000 10.000 30.047 80.423 50.000 60.000 10.105 50.000 20.873 60.079 70.670 70.000 40.117 20.471 80.432 20.829 80.000 10.000 20.584 20.417 110.089 30.684 70.837 60.705 100.021 90.178 60.892 20.000 10.028 40.505 80.000 70.457 60.200 80.662 20.412 60.244 90.496 50.000 110.451 40.626 50.000 40.102 60.943 60.138 80.000 10.000 70.149 40.291 30.534 50.722 30.632 40.331 70.253 100.453 50.487 70.000 30.000 10.479 30.000 60.022 70.000 60.000 30.900 60.128 50.684 20.164 50.413 20.854 80.000 60.000 10.512 110.074 110.003 70.000 40.000 10.000 50.469 90.613 70.132 50.529 40.871 20.227 100.582 40.026 110.787 60.000 30.339 90.000 10.000 40.000 20.626 40.000 10.029 40.000 10.587 50.612 50.411 40.724 70.000 60.000 10.407 30.552 20.513 10.849 40.655 30.408 20.000 70.296 20.000 10.686 90.645 80.145 50.022 50.414 80.633 60.000 10.637 10.224 10.000 50.000 10.650 50.000 20.000 10.622 50.535 70.343 60.483 30.230 70.943 50.289 50.618 40.596 20.140 80.679 40.000 10.022 20.783 60.620 90.906 10.000 10.806 50.137 80.865 30.000 10.378 70.000 90.168 110.680 50.227 10
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
PPT-SpUNet-F.T.0.332 60.556 30.270 30.123 80.519 20.091 30.349 20.000 10.000 30.000 10.339 60.383 70.498 70.833 40.807 20.241 30.584 30.000 30.755 40.124 40.000 60.608 20.330 40.530 60.314 10.000 50.374 50.000 10.000 30.197 20.459 40.000 60.000 10.117 20.000 20.876 40.095 10.682 40.000 40.086 50.518 40.433 10.930 20.000 10.000 20.563 30.542 80.077 40.715 20.858 50.756 30.008 110.171 70.874 40.000 10.039 30.550 60.000 70.545 40.256 50.657 50.453 20.351 40.449 70.213 30.392 60.611 70.000 40.037 90.946 30.138 80.000 10.000 70.063 50.308 20.537 40.796 20.673 20.323 80.392 60.400 80.509 50.000 30.000 10.649 10.000 60.023 60.000 60.000 30.914 50.002 100.506 100.163 60.359 50.872 40.000 60.000 10.623 40.112 40.001 80.000 40.000 10.021 30.753 10.565 100.150 10.579 20.806 70.267 40.616 10.042 100.783 70.000 30.374 70.000 10.000 40.000 20.620 50.000 10.000 50.000 10.572 90.634 30.350 60.792 30.000 60.000 10.376 50.535 30.378 20.855 30.672 20.074 70.000 70.185 40.000 10.727 60.660 60.076 110.000 70.432 60.646 50.000 10.594 60.006 90.000 50.000 10.658 40.000 20.000 10.661 10.549 50.300 80.291 80.045 80.942 60.304 40.600 50.572 40.135 100.695 20.000 10.008 50.793 40.942 10.899 20.000 10.816 30.181 60.897 20.000 10.679 30.223 30.264 20.691 30.345 9
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
Minkowski 34Dpermissive0.253 100.463 100.154 110.102 100.381 110.084 40.134 90.000 10.000 30.000 10.386 40.141 110.279 110.737 100.703 100.014 110.164 90.000 30.663 50.092 100.000 60.224 100.291 50.531 50.056 110.000 50.242 100.000 10.000 30.013 90.331 100.000 60.000 10.035 110.001 10.858 90.059 100.650 100.000 40.056 90.353 100.299 90.670 100.000 10.000 20.284 100.484 90.071 50.594 100.720 100.710 90.027 80.068 110.813 80.000 10.005 60.492 90.164 10.274 100.111 100.571 100.307 110.293 70.307 110.150 50.163 110.531 100.002 30.545 30.932 90.093 110.000 10.000 70.002 80.159 90.368 110.581 90.440 110.228 110.406 50.282 110.294 100.000 30.000 10.189 100.060 10.036 30.000 60.000 30.897 70.000 110.525 80.025 110.205 110.771 110.000 60.000 10.593 80.108 70.044 40.000 40.000 10.000 50.282 110.589 90.094 100.169 100.466 110.227 100.419 110.125 30.757 80.002 10.334 100.000 10.000 40.000 20.357 90.000 10.000 50.000 10.582 60.513 110.337 70.612 110.000 60.000 10.250 100.352 110.136 110.724 100.655 30.280 50.000 70.046 100.000 10.606 110.559 90.159 40.102 10.445 40.655 40.000 10.310 110.117 30.000 50.000 10.581 110.026 10.000 10.265 110.483 100.084 110.097 110.044 90.865 110.142 110.588 60.351 90.272 20.596 110.000 10.003 60.622 100.720 70.096 110.000 10.771 100.016 100.772 90.000 10.302 90.194 40.214 80.621 100.197 11
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrainpermissive0.249 110.455 110.171 100.079 110.418 100.059 100.186 70.000 10.000 30.000 10.335 70.250 90.316 100.766 60.697 110.142 80.170 80.003 20.553 90.112 50.097 10.201 110.186 80.476 110.081 100.000 50.216 110.000 10.000 30.001 110.314 110.000 60.000 10.055 90.000 20.832 110.094 20.659 90.002 20.076 60.310 110.293 110.664 110.000 10.000 20.175 110.634 40.130 20.552 110.686 110.700 110.076 50.110 90.770 110.000 10.000 70.430 110.000 70.319 90.166 90.542 110.327 100.205 100.332 100.052 100.375 70.444 110.000 40.012 110.930 110.203 10.000 10.000 70.046 60.175 80.413 100.592 80.471 100.299 90.152 110.340 100.247 110.000 30.000 10.225 90.058 20.037 20.000 60.207 10.862 100.014 80.548 70.033 100.233 100.816 100.000 60.000 10.542 100.123 30.121 10.019 20.000 10.000 50.463 100.454 110.045 110.128 110.557 100.235 80.441 100.063 80.484 110.000 30.308 110.000 10.000 40.000 20.318 110.000 10.000 50.000 10.545 100.543 90.164 100.734 60.000 60.000 10.215 110.371 100.198 80.743 80.205 100.062 90.000 70.079 80.000 10.683 100.547 100.142 60.000 70.441 50.579 100.000 10.464 90.098 60.041 10.000 10.590 100.000 20.000 10.373 70.494 80.174 90.105 100.001 110.895 100.222 100.537 70.307 100.180 50.625 80.000 10.000 80.591 110.609 100.398 90.000 10.766 110.014 110.638 110.000 10.377 80.004 70.206 90.609 110.465 3
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
AWCS0.305 80.508 80.225 80.142 50.463 80.063 90.195 60.000 10.000 30.000 10.467 20.551 10.504 50.773 50.764 80.142 80.029 110.000 30.626 80.100 70.000 60.360 80.179 90.507 90.137 90.006 40.300 80.000 10.000 30.172 50.364 90.512 40.000 10.056 80.000 20.865 80.093 30.634 110.000 40.071 80.396 90.296 100.876 60.000 10.000 20.373 80.436 100.063 60.749 10.877 40.721 60.131 30.124 80.804 90.000 10.000 70.515 70.010 60.452 70.252 60.578 80.417 50.179 110.484 60.171 40.337 80.606 80.000 40.115 50.937 80.142 70.000 10.008 60.000 90.157 100.484 80.402 110.501 90.339 60.553 30.529 20.478 80.000 30.000 10.404 60.001 50.022 70.077 50.000 30.894 80.219 40.628 40.093 90.305 80.886 10.233 30.000 10.603 60.112 40.023 60.000 40.000 10.000 50.741 20.664 40.097 90.253 80.782 80.264 50.523 70.154 10.707 100.000 30.411 40.000 10.000 40.000 20.332 100.000 10.000 50.000 10.602 30.595 70.185 90.656 100.159 30.000 10.355 70.424 90.154 90.729 90.516 60.220 60.620 20.084 70.000 10.707 80.651 70.173 20.014 60.381 110.582 90.000 10.619 20.049 80.000 50.000 10.702 20.000 20.000 10.302 100.489 90.317 70.334 70.392 20.922 80.254 70.533 80.394 70.129 110.613 90.000 10.000 80.820 20.649 80.749 80.000 10.782 80.282 50.863 40.000 10.288 100.006 60.220 70.633 80.542 2
OA-CNN-L_ScanNet2000.333 50.558 20.269 50.124 70.448 90.080 50.272 30.000 10.000 30.000 10.342 50.515 20.524 40.713 110.789 40.158 70.384 60.000 30.806 30.125 30.000 60.496 40.332 30.498 100.227 50.024 20.474 10.000 10.003 20.071 60.487 20.000 60.000 10.110 40.000 20.876 40.013 110.703 10.000 40.076 60.473 70.355 60.906 40.000 10.000 20.476 40.706 10.000 70.672 80.835 70.748 50.015 100.223 40.860 50.000 10.000 70.572 40.000 70.509 50.313 40.662 20.398 80.396 20.411 90.276 10.527 20.711 20.000 40.076 80.946 30.166 40.000 10.022 50.160 30.183 70.493 70.699 50.637 30.403 30.330 80.406 70.526 40.024 20.000 10.392 70.000 60.016 100.000 60.196 20.915 40.112 60.557 50.197 20.352 60.877 20.000 60.000 10.592 90.103 80.000 90.067 10.000 10.089 20.735 30.625 60.130 60.568 30.836 50.271 30.534 50.043 90.799 50.001 20.445 20.000 10.000 40.024 10.661 20.000 10.262 20.000 10.591 40.517 100.373 50.788 50.021 50.000 10.455 10.517 50.320 40.823 60.200 110.001 110.150 40.100 60.000 10.736 50.668 40.103 90.052 40.662 10.720 30.000 10.602 50.112 40.002 40.000 10.637 60.000 20.000 10.621 60.569 20.398 50.412 50.234 60.949 30.363 20.492 90.495 50.251 40.665 50.000 10.001 70.805 30.833 50.794 60.000 10.821 20.314 40.843 80.000 10.560 50.245 20.262 30.713 20.370 8
LGroundpermissive0.272 90.485 90.184 90.106 90.476 60.077 60.218 50.000 10.000 30.000 10.547 10.295 80.540 30.746 80.745 90.058 100.112 100.005 10.658 60.077 110.000 60.322 90.178 100.512 80.190 70.199 10.277 90.000 10.000 30.173 40.399 60.000 60.000 10.039 100.000 20.858 90.085 50.676 60.002 20.103 30.498 50.323 80.703 90.000 10.000 20.296 90.549 70.216 10.702 40.768 80.718 80.028 70.092 100.786 100.000 10.000 70.453 100.022 50.251 110.252 60.572 90.348 90.321 50.514 40.063 90.279 100.552 90.000 40.019 100.932 90.132 100.000 10.000 70.000 90.156 110.457 90.623 70.518 80.265 100.358 70.381 90.395 90.000 30.000 10.127 110.012 30.051 10.000 60.000 30.886 90.014 80.437 110.179 30.244 90.826 90.000 60.000 10.599 70.136 10.085 30.000 40.000 10.000 50.565 70.612 80.143 20.207 90.566 90.232 90.446 90.127 20.708 90.000 30.384 50.000 10.000 40.000 20.402 80.000 10.059 30.000 10.525 110.566 80.229 80.659 90.000 60.000 10.265 90.446 80.147 100.720 110.597 50.066 80.000 70.187 30.000 10.726 70.467 110.134 70.000 70.413 90.629 70.000 10.363 100.055 70.022 20.000 10.626 70.000 20.000 10.323 90.479 110.154 100.117 90.028 100.901 90.243 90.415 100.295 110.143 60.610 100.000 10.000 80.777 70.397 110.324 100.000 10.778 90.179 70.702 100.000 10.274 110.404 10.233 60.622 90.398 5
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
L3DETR-ScanNet_2000.336 40.533 70.279 20.155 40.508 30.073 70.101 110.000 10.058 20.000 10.294 100.233 100.548 20.927 10.788 50.264 10.463 50.000 30.638 70.098 90.014 40.411 70.226 70.525 70.225 60.010 30.397 30.000 10.000 30.192 30.380 80.598 30.000 10.117 20.000 20.883 30.082 60.689 20.000 40.032 110.549 30.417 30.910 30.000 10.000 20.448 50.613 60.000 70.697 50.960 10.759 20.158 20.293 10.883 30.000 10.312 10.583 10.079 40.422 80.068 110.660 40.418 40.298 60.430 80.114 70.526 30.776 10.051 20.679 10.946 30.152 50.000 10.183 30.000 90.211 40.511 60.409 100.565 60.355 50.448 40.512 40.557 20.000 30.000 10.420 50.000 60.007 110.104 20.000 30.125 110.330 20.514 90.146 70.321 70.860 60.174 50.000 10.629 30.075 100.000 90.000 40.000 10.002 40.671 40.712 30.141 30.339 60.856 30.261 60.529 60.067 70.835 10.000 30.369 80.000 10.259 20.000 20.629 30.000 10.487 10.000 10.579 70.646 20.107 110.720 80.122 40.000 10.333 80.505 60.303 50.908 10.503 90.565 10.074 60.324 10.000 10.740 40.661 50.109 80.000 70.427 70.563 110.000 10.579 70.108 50.000 50.000 10.664 30.000 20.000 10.641 40.539 60.416 30.515 20.256 50.940 70.312 30.209 110.620 10.138 90.636 70.000 10.000 80.775 80.861 40.765 70.000 10.801 60.119 90.860 60.000 10.687 10.001 80.192 100.679 60.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12


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




Method Infoavg ap 25%head ap 25%common ap 25%tail ap 25%alarm clockarmchairbackpackbagballbarbasketbathroom cabinetbathroom counterbathroom stallbathroom stall doorbathroom vanitybathtubbedbenchbicyclebinblackboardblanketblindsboardbookbookshelfbottlebowlboxbroombucketbulletin boardcabinetcalendarcandlecartcase of water bottlescd caseceilingceiling lightchairclockclosetcloset doorcloset rodcloset wallclothesclothes dryercoat rackcoffee kettlecoffee makercoffee tablecolumncomputer towercontainercopiercouchcountercratecupcurtaincushiondecorationdeskdining tabledish rackdishwasherdividerdoordoorframedresserdumbbelldustpanend tablefanfile cabinetfire alarmfire extinguisherfireplacefolded chairfurnitureguitarguitar casehair dryerhandicap barhatheadphonesironing boardjacketkeyboardkeyboard pianokitchen cabinetkitchen counterladderlamplaptoplaundry basketlaundry detergentlaundry hamperledgelightlight switchluggagemachinemailboxmatmattressmicrowavemini fridgemirrormonitormousemusic standnightstandobjectoffice chairottomanovenpaperpaper bagpaper cutterpaper towel dispenserpaper towel rollpersonpianopicturepillarpillowpipeplantplateplungerposterpotted plantpower outletpower stripprinterprojectorprojector screenpurserackradiatorrailrange hoodrecycling binrefrigeratorscaleseatshelfshoeshowershower curtainshower curtain rodshower doorshower floorshower headshower wallsignsinksoap dishsoap dispensersofa chairspeakerstair railstairsstandstoolstorage binstorage containerstorage organizerstovestructurestuffed animalsuitcasetabletelephonetissue boxtoastertoaster oventoilettoilet papertoilet paper dispensertoilet paper holdertoilet seat cover dispensertoweltrash bintrash cantraytubetvtv standvacuum cleanerventwardrobewashing machinewater bottlewater coolerwater pitcherwhiteboardwindowwindowsill
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
Mask3D Scannet2000.445 10.653 10.392 10.254 10.648 10.097 10.125 50.000 10.000 10.000 10.657 10.971 10.451 21.000 11.000 10.640 10.500 10.045 11.000 10.241 20.409 10.363 10.440 10.686 30.300 10.000 10.201 10.000 10.009 10.290 10.556 11.000 10.000 10.063 30.000 10.830 10.573 10.844 20.333 10.204 10.058 50.158 50.552 20.056 10.000 11.000 10.725 40.750 10.927 11.000 10.888 40.042 30.120 20.615 40.226 10.250 10.890 10.792 10.677 20.510 20.818 10.699 10.512 20.167 50.125 10.315 20.943 10.309 10.017 30.200 30.000 10.188 10.000 10.183 30.815 11.000 10.827 10.741 10.442 30.414 40.600 10.000 10.000 10.458 10.049 30.321 10.381 10.000 10.908 20.400 10.841 10.260 10.710 10.966 10.265 10.000 10.924 10.152 10.025 20.500 10.027 10.028 11.000 10.556 50.016 10.080 50.500 10.694 30.608 10.084 10.604 30.194 10.538 30.000 10.500 10.000 20.354 40.000 11.000 10.000 10.761 20.930 10.053 40.890 31.000 10.008 20.262 10.358 21.000 11.000 10.792 40.966 11.000 10.765 20.004 20.930 10.780 20.330 20.027 20.625 10.974 40.050 10.412 50.021 20.000 30.000 20.778 10.000 10.000 10.493 20.746 20.454 10.335 20.396 10.930 50.551 21.000 10.552 10.606 10.853 10.000 10.004 10.806 11.000 10.727 20.000 10.042 30.745 20.000 10.399 40.391 10.630 10.721 10.619 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TD3D Scannet200permissive0.379 20.603 20.306 20.190 20.635 20.073 20.500 10.000 10.000 10.000 10.495 30.735 20.275 51.000 10.979 20.590 20.000 40.021 20.000 30.146 30.000 20.356 20.173 50.795 10.226 20.000 10.173 20.000 10.000 20.226 20.390 20.000 20.000 10.250 10.000 10.706 20.061 30.885 10.093 20.186 20.259 40.200 10.667 10.000 20.000 10.667 20.825 10.250 40.834 41.000 10.958 10.553 10.111 30.748 10.220 20.051 20.866 20.792 10.390 50.045 50.800 20.302 50.517 10.533 30.113 20.427 10.843 20.000 20.458 10.600 10.000 10.101 20.000 10.259 10.717 20.500 20.615 20.520 20.526 20.457 10.270 40.000 10.000 10.400 20.088 20.294 20.181 20.000 11.000 10.400 10.710 50.103 30.477 50.905 20.061 20.000 10.906 20.102 20.232 10.125 20.000 20.003 20.792 31.000 10.000 20.102 30.125 40.559 50.523 30.075 20.715 10.000 20.424 50.000 10.396 20.250 10.638 10.000 10.000 20.000 10.622 50.833 20.221 10.970 10.250 20.038 10.260 20.415 10.125 21.000 11.000 10.857 20.000 20.908 10.012 10.869 30.836 10.635 10.111 10.625 11.000 10.020 20.510 10.003 30.009 21.000 10.778 10.000 10.000 10.370 30.755 10.288 20.333 30.274 21.000 10.557 10.731 20.456 20.433 30.769 50.000 10.000 20.621 41.000 10.458 40.000 10.196 20.817 10.000 10.472 10.222 30.205 50.689 20.274 3
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
Minkowski 34D Inst.permissive0.280 40.488 40.192 50.124 40.593 40.010 40.500 10.000 10.000 10.000 10.447 40.535 40.445 31.000 10.861 40.400 30.225 20.000 30.000 30.142 40.000 20.074 40.342 30.467 50.067 30.000 10.119 50.000 10.000 20.000 40.337 50.000 20.000 10.000 40.000 10.506 50.070 20.804 40.000 30.000 40.333 30.172 30.150 50.000 20.000 10.479 50.745 30.000 50.830 51.000 10.904 30.167 20.090 40.732 20.000 30.000 30.443 40.000 30.500 30.542 10.772 50.396 40.077 50.385 40.044 40.118 50.777 40.000 20.000 40.200 30.000 10.000 30.000 10.148 40.502 40.500 20.419 40.159 50.281 40.404 50.317 30.000 10.000 10.200 30.000 40.077 30.000 30.000 10.750 30.200 30.715 40.021 40.551 20.828 50.000 30.000 10.743 40.059 50.000 30.000 30.000 20.000 30.125 50.648 30.000 20.191 20.500 10.669 40.502 40.000 50.568 40.000 20.516 40.000 10.000 30.000 20.305 50.000 10.000 20.000 10.825 10.833 20.021 50.918 20.000 30.000 30.191 40.346 40.100 40.981 31.000 10.286 40.000 20.000 50.000 30.868 40.648 50.292 30.000 30.375 31.000 10.000 30.500 20.000 40.333 10.000 20.538 50.000 10.000 10.213 50.518 40.098 40.528 10.250 30.997 30.284 50.677 30.398 30.167 40.790 40.000 10.000 20.618 50.903 50.200 50.000 10.333 10.333 40.000 10.442 30.083 40.213 40.587 40.131 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.275 50.466 50.218 40.110 50.625 30.007 50.500 10.000 10.000 10.000 10.000 50.222 50.377 41.000 10.661 50.400 30.000 40.000 30.000 30.119 50.000 20.000 50.277 40.685 40.067 30.000 10.132 30.000 10.000 20.000 40.367 40.000 20.000 10.000 40.000 10.591 30.055 40.783 50.000 30.014 30.500 20.161 40.278 30.000 20.000 10.667 20.768 20.500 20.866 21.000 10.829 50.000 40.019 50.555 50.000 30.000 30.305 50.000 30.750 10.200 40.783 40.429 30.395 30.677 20.020 50.286 30.584 50.000 20.000 40.115 50.000 10.000 30.000 10.145 50.423 50.500 20.364 50.369 40.571 10.448 30.206 50.000 10.000 10.200 30.106 10.065 50.000 30.000 10.750 30.200 30.774 20.000 50.501 30.841 40.000 30.000 10.692 50.063 40.000 30.000 30.000 20.000 30.500 40.649 20.000 20.084 40.125 40.719 10.413 50.004 40.450 50.000 20.638 10.000 10.000 30.000 20.505 30.000 10.000 20.000 10.727 30.833 20.221 20.779 50.000 30.000 30.168 50.311 50.125 20.571 40.500 50.143 50.000 20.250 40.000 30.869 20.667 40.162 50.000 30.250 41.000 10.000 30.500 20.000 40.000 30.000 20.689 40.000 10.000 10.312 40.383 50.114 30.333 30.000 40.997 30.420 30.613 40.212 50.500 20.819 20.000 10.000 20.768 21.000 10.918 10.000 10.000 40.278 50.000 10.333 50.000 50.353 20.546 50.258 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.314 30.529 30.225 30.155 30.578 50.010 30.500 10.000 10.000 10.000 10.515 20.556 30.696 11.000 10.927 30.400 30.083 30.000 31.000 10.252 10.000 20.167 30.350 20.731 20.067 30.000 10.123 40.000 10.000 20.036 30.372 30.000 20.000 10.250 10.000 10.569 40.031 50.810 30.000 30.000 40.630 10.183 20.278 30.000 20.000 10.582 40.589 50.500 20.863 31.000 10.940 20.000 40.144 10.716 30.000 30.000 30.484 30.000 30.500 30.400 30.798 30.500 20.278 40.750 10.093 30.166 40.783 30.000 20.200 20.400 20.000 10.000 30.000 10.219 20.539 30.500 20.578 30.413 30.181 50.457 20.375 20.000 10.000 10.050 50.000 40.077 40.000 30.000 10.500 50.000 50.743 30.250 20.488 40.846 30.000 30.000 10.800 30.069 30.000 30.000 30.000 20.000 31.000 10.607 40.000 20.200 10.500 10.694 20.528 20.063 30.659 20.000 20.594 20.000 10.000 30.000 20.571 20.000 10.000 20.000 10.716 40.647 50.221 20.857 40.000 30.000 30.217 30.346 30.071 50.530 51.000 10.429 30.000 20.286 30.000 30.826 50.706 30.208 40.000 30.250 40.744 50.000 30.500 20.042 10.000 30.000 20.746 30.000 10.000 10.517 10.625 30.085 50.333 30.000 41.000 10.378 40.533 50.376 40.042 50.814 30.000 10.000 20.765 31.000 10.600 30.000 10.000 40.667 30.000 10.472 10.333 20.337 30.605 30.305 2
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.


ScanNet Benchmark

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PTv3 ScanNet0.794 10.941 30.813 180.851 70.782 60.890 20.597 10.916 20.696 80.713 30.979 10.635 10.384 20.793 20.907 80.821 40.790 300.696 110.967 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. CVPR 2024 (Oral)
PonderV20.785 20.978 10.800 260.833 220.788 40.853 160.545 160.910 50.713 10.705 40.979 10.596 70.390 10.769 110.832 410.821 40.792 290.730 10.975 10.897 40.785 4
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 10.843 160.781 70.858 120.575 60.831 320.685 140.714 20.979 10.594 80.310 260.801 10.892 160.841 20.819 40.723 40.940 130.887 60.725 23
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 40.861 200.818 140.836 190.790 30.875 40.576 50.905 60.704 50.739 10.969 100.611 20.349 100.756 210.958 10.702 440.805 140.708 70.916 310.898 30.801 2
TTT-KD0.773 50.646 900.818 140.809 340.774 90.878 30.581 20.943 10.687 120.704 50.978 40.607 50.336 150.775 80.912 60.838 30.823 20.694 120.967 30.899 20.794 3
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 60.939 40.824 60.854 60.771 100.840 300.564 100.900 80.686 130.677 110.961 160.537 300.348 110.769 110.903 100.785 100.815 60.676 210.939 140.880 110.772 8
PPT-SpUNet-Joint0.766 70.932 50.794 320.829 240.751 220.854 140.540 200.903 70.630 330.672 140.963 140.565 210.357 80.788 30.900 120.737 250.802 150.685 160.950 70.887 60.780 5
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 70.925 70.808 220.849 90.786 50.846 260.566 90.876 140.690 100.674 130.960 170.576 170.226 660.753 230.904 90.777 120.815 60.722 50.923 270.877 130.776 7
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net0.764 90.924 80.819 120.840 170.757 170.853 160.580 30.848 250.709 30.643 230.958 200.587 120.295 320.753 230.884 200.758 190.815 60.725 30.927 240.867 210.743 14
OccuSeg+Semantic0.764 90.758 580.796 300.839 180.746 240.907 10.562 110.850 240.680 160.672 140.978 40.610 30.335 170.777 60.819 440.847 10.830 10.691 140.972 20.885 80.727 21
O-CNNpermissive0.762 110.924 80.823 70.844 150.770 110.852 180.577 40.847 270.711 20.640 270.958 200.592 90.217 720.762 160.888 170.758 190.813 100.726 20.932 220.868 200.744 13
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
DTC0.757 120.843 260.820 100.847 120.791 20.862 100.511 320.870 160.707 40.652 190.954 340.604 60.279 430.760 170.942 20.734 260.766 430.701 100.884 530.874 180.736 15
OA-CNN-L_ScanNet200.756 130.783 440.826 50.858 40.776 80.837 330.548 150.896 110.649 250.675 120.962 150.586 130.335 170.771 100.802 480.770 150.787 320.691 140.936 170.880 110.761 10
ConDaFormer0.755 140.927 60.822 80.836 190.801 10.849 210.516 300.864 210.651 240.680 100.958 200.584 150.282 400.759 190.855 310.728 280.802 150.678 180.880 580.873 190.756 11
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
PNE0.755 140.786 420.835 40.834 210.758 150.849 210.570 80.836 310.648 260.668 160.978 40.581 160.367 60.683 340.856 290.804 60.801 190.678 180.961 50.889 50.716 28
P. Hermosilla: Point Neighborhood Embeddings.
DMF-Net0.752 160.906 120.793 340.802 400.689 390.825 450.556 120.867 170.681 150.602 430.960 170.555 260.365 70.779 50.859 260.747 220.795 260.717 60.917 300.856 290.764 9
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
PointTransformerV20.752 160.742 660.809 210.872 10.758 150.860 110.552 130.891 120.610 400.687 60.960 170.559 240.304 290.766 140.926 40.767 160.797 220.644 320.942 110.876 160.722 25
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
PointConvFormer0.749 180.793 400.790 350.807 360.750 230.856 130.524 260.881 130.588 520.642 260.977 80.591 100.274 460.781 40.929 30.804 60.796 230.642 330.947 90.885 80.715 29
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
BPNetcopyleft0.749 180.909 100.818 140.811 320.752 200.839 320.485 460.842 280.673 170.644 220.957 240.528 360.305 280.773 90.859 260.788 80.818 50.693 130.916 310.856 290.723 24
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MSP0.748 200.623 930.804 240.859 30.745 250.824 470.501 360.912 40.690 100.685 80.956 250.567 200.320 230.768 130.918 50.720 330.802 150.676 210.921 280.881 100.779 6
StratifiedFormerpermissive0.747 210.901 130.803 250.845 140.757 170.846 260.512 310.825 350.696 80.645 210.956 250.576 170.262 570.744 280.861 250.742 230.770 410.705 80.899 430.860 260.734 16
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
VMNetpermissive0.746 220.870 180.838 20.858 40.729 300.850 200.501 360.874 150.587 530.658 180.956 250.564 220.299 300.765 150.900 120.716 360.812 110.631 380.939 140.858 270.709 30
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 MVFusion0.746 220.771 520.819 120.848 110.702 360.865 90.397 840.899 90.699 60.664 170.948 540.588 110.330 190.746 270.851 350.764 170.796 230.704 90.935 180.866 220.728 19
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-FPN0.744 240.842 270.800 260.767 540.740 260.836 350.541 180.914 30.672 180.626 310.958 200.552 270.272 480.777 60.886 190.696 450.801 190.674 240.941 120.858 270.717 26
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-Net0.743 250.620 940.799 290.849 90.730 290.822 490.493 430.897 100.664 190.681 90.955 280.562 230.378 30.760 170.903 100.738 240.801 190.673 250.907 350.877 130.745 12
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT0.742 260.860 210.765 480.819 270.769 120.848 230.533 220.829 330.663 200.631 300.955 280.586 130.274 460.753 230.896 140.729 270.760 490.666 270.921 280.855 310.733 17
LRPNet0.742 260.816 350.806 230.807 360.752 200.828 430.575 60.839 300.699 60.637 280.954 340.520 390.320 230.755 220.834 390.760 180.772 380.676 210.915 330.862 240.717 26
LargeKernel3D0.739 280.909 100.820 100.806 380.740 260.852 180.545 160.826 340.594 510.643 230.955 280.541 290.263 560.723 320.858 280.775 140.767 420.678 180.933 200.848 360.694 35
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
MinkowskiNetpermissive0.736 290.859 220.818 140.832 230.709 340.840 300.521 280.853 230.660 220.643 230.951 440.544 280.286 380.731 300.893 150.675 540.772 380.683 170.874 650.852 340.727 21
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
RPN0.736 290.776 480.790 350.851 70.754 190.854 140.491 450.866 190.596 500.686 70.955 280.536 310.342 130.624 490.869 220.787 90.802 150.628 390.927 240.875 170.704 32
IPCA0.731 310.890 140.837 30.864 20.726 310.873 50.530 250.824 360.489 860.647 200.978 40.609 40.336 150.624 490.733 570.758 190.776 360.570 640.949 80.877 130.728 19
SparseConvNet0.725 320.647 890.821 90.846 130.721 320.869 60.533 220.754 570.603 460.614 350.955 280.572 190.325 210.710 330.870 210.724 310.823 20.628 390.934 190.865 230.683 38
PointTransformer++0.725 320.727 740.811 200.819 270.765 130.841 290.502 350.814 410.621 360.623 330.955 280.556 250.284 390.620 510.866 230.781 110.757 530.648 300.932 220.862 240.709 30
MatchingNet0.724 340.812 370.812 190.810 330.735 280.834 370.495 420.860 220.572 600.602 430.954 340.512 410.280 420.757 200.845 370.725 300.780 340.606 490.937 160.851 350.700 34
INS-Conv-semantic0.717 350.751 610.759 510.812 310.704 350.868 70.537 210.842 280.609 420.608 390.953 380.534 330.293 330.616 520.864 240.719 350.793 270.640 340.933 200.845 400.663 44
PointMetaBase0.714 360.835 280.785 370.821 250.684 410.846 260.531 240.865 200.614 370.596 470.953 380.500 440.246 620.674 350.888 170.692 460.764 450.624 410.849 800.844 410.675 40
contrastBoundarypermissive0.705 370.769 550.775 420.809 340.687 400.820 520.439 720.812 420.661 210.591 490.945 620.515 400.171 900.633 460.856 290.720 330.796 230.668 260.889 500.847 370.689 36
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 380.774 500.800 260.793 450.760 140.847 250.471 500.802 450.463 930.634 290.968 120.491 470.271 500.726 310.910 70.706 400.815 60.551 760.878 590.833 420.570 76
RFCR0.702 390.889 150.745 620.813 300.672 440.818 560.493 430.815 400.623 340.610 370.947 560.470 560.249 610.594 550.848 360.705 410.779 350.646 310.892 480.823 480.611 59
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 Click0.701 400.825 320.796 300.723 610.716 330.832 390.433 740.816 380.634 310.609 380.969 100.418 820.344 120.559 670.833 400.715 370.808 130.560 700.902 400.847 370.680 39
JSENetpermissive0.699 410.881 170.762 490.821 250.667 450.800 680.522 270.792 480.613 380.607 400.935 820.492 460.205 770.576 600.853 330.691 480.758 510.652 290.872 680.828 450.649 48
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-Click0.693 420.743 650.794 320.655 840.684 410.822 490.497 410.719 670.622 350.617 340.977 80.447 690.339 140.750 260.664 730.703 430.790 300.596 540.946 100.855 310.647 49
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 430.732 700.772 430.786 460.677 430.866 80.517 290.848 250.509 790.626 310.952 420.536 310.225 680.545 730.704 640.689 510.810 120.564 690.903 390.854 330.729 18
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 440.884 160.754 550.795 430.647 520.818 560.422 760.802 450.612 390.604 410.945 620.462 590.189 850.563 660.853 330.726 290.765 440.632 370.904 370.821 510.606 63
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 450.704 790.741 660.754 580.656 470.829 410.501 360.741 620.609 420.548 570.950 480.522 380.371 40.633 460.756 520.715 370.771 400.623 420.861 760.814 540.658 45
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 460.866 190.748 590.819 270.645 540.794 710.450 620.802 450.587 530.604 410.945 620.464 580.201 800.554 690.840 380.723 320.732 630.602 520.907 350.822 500.603 66
KP-FCNN0.684 470.847 250.758 530.784 480.647 520.814 590.473 490.772 510.605 440.594 480.935 820.450 670.181 880.587 560.805 470.690 490.785 330.614 450.882 550.819 520.632 55
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 470.728 730.757 540.776 510.690 370.804 660.464 550.816 380.577 590.587 500.945 620.508 430.276 450.671 360.710 620.663 590.750 570.589 590.881 560.832 440.653 47
DGNet0.684 470.712 780.784 380.782 500.658 460.835 360.499 400.823 370.641 280.597 460.950 480.487 490.281 410.575 610.619 770.647 670.764 450.620 440.871 710.846 390.688 37
PointContrast_LA_SEM0.683 500.757 590.784 380.786 460.639 560.824 470.408 790.775 500.604 450.541 590.934 860.532 340.269 520.552 700.777 500.645 700.793 270.640 340.913 340.824 470.671 41
Superpoint Network0.683 500.851 240.728 700.800 420.653 490.806 640.468 520.804 430.572 600.602 430.946 590.453 660.239 650.519 780.822 420.689 510.762 480.595 560.895 460.827 460.630 56
VI-PointConv0.676 520.770 540.754 550.783 490.621 600.814 590.552 130.758 550.571 620.557 550.954 340.529 350.268 540.530 760.682 680.675 540.719 660.603 510.888 510.833 420.665 43
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 530.789 410.748 590.763 560.635 580.814 590.407 810.747 590.581 570.573 520.950 480.484 500.271 500.607 530.754 530.649 640.774 370.596 540.883 540.823 480.606 63
SALANet0.670 540.816 350.770 460.768 530.652 500.807 630.451 590.747 590.659 230.545 580.924 920.473 550.149 1000.571 630.811 460.635 730.746 580.623 420.892 480.794 670.570 76
O3DSeg0.668 550.822 330.771 450.496 1040.651 510.833 380.541 180.761 540.555 680.611 360.966 130.489 480.370 50.388 980.580 800.776 130.751 550.570 640.956 60.817 530.646 50
PointConvpermissive0.666 560.781 450.759 510.699 690.644 550.822 490.475 480.779 490.564 650.504 750.953 380.428 760.203 790.586 580.754 530.661 600.753 540.588 600.902 400.813 560.642 51
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointASNLpermissive0.666 560.703 800.781 400.751 600.655 480.830 400.471 500.769 520.474 890.537 610.951 440.475 540.279 430.635 440.698 670.675 540.751 550.553 750.816 870.806 580.703 33
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++permissive0.663 580.746 630.708 730.722 620.638 570.820 520.451 590.566 950.599 480.541 590.950 480.510 420.313 250.648 410.819 440.616 780.682 810.590 580.869 720.810 570.656 46
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
MVF-GNN0.658 590.558 1010.751 570.655 840.690 370.722 930.453 580.867 170.579 580.576 510.893 1040.523 370.293 330.733 290.571 820.692 460.659 880.606 490.875 620.804 600.668 42
DCM-Net0.658 590.778 460.702 760.806 380.619 610.813 620.468 520.693 750.494 820.524 670.941 740.449 680.298 310.510 800.821 430.675 540.727 650.568 670.826 850.803 610.637 53
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN0.656 610.698 820.743 640.650 860.564 780.820 520.505 340.758 550.631 320.479 790.945 620.480 520.226 660.572 620.774 510.690 490.735 610.614 450.853 790.776 820.597 69
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 620.752 600.734 680.664 820.583 730.815 580.399 830.754 570.639 290.535 630.942 720.470 560.309 270.665 370.539 840.650 630.708 710.635 360.857 780.793 690.642 51
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 630.778 460.731 690.699 690.577 740.829 410.446 640.736 630.477 880.523 690.945 620.454 630.269 520.484 880.749 560.618 760.738 590.599 530.827 840.792 720.621 58
PointConv-SFPN0.641 640.776 480.703 750.721 630.557 810.826 440.451 590.672 800.563 660.483 780.943 710.425 790.162 950.644 420.726 580.659 610.709 700.572 630.875 620.786 770.559 82
MVPNetpermissive0.641 640.831 290.715 710.671 790.590 690.781 770.394 850.679 770.642 270.553 560.937 790.462 590.256 580.649 400.406 980.626 740.691 780.666 270.877 600.792 720.608 62
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 660.717 770.701 770.692 720.576 750.801 670.467 540.716 680.563 660.459 850.953 380.429 750.169 920.581 590.854 320.605 790.710 680.550 770.894 470.793 690.575 74
FPConvpermissive0.639 670.785 430.760 500.713 670.603 640.798 690.392 860.534 1000.603 460.524 670.948 540.457 610.250 600.538 740.723 600.598 830.696 760.614 450.872 680.799 620.567 79
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 680.797 390.769 470.641 920.590 690.820 520.461 560.537 990.637 300.536 620.947 560.388 890.206 760.656 380.668 710.647 670.732 630.585 610.868 730.793 690.473 102
PointSPNet0.637 690.734 690.692 840.714 660.576 750.797 700.446 640.743 610.598 490.437 900.942 720.403 850.150 990.626 480.800 490.649 640.697 750.557 730.846 810.777 810.563 80
SConv0.636 700.830 300.697 800.752 590.572 770.780 790.445 660.716 680.529 720.530 640.951 440.446 700.170 910.507 830.666 720.636 720.682 810.541 830.886 520.799 620.594 70
Supervoxel-CNN0.635 710.656 870.711 720.719 640.613 620.757 880.444 690.765 530.534 710.566 530.928 900.478 530.272 480.636 430.531 860.664 580.645 920.508 900.864 750.792 720.611 59
joint point-basedpermissive0.634 720.614 950.778 410.667 810.633 590.825 450.420 770.804 430.467 910.561 540.951 440.494 450.291 350.566 640.458 930.579 890.764 450.559 720.838 820.814 540.598 68
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 730.731 710.688 870.675 760.591 680.784 760.444 690.565 960.610 400.492 760.949 520.456 620.254 590.587 560.706 630.599 820.665 870.612 480.868 730.791 750.579 73
3DSM_DMMF0.631 740.626 920.745 620.801 410.607 630.751 890.506 330.729 660.565 640.491 770.866 1070.434 710.197 830.595 540.630 760.709 390.705 730.560 700.875 620.740 920.491 97
PointNet2-SFPN0.631 740.771 520.692 840.672 770.524 860.837 330.440 710.706 730.538 700.446 870.944 680.421 810.219 710.552 700.751 550.591 850.737 600.543 820.901 420.768 840.557 83
APCF-Net0.631 740.742 660.687 890.672 770.557 810.792 740.408 790.665 810.545 690.508 720.952 420.428 760.186 860.634 450.702 650.620 750.706 720.555 740.873 660.798 640.581 72
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv0.630 770.604 970.741 660.766 550.590 690.747 900.501 360.734 640.503 810.527 650.919 960.454 630.323 220.550 720.420 970.678 530.688 790.544 800.896 450.795 660.627 57
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 780.800 380.625 1000.719 640.545 830.806 640.445 660.597 890.448 960.519 700.938 780.481 510.328 200.489 870.499 910.657 620.759 500.592 570.881 560.797 650.634 54
SegGroup_sempermissive0.627 790.818 340.747 610.701 680.602 650.764 850.385 900.629 860.490 840.508 720.931 890.409 840.201 800.564 650.725 590.618 760.692 770.539 840.873 660.794 670.548 86
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 800.830 300.694 820.757 570.563 790.772 830.448 630.647 840.520 750.509 710.949 520.431 740.191 840.496 850.614 780.647 670.672 850.535 860.876 610.783 780.571 75
dtc_net0.625 800.703 800.751 570.794 440.535 840.848 230.480 470.676 790.528 730.469 820.944 680.454 630.004 1130.464 900.636 750.704 420.758 510.548 790.924 260.787 760.492 96
HPEIN0.618 820.729 720.668 900.647 880.597 670.766 840.414 780.680 760.520 750.525 660.946 590.432 720.215 730.493 860.599 790.638 710.617 970.570 640.897 440.806 580.605 65
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-GCNpermissive0.610 830.858 230.772 430.489 1050.532 850.792 740.404 820.643 850.570 630.507 740.935 820.414 830.046 1100.510 800.702 650.602 810.705 730.549 780.859 770.773 830.534 89
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 840.760 570.667 910.649 870.521 870.793 720.457 570.648 830.528 730.434 920.947 560.401 860.153 980.454 910.721 610.648 660.717 670.536 850.904 370.765 850.485 98
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 850.634 910.743 640.697 710.601 660.781 770.437 730.585 920.493 830.446 870.933 870.394 870.011 1120.654 390.661 740.603 800.733 620.526 870.832 830.761 870.480 99
LAP-D0.594 860.720 750.692 840.637 930.456 970.773 820.391 880.730 650.587 530.445 890.940 760.381 900.288 360.434 940.453 950.591 850.649 900.581 620.777 910.749 910.610 61
DPC0.592 870.720 750.700 780.602 970.480 930.762 870.380 910.713 710.585 560.437 900.940 760.369 920.288 360.434 940.509 900.590 870.639 950.567 680.772 930.755 890.592 71
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 880.766 560.659 950.683 740.470 960.740 920.387 890.620 880.490 840.476 800.922 940.355 950.245 630.511 790.511 890.571 900.643 930.493 940.872 680.762 860.600 67
ROSMRF0.580 890.772 510.707 740.681 750.563 790.764 850.362 930.515 1010.465 920.465 840.936 810.427 780.207 750.438 920.577 810.536 930.675 840.486 950.723 990.779 790.524 92
SD-DETR0.576 900.746 630.609 1040.445 1090.517 880.643 1040.366 920.714 700.456 940.468 830.870 1060.432 720.264 550.558 680.674 690.586 880.688 790.482 960.739 970.733 940.537 88
SQN_0.1%0.569 910.676 840.696 810.657 830.497 890.779 800.424 750.548 970.515 770.376 970.902 1030.422 800.357 80.379 990.456 940.596 840.659 880.544 800.685 1020.665 1050.556 84
TextureNetpermissive0.566 920.672 860.664 920.671 790.494 910.719 940.445 660.678 780.411 1020.396 950.935 820.356 940.225 680.412 960.535 850.565 910.636 960.464 980.794 900.680 1020.568 78
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
DVVNet0.562 930.648 880.700 780.770 520.586 720.687 980.333 970.650 820.514 780.475 810.906 1000.359 930.223 700.340 1010.442 960.422 1040.668 860.501 910.708 1000.779 790.534 89
Pointnet++ & Featurepermissive0.557 940.735 680.661 940.686 730.491 920.744 910.392 860.539 980.451 950.375 980.946 590.376 910.205 770.403 970.356 1010.553 920.643 930.497 920.824 860.756 880.515 93
GMLPs0.538 950.495 1060.693 830.647 880.471 950.793 720.300 1000.477 1020.505 800.358 1000.903 1020.327 980.081 1070.472 890.529 870.448 1020.710 680.509 880.746 950.737 930.554 85
PanopticFusion-label0.529 960.491 1070.688 870.604 960.386 1020.632 1050.225 1100.705 740.434 990.293 1060.815 1080.348 960.241 640.499 840.669 700.507 950.649 900.442 1040.796 890.602 1090.561 81
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_weak0.516 970.676 840.591 1070.609 940.442 980.774 810.335 960.597 890.422 1010.357 1010.932 880.341 970.094 1060.298 1030.528 880.473 1000.676 830.495 930.602 1080.721 970.349 109
Online SegFusion0.515 980.607 960.644 980.579 990.434 990.630 1060.353 940.628 870.440 970.410 930.762 1120.307 1000.167 930.520 770.403 990.516 940.565 1000.447 1020.678 1030.701 990.514 94
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, FTSDF0.501 990.558 1010.608 1050.424 1110.478 940.690 970.246 1060.586 910.468 900.450 860.911 980.394 870.160 960.438 920.212 1080.432 1030.541 1060.475 970.742 960.727 950.477 100
PCNN0.498 1000.559 1000.644 980.560 1010.420 1010.711 960.229 1080.414 1030.436 980.352 1020.941 740.324 990.155 970.238 1080.387 1000.493 960.529 1070.509 880.813 880.751 900.504 95
Weakly-Openseg v30.489 1010.749 620.664 920.646 900.496 900.559 1100.122 1130.577 930.257 1130.364 990.805 1090.198 1110.096 1050.510 800.496 920.361 1080.563 1010.359 1110.777 910.644 1060.532 91
3DMV0.484 1020.484 1080.538 1090.643 910.424 1000.606 1090.310 980.574 940.433 1000.378 960.796 1100.301 1010.214 740.537 750.208 1090.472 1010.507 1100.413 1070.693 1010.602 1090.539 87
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 1030.577 990.611 1030.356 1130.321 1100.715 950.299 1020.376 1070.328 1090.319 1040.944 680.285 1030.164 940.216 1110.229 1060.484 980.545 1050.456 1000.755 940.709 980.475 101
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 1040.679 830.604 1060.578 1000.380 1030.682 990.291 1030.106 1130.483 870.258 1110.920 950.258 1070.025 1110.231 1100.325 1020.480 990.560 1030.463 990.725 980.666 1040.231 113
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 1050.474 1090.623 1010.463 1070.366 1050.651 1020.310 980.389 1060.349 1070.330 1030.937 790.271 1050.126 1020.285 1040.224 1070.350 1100.577 990.445 1030.625 1060.723 960.394 105
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 1060.548 1030.548 1080.597 980.363 1060.628 1070.300 1000.292 1080.374 1040.307 1050.881 1050.268 1060.186 860.238 1080.204 1100.407 1050.506 1110.449 1010.667 1040.620 1080.462 103
SurfaceConvPF0.442 1060.505 1050.622 1020.380 1120.342 1080.654 1010.227 1090.397 1050.367 1050.276 1080.924 920.240 1080.198 820.359 1000.262 1040.366 1060.581 980.435 1050.640 1050.668 1030.398 104
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 1080.437 1110.646 970.474 1060.369 1040.645 1030.353 940.258 1100.282 1110.279 1070.918 970.298 1020.147 1010.283 1050.294 1030.487 970.562 1020.427 1060.619 1070.633 1070.352 108
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1090.525 1040.647 960.522 1020.324 1090.488 1130.077 1140.712 720.353 1060.401 940.636 1140.281 1040.176 890.340 1010.565 830.175 1140.551 1040.398 1080.370 1140.602 1090.361 107
SPLAT Netcopyleft0.393 1100.472 1100.511 1100.606 950.311 1110.656 1000.245 1070.405 1040.328 1090.197 1120.927 910.227 1100.000 1150.001 1150.249 1050.271 1130.510 1080.383 1100.593 1090.699 1000.267 111
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 1110.297 1130.491 1110.432 1100.358 1070.612 1080.274 1040.116 1120.411 1020.265 1090.904 1010.229 1090.079 1080.250 1060.185 1110.320 1110.510 1080.385 1090.548 1100.597 1120.394 105
PointNet++permissive0.339 1120.584 980.478 1120.458 1080.256 1130.360 1140.250 1050.247 1110.278 1120.261 1100.677 1130.183 1120.117 1030.212 1120.145 1130.364 1070.346 1140.232 1140.548 1100.523 1130.252 112
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 1130.353 1120.290 1140.278 1140.166 1140.553 1110.169 1120.286 1090.147 1140.148 1140.908 990.182 1130.064 1090.023 1140.018 1150.354 1090.363 1120.345 1120.546 1120.685 1010.278 110
ScanNetpermissive0.306 1140.203 1140.366 1130.501 1030.311 1110.524 1120.211 1110.002 1150.342 1080.189 1130.786 1110.145 1140.102 1040.245 1070.152 1120.318 1120.348 1130.300 1130.460 1130.437 1140.182 114
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 1150.000 1150.041 1150.172 1150.030 1150.062 1150.001 1150.035 1140.004 1150.051 1150.143 1150.019 1150.003 1140.041 1130.050 1140.003 1150.054 1150.018 1150.005 1150.264 1150.082 115


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




Method Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
OneFormer3Dcopyleft0.896 11.000 11.000 10.913 50.858 40.951 30.786 90.837 140.916 80.908 10.778 40.803 20.750 101.000 10.976 30.926 40.882 40.995 400.849 1
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
UniPerception0.884 21.000 10.979 140.872 150.869 20.892 200.806 60.890 50.835 230.892 30.755 90.811 10.779 70.955 400.951 40.876 190.914 10.997 340.840 2
TST3D0.879 31.000 10.994 40.921 40.807 150.939 80.771 100.887 60.923 60.862 90.722 140.768 70.756 91.000 10.910 220.904 60.836 180.999 330.824 5
Spherical Mask(CtoF)0.875 41.000 10.991 90.873 140.850 50.946 50.691 190.752 290.926 40.889 50.759 70.794 40.820 21.000 10.912 140.900 80.878 81.000 10.769 15
TD3Dpermissive0.875 41.000 10.976 170.877 120.783 220.970 10.889 10.828 150.945 30.803 150.713 160.720 170.709 131.000 10.936 100.934 30.873 111.000 10.791 12
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
SoftGroup++0.874 61.000 10.972 180.947 10.839 80.898 190.556 330.913 20.881 150.756 170.828 20.748 120.821 11.000 10.937 90.937 10.887 31.000 10.821 6
Queryformer0.874 61.000 10.978 160.809 310.876 10.936 100.702 160.716 340.920 70.875 80.766 50.772 60.818 41.000 10.995 20.916 50.892 21.000 10.767 16
Mask3D0.870 81.000 10.985 110.782 390.818 130.938 90.760 110.749 300.923 50.877 70.760 60.785 50.820 21.000 10.912 140.864 300.878 80.983 460.825 4
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
ExtMask3D0.867 91.000 11.000 10.756 460.816 140.940 70.795 70.760 280.862 170.888 60.739 110.763 80.774 81.000 10.929 120.878 180.879 61.000 10.819 8
SoftGrouppermissive0.865 101.000 10.969 190.860 170.860 30.913 150.558 300.899 30.911 90.760 160.828 10.736 140.802 60.981 370.919 130.875 200.877 101.000 10.820 7
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
MAFT0.860 111.000 10.990 100.810 300.829 90.949 40.809 50.688 400.836 220.904 20.751 100.796 30.741 111.000 10.864 320.848 370.837 161.000 10.828 3
SIM3D0.852 121.000 10.842 540.913 50.804 160.922 120.828 20.781 250.909 100.831 110.690 230.755 100.676 191.000 10.997 10.848 380.735 331.000 10.815 9
IPCA-Inst0.851 131.000 10.968 200.884 110.842 70.862 320.693 180.812 200.888 140.677 290.783 30.698 180.807 51.000 10.911 190.865 290.865 131.000 10.757 19
SPFormerpermissive0.851 131.000 10.994 50.806 320.774 240.942 60.637 220.849 120.859 190.889 40.720 150.730 150.665 201.000 10.911 190.868 280.873 121.000 10.796 11
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
Mask3D_evaluation0.843 151.000 10.955 250.847 190.795 180.932 110.750 130.780 260.891 120.818 120.737 120.633 270.703 141.000 10.902 240.870 240.820 190.941 540.805 10
ISBNetpermissive0.835 161.000 10.950 260.731 480.819 110.918 130.790 80.740 310.851 210.831 100.661 250.742 130.650 231.000 10.937 80.814 500.836 171.000 10.765 17
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
SphereSeg0.835 161.000 10.963 230.891 90.794 190.954 20.822 40.710 350.961 20.721 210.693 220.530 400.653 221.000 10.867 310.857 330.859 140.991 430.771 14
GraphCut0.832 181.000 10.922 400.724 500.798 170.902 180.701 170.856 100.859 180.715 220.706 170.748 110.640 341.000 10.934 110.862 310.880 51.000 10.729 22
TopoSeg0.832 181.000 10.981 130.933 20.819 120.826 410.524 390.841 130.811 270.681 280.759 80.687 190.727 120.981 370.911 190.883 140.853 151.000 10.756 20
PBNetpermissive0.825 201.000 10.963 220.837 220.843 60.865 270.822 30.647 430.878 160.733 190.639 320.683 200.650 231.000 10.853 330.870 250.820 201.000 10.744 21
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
SSEC0.820 211.000 10.983 120.924 30.826 100.817 440.415 480.899 40.793 310.673 300.731 130.636 250.653 211.000 10.939 70.804 520.878 71.000 10.780 13
DKNet0.815 221.000 10.930 320.844 200.765 280.915 140.534 370.805 220.805 290.807 140.654 260.763 90.650 231.000 10.794 450.881 150.766 241.000 10.758 18
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
RPGN0.806 231.000 10.992 70.789 340.723 410.891 210.650 210.810 210.832 240.665 320.699 200.658 210.700 151.000 10.881 260.832 420.774 220.997 340.613 42
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
HAISpermissive0.803 241.000 10.994 50.820 260.759 290.855 330.554 340.882 70.827 260.615 380.676 240.638 240.646 321.000 10.912 140.797 550.767 230.994 410.726 23
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
Box2Mask0.803 241.000 10.962 240.874 130.707 450.887 240.686 200.598 480.961 10.715 230.694 210.469 450.700 151.000 10.912 140.902 70.753 290.997 340.637 36
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
Mask-Group0.792 261.000 10.968 210.812 270.766 270.864 280.460 420.815 190.888 130.598 420.651 290.639 230.600 400.918 430.941 50.896 100.721 371.000 10.723 24
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
CSC-Pretrained0.791 271.000 10.996 30.829 250.767 260.889 230.600 250.819 180.770 360.594 430.620 360.541 370.700 151.000 10.941 50.889 120.763 251.000 10.526 52
SSTNetpermissive0.789 281.000 10.840 550.888 100.717 420.835 370.717 150.684 410.627 510.724 200.652 280.727 160.600 401.000 10.912 140.822 450.757 281.000 10.691 30
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
GICN0.788 291.000 10.978 150.867 160.781 230.833 380.527 380.824 160.806 280.549 510.596 390.551 330.700 151.000 10.853 330.935 20.733 341.000 10.651 33
DANCENET0.786 301.000 10.936 290.783 370.737 380.852 350.742 140.647 430.765 380.811 130.624 350.579 300.632 371.000 10.909 230.898 90.696 420.944 500.601 45
DENet0.786 301.000 10.929 330.736 470.750 350.720 570.755 120.934 10.794 300.590 440.561 450.537 380.650 231.000 10.882 250.804 530.789 211.000 10.719 25
DualGroup0.782 321.000 10.927 340.811 280.772 250.853 340.631 240.805 220.773 330.613 390.611 370.610 280.650 230.835 540.881 260.879 170.750 311.000 10.675 31
PointGroup0.778 331.000 10.900 440.798 330.715 430.863 290.493 400.706 360.895 110.569 490.701 180.576 310.639 351.000 10.880 280.851 350.719 380.997 340.709 27
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
PE0.776 341.000 10.900 450.860 170.728 400.869 250.400 490.857 90.774 320.568 500.701 190.602 290.646 320.933 420.843 360.890 110.691 460.997 340.709 26
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
AOIA0.767 351.000 10.937 280.810 290.740 370.906 160.550 350.800 240.706 430.577 480.624 340.544 360.596 450.857 460.879 300.880 160.750 300.992 420.658 32
DD-UNet+Group0.764 361.000 10.897 470.837 210.753 320.830 400.459 440.824 160.699 450.629 360.653 270.438 480.650 231.000 10.880 280.858 320.690 471.000 10.650 34
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
INS-Conv-instance0.762 371.000 10.923 370.765 420.785 210.905 170.600 250.655 420.646 500.683 270.647 300.530 390.650 231.000 10.824 380.830 430.693 450.944 500.644 35
Dyco3Dcopyleft0.761 381.000 10.935 300.893 80.752 340.863 300.600 250.588 490.742 400.641 340.633 330.546 350.550 470.857 460.789 470.853 340.762 260.987 440.699 28
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OccuSeg+instance0.742 391.000 10.923 370.785 350.745 360.867 260.557 310.578 520.729 410.670 310.644 310.488 430.577 461.000 10.794 450.830 430.620 551.000 10.550 48
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
RWSeg0.739 401.000 10.899 460.759 440.753 330.823 420.282 540.691 390.658 480.582 470.594 400.547 340.628 381.000 10.795 440.868 270.728 361.000 10.692 29
3D-MPA0.737 411.000 10.933 310.785 350.794 200.831 390.279 560.588 490.695 460.616 370.559 460.556 320.650 231.000 10.809 420.875 210.696 431.000 10.608 44
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
MTML0.731 421.000 10.992 70.779 410.609 540.746 520.308 530.867 80.601 540.607 400.539 490.519 410.550 471.000 10.824 380.869 260.729 351.000 10.616 40
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
OSIS0.725 431.000 10.885 500.653 560.657 510.801 450.576 290.695 380.828 250.698 250.534 500.457 470.500 540.857 460.831 370.841 400.627 531.000 10.619 39
SSEN0.724 441.000 10.926 350.781 400.661 490.845 360.596 280.529 550.764 390.653 330.489 560.461 460.500 540.859 450.765 480.872 230.761 271.000 10.577 46
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
NeuralBF0.718 451.000 10.945 270.901 70.754 310.817 430.460 420.700 370.772 340.688 260.568 440.000 670.500 540.981 370.606 580.872 220.740 321.000 10.614 41
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
Sparse R-CNN0.714 461.000 10.926 360.694 510.699 470.890 220.636 230.516 560.693 470.743 180.588 410.369 520.601 390.594 600.800 430.886 130.676 480.986 450.546 49
SALoss-ResNet0.695 471.000 10.855 520.579 610.589 560.735 550.484 410.588 490.856 200.634 350.571 430.298 530.500 541.000 10.824 380.818 460.702 410.935 570.545 50
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
PanopticFusion-inst0.693 481.000 10.852 530.655 550.616 530.788 470.334 510.763 270.771 350.457 610.555 470.652 220.518 510.857 460.765 480.732 610.631 510.944 500.577 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)
Occipital-SCS0.688 491.000 10.913 410.730 490.737 390.743 540.442 450.855 110.655 490.546 520.546 480.263 550.508 530.889 440.568 590.771 580.705 400.889 600.625 38
3D-BoNet0.687 501.000 10.887 490.836 230.587 570.643 640.550 350.620 450.724 420.522 560.501 540.243 560.512 521.000 10.751 500.807 510.661 500.909 590.612 43
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
ClickSeg_Instance0.685 511.000 10.818 570.600 590.715 440.795 460.557 310.533 540.591 560.601 410.519 520.429 500.638 360.938 410.706 530.817 480.624 540.944 500.502 54
PCJC0.684 521.000 10.895 480.757 450.659 500.862 310.189 630.739 320.606 530.712 240.581 420.515 420.650 230.857 460.357 640.785 560.631 520.889 600.635 37
SPG_WSIS0.678 531.000 10.880 510.836 230.701 460.727 560.273 580.607 470.706 440.541 540.515 530.174 590.600 400.857 460.716 520.846 390.711 391.000 10.506 53
One_Thing_One_Clickpermissive0.675 541.000 10.823 560.782 380.621 520.766 490.211 600.736 330.560 580.586 450.522 510.636 260.453 580.641 580.853 330.850 360.694 440.997 340.411 59
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
SegGroup_inspermissive0.637 551.000 10.923 390.593 600.561 580.746 530.143 650.504 570.766 370.485 590.442 570.372 510.530 500.714 550.815 410.775 570.673 491.000 10.431 58
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
MASCpermissive0.615 560.711 630.802 580.540 620.757 300.777 480.029 660.577 530.588 570.521 570.600 380.436 490.534 490.697 560.616 570.838 410.526 570.980 470.534 51
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
UNet-backbone0.605 571.000 10.909 420.764 430.603 550.704 580.415 470.301 620.548 590.461 600.394 580.267 540.386 600.857 460.649 560.817 470.504 590.959 480.356 62
3D-SISpermissive0.558 581.000 10.773 590.614 580.503 610.691 600.200 610.412 580.498 620.546 530.311 630.103 630.600 400.857 460.382 610.799 540.445 650.938 560.371 60
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.544 590.500 660.655 650.661 540.663 480.765 500.432 460.214 650.612 520.584 460.499 550.204 580.286 640.429 630.655 550.650 660.539 560.950 490.499 55
Hier3Dcopyleft0.540 601.000 10.727 600.626 570.467 640.693 590.200 610.412 580.480 630.528 550.318 620.077 660.600 400.688 570.382 610.768 590.472 610.941 540.350 63
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
Region-18class0.497 610.250 680.902 430.689 520.540 590.747 510.276 570.610 460.268 670.489 580.348 590.000 670.243 670.220 660.663 540.814 490.459 630.928 580.496 56
Sem_Recon_ins0.484 620.764 620.608 670.470 640.521 600.637 650.311 520.218 640.348 660.365 650.223 640.222 570.258 650.629 590.734 510.596 670.509 580.858 630.444 57
tmp0.474 631.000 10.727 600.433 660.481 630.673 620.022 680.380 600.517 610.436 630.338 610.128 610.343 620.429 630.291 660.728 620.473 600.833 640.300 65
SemRegionNet-20cls0.470 641.000 10.727 600.447 650.481 620.678 610.024 670.380 600.518 600.440 620.339 600.128 610.350 610.429 630.212 670.711 630.465 620.833 640.290 66
ASIS0.422 650.333 670.707 630.676 530.401 650.650 630.350 500.177 660.594 550.376 640.202 650.077 650.404 590.571 610.197 680.674 650.447 640.500 670.260 67
3D-BEVIS0.401 660.667 640.687 640.419 670.137 680.587 660.188 640.235 630.359 650.211 670.093 680.080 640.311 630.571 610.382 610.754 600.300 670.874 620.357 61
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet0.390 670.556 650.636 660.493 630.353 660.539 670.271 590.160 670.450 640.359 660.178 660.146 600.250 660.143 670.347 650.698 640.436 660.667 660.331 64
MaskRCNN 2d->3d Proj0.261 680.903 610.081 680.008 680.233 670.175 680.280 550.106 680.150 680.203 680.175 670.480 440.218 680.143 670.542 600.404 680.153 680.393 680.049 68


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 Fusion for 3D Semantic Segmentation. ECCV 2020
BPNet_2Dcopyleft0.670 20.822 30.795 30.836 20.659 30.481 20.451 130.769 40.656 30.567 40.931 30.395 60.390 50.700 40.534 40.689 100.770 20.574 30.865 90.831 30.675 5
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 30.606 140.794 40.434 160.688 1