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 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 bysort bysort by
BFANet ScanNet200permissive0.360 40.553 60.293 40.193 40.483 90.096 50.266 60.000 10.000 40.000 10.298 120.255 110.661 10.810 50.810 30.194 80.785 50.000 30.000 150.161 60.000 80.494 60.382 20.574 40.258 40.000 80.372 80.000 10.000 30.043 110.436 70.000 90.000 10.239 20.000 20.901 30.105 10.689 50.025 40.128 20.614 20.436 10.493 150.000 10.000 20.526 40.546 110.109 40.651 120.953 40.753 70.101 60.143 110.897 40.000 10.431 10.469 130.000 70.522 50.337 50.661 70.459 20.409 40.666 40.102 110.508 60.757 40.000 70.060 120.970 30.497 10.000 10.376 20.511 40.262 40.688 20.921 10.617 80.321 120.590 50.491 60.556 30.000 40.000 10.481 40.093 10.043 20.284 20.000 50.875 130.135 70.669 50.124 110.394 60.849 120.298 20.000 10.476 150.088 120.042 50.000 40.000 10.254 30.653 90.741 40.215 10.573 50.852 60.266 80.654 10.056 110.835 30.000 60.492 20.000 10.000 60.000 30.612 80.000 20.000 60.000 10.616 50.469 150.460 40.698 110.516 20.000 10.378 70.563 40.476 30.863 50.574 80.330 60.000 100.282 40.000 10.760 40.710 20.233 10.000 90.641 40.814 30.000 10.585 80.053 100.000 60.000 10.629 90.000 20.000 10.678 30.528 100.534 40.129 120.596 20.973 30.264 100.772 20.526 80.139 100.707 40.000 10.000 110.764 120.591 140.848 70.000 10.827 40.338 30.806 110.000 10.568 70.151 60.358 20.659 100.510 4
DITR0.409 20.616 10.351 10.215 30.651 10.238 10.400 20.000 10.340 10.000 10.534 20.476 40.585 20.687 140.853 10.143 110.854 20.000 30.865 30.167 50.000 80.175 150.573 10.617 20.372 10.362 10.591 10.000 10.000 30.330 10.494 20.247 80.000 10.385 10.000 20.878 60.037 140.791 10.053 20.118 30.479 100.429 40.940 30.000 10.000 20.461 80.562 90.093 50.628 130.991 10.762 30.135 30.270 30.917 30.000 10.140 40.597 20.000 70.361 120.375 10.730 20.431 50.459 30.410 130.008 140.656 10.814 10.036 40.554 40.947 60.139 110.000 10.263 30.896 10.191 90.615 40.839 30.757 10.399 60.877 10.504 50.524 60.000 40.000 10.587 30.000 80.022 90.077 80.921 10.928 20.132 80.670 40.759 10.652 10.862 70.091 90.000 10.662 30.072 150.000 110.000 40.000 10.496 10.852 20.752 20.152 30.743 10.953 10.301 30.625 30.053 120.913 10.399 10.452 50.000 10.000 60.000 30.742 20.000 20.000 60.000 10.694 20.643 40.444 60.784 70.000 90.000 10.571 10.614 30.491 20.938 10.559 90.357 50.107 70.404 10.000 10.796 20.688 40.148 60.186 10.629 50.827 20.000 10.558 100.198 40.000 60.000 10.723 20.000 20.000 10.833 10.619 10.609 20.478 40.617 10.959 40.370 30.597 90.737 20.191 50.752 20.000 10.118 10.853 10.925 20.670 120.000 10.831 30.000 150.873 30.000 10.699 10.005 100.360 10.723 30.235 13
PonderV2 ScanNet2000.346 50.552 70.270 80.175 60.497 70.070 120.239 70.000 10.000 40.000 10.232 140.412 70.584 30.842 30.804 50.212 70.540 80.000 30.433 140.106 100.000 80.590 40.290 90.548 50.243 60.000 80.356 100.000 10.000 30.062 90.398 100.441 60.000 10.104 90.000 20.888 40.076 90.682 80.030 30.094 60.491 90.351 110.869 90.000 10.063 10.403 100.700 20.000 100.660 110.881 70.761 40.050 90.186 80.852 110.000 10.007 80.570 70.100 20.565 20.326 60.641 100.431 50.290 120.621 50.259 40.408 90.622 100.125 20.082 100.950 40.179 50.000 10.263 30.424 50.193 80.558 60.880 20.545 110.375 70.727 30.445 90.499 80.000 40.000 10.475 60.002 60.034 50.083 70.000 50.924 30.290 40.636 60.115 120.400 50.874 40.186 70.000 10.611 80.128 30.113 20.000 40.000 10.000 80.584 100.636 90.103 110.385 90.843 70.283 40.603 60.080 70.825 70.000 60.377 100.000 10.000 60.000 30.457 110.000 20.000 60.000 10.574 120.608 80.481 30.792 40.394 40.000 10.357 90.503 100.261 90.817 100.504 120.304 70.472 40.115 80.000 10.750 60.677 60.202 20.000 90.509 70.729 50.000 10.519 110.000 130.000 60.000 10.620 110.000 20.000 10.660 60.560 60.486 50.384 70.346 70.952 50.247 120.667 40.436 100.269 30.691 60.000 10.010 60.787 80.889 30.880 40.000 10.810 80.336 40.860 70.000 10.606 60.009 80.248 90.681 70.392 9
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.
L3DETR-ScanNet_2000.336 80.533 110.279 50.155 80.508 50.073 100.101 150.000 10.058 30.000 10.294 130.233 140.548 40.927 10.788 80.264 30.463 90.000 30.638 100.098 130.014 60.411 90.226 110.525 110.225 80.010 50.397 50.000 10.000 30.192 50.380 120.598 40.000 10.117 50.000 20.883 50.082 70.689 50.000 70.032 150.549 50.417 50.910 50.000 10.000 20.448 90.613 80.000 100.697 70.960 20.759 50.158 20.293 20.883 70.000 10.312 30.583 30.079 40.422 100.068 150.660 80.418 70.298 100.430 110.114 90.526 40.776 30.051 30.679 10.946 70.152 70.000 10.183 60.000 130.211 60.511 100.409 140.565 100.355 80.448 70.512 40.557 20.000 40.000 10.420 80.000 80.007 150.104 50.000 50.125 150.330 30.514 120.146 100.321 110.860 80.174 80.000 10.629 60.075 130.000 110.000 40.000 10.002 70.671 70.712 50.141 60.339 100.856 50.261 100.529 100.067 90.835 30.000 60.369 120.000 10.259 20.000 30.629 50.000 20.487 10.000 10.579 110.646 30.107 150.720 100.122 60.000 10.333 110.505 90.303 80.908 30.503 130.565 20.074 80.324 20.000 10.740 80.661 80.109 110.000 90.427 110.563 150.000 10.579 90.108 70.000 60.000 10.664 50.000 20.000 10.641 70.539 80.416 70.515 20.256 80.940 100.312 60.209 150.620 30.138 120.636 110.000 10.000 110.775 110.861 50.765 100.000 10.801 100.119 120.860 70.000 10.687 20.001 120.192 140.679 90.699 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
LGroundpermissive0.272 130.485 130.184 130.106 130.476 100.077 90.218 80.000 10.000 40.000 10.547 10.295 100.540 50.746 100.745 130.058 140.112 140.005 10.658 90.077 150.000 80.322 110.178 140.512 120.190 100.199 20.277 130.000 10.000 30.173 60.399 90.000 90.000 10.039 140.000 20.858 130.085 60.676 100.002 50.103 50.498 80.323 120.703 110.000 10.000 20.296 130.549 100.216 10.702 60.768 120.718 120.028 110.092 140.786 140.000 10.000 100.453 140.022 50.251 150.252 100.572 130.348 130.321 90.514 60.063 120.279 140.552 130.000 70.019 140.932 130.132 140.000 10.000 110.000 130.156 150.457 130.623 100.518 120.265 140.358 100.381 130.395 130.000 40.000 10.127 150.012 50.051 10.000 100.000 50.886 110.014 120.437 150.179 50.244 130.826 130.000 100.000 10.599 100.136 10.085 30.000 40.000 10.000 80.565 110.612 120.143 50.207 130.566 130.232 130.446 130.127 20.708 130.000 60.384 90.000 10.000 60.000 30.402 120.000 20.059 30.000 10.525 150.566 100.229 110.659 130.000 90.000 10.265 120.446 120.147 140.720 140.597 70.066 110.000 100.187 60.000 10.726 110.467 150.134 100.000 90.413 130.629 110.000 10.363 140.055 90.022 30.000 10.626 100.000 20.000 10.323 130.479 150.154 140.117 130.028 140.901 130.243 130.415 140.295 150.143 70.610 140.000 10.000 110.777 100.397 150.324 140.000 10.778 130.179 80.702 140.000 10.274 150.404 10.233 100.622 130.398 8
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
ALS-MinkowskiNetcopyleft0.414 10.610 20.322 30.271 10.542 20.153 20.159 110.000 10.000 40.000 10.404 40.503 30.532 60.672 150.804 50.285 20.888 10.000 30.900 10.226 10.087 20.598 30.342 40.671 10.217 90.087 30.449 30.000 10.000 30.253 20.477 51.000 10.000 10.118 40.000 20.905 10.071 110.710 20.076 10.047 140.665 10.376 80.981 10.000 10.000 20.466 70.632 60.113 30.769 10.956 30.795 10.031 100.314 10.936 10.000 10.390 20.601 10.000 70.458 70.366 20.719 30.440 40.564 10.699 30.314 20.464 70.784 20.200 10.283 60.973 10.142 90.000 10.250 50.285 60.220 50.718 10.752 50.723 20.460 10.248 140.475 70.463 120.000 40.000 10.446 70.021 40.025 70.285 10.000 50.972 10.149 60.769 10.230 20.535 20.879 20.252 40.000 10.693 10.129 20.000 110.000 40.000 10.447 20.958 10.662 80.159 20.598 30.780 120.344 20.646 20.106 40.893 20.135 20.455 40.000 10.194 30.259 10.726 30.475 10.000 60.000 10.741 10.865 10.571 20.817 30.445 30.000 10.506 20.630 20.230 100.916 20.728 10.635 11.000 10.252 50.000 10.804 10.697 30.137 90.043 60.717 20.807 40.000 10.510 120.245 10.000 60.000 10.709 30.000 20.000 10.703 20.572 30.646 10.223 110.531 30.984 10.397 20.813 10.798 10.135 130.800 10.000 10.097 20.832 30.752 80.842 80.000 10.852 10.149 90.846 90.000 10.666 50.359 20.252 80.777 10.690 2
OA-CNN-L_ScanNet2000.333 90.558 40.269 90.124 110.448 130.080 80.272 50.000 10.000 40.000 10.342 70.515 20.524 70.713 130.789 70.158 100.384 100.000 30.806 60.125 70.000 80.496 50.332 60.498 140.227 70.024 40.474 20.000 10.003 20.071 80.487 30.000 90.000 10.110 70.000 20.876 70.013 150.703 30.000 70.076 90.473 110.355 100.906 60.000 10.000 20.476 50.706 10.000 100.672 100.835 110.748 90.015 140.223 70.860 90.000 10.000 100.572 60.000 70.509 60.313 70.662 50.398 110.396 50.411 120.276 30.527 30.711 50.000 70.076 110.946 70.166 60.000 10.022 90.160 70.183 110.493 110.699 80.637 60.403 50.330 110.406 110.526 50.024 30.000 10.392 100.000 80.016 140.000 100.196 30.915 60.112 100.557 80.197 40.352 90.877 30.000 100.000 10.592 120.103 100.000 110.067 10.000 10.089 50.735 50.625 100.130 90.568 60.836 80.271 60.534 90.043 130.799 80.001 50.445 60.000 10.000 60.024 20.661 40.000 20.262 20.000 10.591 70.517 130.373 80.788 60.021 80.000 10.455 30.517 80.320 70.823 90.200 150.001 140.150 50.100 90.000 10.736 90.668 70.103 120.052 50.662 30.720 70.000 10.602 60.112 60.002 50.000 10.637 80.000 20.000 10.621 90.569 40.398 90.412 60.234 90.949 60.363 50.492 130.495 90.251 40.665 90.000 10.001 100.805 60.833 60.794 90.000 10.821 50.314 50.843 100.000 10.560 80.245 30.262 60.713 40.370 11
AWCS0.305 120.508 120.225 120.142 90.463 120.063 130.195 90.000 10.000 40.000 10.467 30.551 10.504 80.773 60.764 120.142 120.029 150.000 30.626 110.100 110.000 80.360 100.179 130.507 130.137 130.006 60.300 120.000 10.000 30.172 70.364 130.512 50.000 10.056 120.000 20.865 120.093 40.634 150.000 70.071 110.396 130.296 140.876 80.000 10.000 20.373 120.436 140.063 90.749 20.877 80.721 100.131 40.124 120.804 130.000 10.000 100.515 90.010 60.452 90.252 100.578 120.417 80.179 150.484 80.171 60.337 120.606 120.000 70.115 80.937 120.142 90.000 10.008 100.000 130.157 140.484 120.402 150.501 130.339 90.553 60.529 20.478 100.000 40.000 10.404 90.001 70.022 90.077 80.000 50.894 100.219 50.628 70.093 130.305 120.886 10.233 50.000 10.603 90.112 50.023 70.000 40.000 10.000 80.741 40.664 70.097 120.253 120.782 110.264 90.523 110.154 10.707 140.000 60.411 80.000 10.000 60.000 30.332 140.000 20.000 60.000 10.602 60.595 90.185 120.656 140.159 50.000 10.355 100.424 130.154 130.729 120.516 100.220 90.620 30.084 100.000 10.707 120.651 100.173 30.014 80.381 150.582 130.000 10.619 20.049 110.000 60.000 10.702 40.000 20.000 10.302 140.489 130.317 110.334 80.392 50.922 110.254 110.533 120.394 110.129 150.613 130.000 10.000 110.820 50.649 110.749 110.000 10.782 120.282 60.863 50.000 10.288 140.006 90.220 110.633 120.542 3
CeCo0.340 60.551 80.247 110.181 50.475 110.057 150.142 120.000 10.000 40.000 10.387 50.463 50.499 90.924 20.774 100.213 60.257 110.000 30.546 130.100 110.006 70.615 10.177 150.534 80.246 50.000 80.400 40.000 10.338 10.006 140.484 40.609 30.000 10.083 110.000 20.873 100.089 50.661 120.000 70.048 130.560 30.408 60.892 70.000 10.000 20.586 10.616 70.000 100.692 80.900 50.721 100.162 10.228 60.860 90.000 10.000 100.575 40.083 30.550 30.347 40.624 110.410 100.360 70.740 20.109 100.321 130.660 70.000 70.121 70.939 110.143 80.000 10.400 10.003 110.190 100.564 50.652 90.615 90.421 30.304 120.579 10.547 40.000 40.000 10.296 120.000 80.030 60.096 60.000 50.916 50.037 110.551 90.171 60.376 70.865 60.286 30.000 10.633 50.102 110.027 60.011 30.000 10.000 80.474 120.742 30.133 70.311 110.824 90.242 110.503 120.068 80.828 60.000 60.429 70.000 10.063 50.000 30.781 10.000 20.000 60.000 10.665 30.633 60.450 50.818 20.000 90.000 10.429 40.532 70.226 110.825 80.510 110.377 40.709 20.079 110.000 10.753 50.683 50.102 130.063 40.401 140.620 120.000 10.619 20.000 130.000 60.000 10.595 130.000 20.000 10.345 120.564 50.411 80.603 10.384 60.945 70.266 90.643 60.367 120.304 10.663 100.000 10.010 60.726 130.767 70.898 30.000 10.784 110.435 10.861 60.000 10.447 90.000 130.257 70.656 110.377 10
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
PPT-SpUNet-F.T.0.332 100.556 50.270 70.123 120.519 40.091 60.349 40.000 10.000 40.000 10.339 80.383 90.498 100.833 40.807 40.241 50.584 70.000 30.755 70.124 80.000 80.608 20.330 70.530 100.314 20.000 80.374 70.000 10.000 30.197 40.459 60.000 90.000 10.117 50.000 20.876 70.095 20.682 80.000 70.086 70.518 60.433 20.930 40.000 10.000 20.563 30.542 120.077 70.715 40.858 90.756 60.008 150.171 100.874 80.000 10.039 60.550 80.000 70.545 40.256 90.657 90.453 30.351 80.449 100.213 50.392 100.611 110.000 70.037 130.946 70.138 120.000 10.000 110.063 90.308 20.537 70.796 40.673 40.323 110.392 90.400 120.509 70.000 40.000 10.649 10.000 80.023 80.000 100.000 50.914 70.002 140.506 130.163 80.359 80.872 50.000 100.000 10.623 70.112 50.001 100.000 40.000 10.021 60.753 30.565 140.150 40.579 40.806 100.267 70.616 40.042 140.783 110.000 60.374 110.000 10.000 60.000 30.620 70.000 20.000 60.000 10.572 130.634 50.350 90.792 40.000 90.000 10.376 80.535 60.378 40.855 60.672 30.074 100.000 100.185 70.000 10.727 100.660 90.076 150.000 90.432 100.646 90.000 10.594 70.006 120.000 60.000 10.658 60.000 20.000 10.661 40.549 70.300 120.291 90.045 120.942 90.304 70.600 80.572 70.135 130.695 50.000 10.008 80.793 70.942 10.899 20.000 10.816 60.181 70.897 20.000 10.679 40.223 40.264 50.691 60.345 12
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
PTv3 ScanNet2000.393 30.592 30.330 20.216 20.520 30.109 40.108 140.000 10.337 20.000 10.310 110.394 80.494 110.753 90.848 20.256 40.717 60.000 30.842 40.192 40.065 40.449 70.346 30.546 60.190 100.000 80.384 60.000 10.000 30.218 30.505 10.791 20.000 10.136 30.000 20.903 20.073 100.687 70.000 70.168 10.551 40.387 70.941 20.000 10.000 20.397 110.654 40.000 100.714 50.759 130.752 80.118 50.264 40.926 20.000 10.048 50.575 40.000 70.597 10.366 20.755 10.469 10.474 20.798 10.140 80.617 20.692 60.000 70.592 30.971 20.188 30.000 10.133 80.593 20.349 10.650 30.717 70.699 30.455 20.790 20.523 30.636 10.301 10.000 10.622 20.000 80.017 130.259 30.000 50.921 40.337 20.733 20.210 30.514 30.860 80.407 10.000 10.688 20.109 70.000 110.000 40.000 10.151 40.671 70.782 10.115 100.641 20.903 20.349 10.616 40.088 60.832 50.000 60.480 30.000 10.428 10.000 30.497 90.000 20.000 60.000 10.662 40.690 20.612 10.828 10.575 10.000 10.404 60.644 10.325 60.887 40.728 10.009 130.134 60.026 150.000 10.761 30.731 10.172 40.077 30.528 60.727 60.000 10.603 50.220 30.022 30.000 10.740 10.000 20.000 10.661 40.586 20.566 30.436 50.531 30.978 20.457 10.708 30.583 60.141 80.748 30.000 10.026 40.822 40.871 40.879 50.000 10.851 20.405 20.914 10.000 10.682 30.000 130.281 40.738 20.463 6
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)
GSTran0.339 70.536 100.273 60.169 70.491 80.071 110.365 30.000 10.000 40.000 10.178 150.246 130.458 120.754 80.788 80.316 10.834 40.000 30.872 20.202 30.079 30.318 120.286 100.538 70.156 120.004 70.310 110.000 10.000 30.009 130.397 110.297 70.000 10.093 100.000 20.876 70.060 120.690 40.000 70.086 70.517 70.358 90.667 130.000 10.000 20.473 60.670 30.000 100.731 30.896 60.765 20.061 80.256 50.889 60.000 10.000 100.480 120.000 70.412 110.279 80.690 40.366 120.373 60.466 90.357 10.514 50.648 80.024 50.615 20.949 50.183 40.000 10.162 70.564 30.196 70.535 80.413 130.638 50.410 40.682 40.445 90.470 110.289 20.000 10.358 110.000 80.022 90.161 40.008 40.877 120.495 10.461 140.161 90.348 100.853 110.199 60.000 10.643 40.109 70.014 80.000 40.000 10.000 80.681 60.705 60.079 140.441 80.872 30.282 50.593 70.096 50.786 100.021 30.495 10.000 10.118 40.000 30.487 100.000 20.002 50.000 10.589 80.563 110.144 140.682 120.109 70.000 10.235 140.455 110.368 50.659 150.609 60.000 150.060 90.033 140.000 10.746 70.648 110.084 140.000 90.803 10.832 10.000 10.614 40.000 130.497 10.000 10.597 120.000 20.000 10.621 90.506 110.459 60.252 100.228 110.913 120.369 40.665 50.598 40.139 100.666 80.000 10.097 20.841 20.698 100.857 60.000 10.811 70.129 110.784 120.000 10.386 100.012 70.317 30.696 50.425 7
OctFormer ScanNet200permissive0.326 110.539 90.265 100.131 100.499 60.110 30.522 10.000 10.000 40.000 10.318 100.427 60.455 130.743 110.765 110.175 90.842 30.000 30.828 50.204 20.033 50.429 80.335 50.601 30.312 30.000 80.357 90.000 10.000 30.047 100.423 80.000 90.000 10.105 80.000 20.873 100.079 80.670 110.000 70.117 40.471 120.432 30.829 100.000 10.000 20.584 20.417 150.089 60.684 90.837 100.705 140.021 130.178 90.892 50.000 10.028 70.505 100.000 70.457 80.200 120.662 50.412 90.244 130.496 70.000 150.451 80.626 90.000 70.102 90.943 100.138 120.000 10.000 110.149 80.291 30.534 90.722 60.632 70.331 100.253 130.453 80.487 90.000 40.000 10.479 50.000 80.022 90.000 100.000 50.900 80.128 90.684 30.164 70.413 40.854 100.000 100.000 10.512 140.074 140.003 90.000 40.000 10.000 80.469 130.613 110.132 80.529 70.871 40.227 140.582 80.026 150.787 90.000 60.339 130.000 10.000 60.000 30.626 60.000 20.029 40.000 10.587 90.612 70.411 70.724 90.000 90.000 10.407 50.552 50.513 10.849 70.655 40.408 30.000 100.296 30.000 10.686 130.645 120.145 70.022 70.414 120.633 100.000 10.637 10.224 20.000 60.000 10.650 70.000 20.000 10.622 80.535 90.343 100.483 30.230 100.943 80.289 80.618 70.596 50.140 90.679 70.000 10.022 50.783 90.620 120.906 10.000 10.806 90.137 100.865 40.000 10.378 110.000 130.168 150.680 80.227 14
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CSC-Pretrainpermissive0.249 150.455 150.171 140.079 150.418 140.059 140.186 100.000 10.000 40.000 10.335 90.250 120.316 140.766 70.697 150.142 120.170 120.003 20.553 120.112 90.097 10.201 140.186 120.476 150.081 140.000 80.216 150.000 10.000 30.001 150.314 150.000 90.000 10.055 130.000 20.832 150.094 30.659 130.002 50.076 90.310 150.293 150.664 140.000 10.000 20.175 150.634 50.130 20.552 150.686 150.700 150.076 70.110 130.770 150.000 10.000 100.430 150.000 70.319 130.166 130.542 150.327 140.205 140.332 140.052 130.375 110.444 150.000 70.012 150.930 150.203 20.000 10.000 110.046 100.175 120.413 140.592 110.471 140.299 130.152 150.340 140.247 150.000 40.000 10.225 130.058 30.037 30.000 100.207 20.862 140.014 120.548 100.033 140.233 140.816 140.000 100.000 10.542 130.123 40.121 10.019 20.000 10.000 80.463 140.454 150.045 150.128 150.557 140.235 120.441 140.063 100.484 150.000 60.308 150.000 10.000 60.000 30.318 150.000 20.000 60.000 10.545 140.543 120.164 130.734 80.000 90.000 10.215 150.371 140.198 120.743 110.205 140.062 120.000 100.079 110.000 10.683 140.547 140.142 80.000 90.441 90.579 140.000 10.464 130.098 80.041 20.000 10.590 140.000 20.000 10.373 110.494 120.174 130.105 140.001 150.895 140.222 140.537 110.307 140.180 60.625 120.000 10.000 110.591 150.609 130.398 130.000 10.766 150.014 140.638 150.000 10.377 120.004 110.206 130.609 150.465 5
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
Minkowski 34Dpermissive0.253 140.463 140.154 150.102 140.381 150.084 70.134 130.000 10.000 40.000 10.386 60.141 150.279 150.737 120.703 140.014 150.164 130.000 30.663 80.092 140.000 80.224 130.291 80.531 90.056 150.000 80.242 140.000 10.000 30.013 120.331 140.000 90.000 10.035 150.001 10.858 130.059 130.650 140.000 70.056 120.353 140.299 130.670 120.000 10.000 20.284 140.484 130.071 80.594 140.720 140.710 130.027 120.068 150.813 120.000 10.005 90.492 110.164 10.274 140.111 140.571 140.307 150.293 110.307 150.150 70.163 150.531 140.002 60.545 50.932 130.093 150.000 10.000 110.002 120.159 130.368 150.581 120.440 150.228 150.406 80.282 150.294 140.000 40.000 10.189 140.060 20.036 40.000 100.000 50.897 90.000 150.525 110.025 150.205 150.771 150.000 100.000 10.593 110.108 90.044 40.000 40.000 10.000 80.282 150.589 130.094 130.169 140.466 150.227 140.419 150.125 30.757 120.002 40.334 140.000 10.000 60.000 30.357 130.000 20.000 60.000 10.582 100.513 140.337 100.612 150.000 90.000 10.250 130.352 150.136 150.724 130.655 40.280 80.000 100.046 130.000 10.606 150.559 130.159 50.102 20.445 80.655 80.000 10.310 150.117 50.000 60.000 10.581 150.026 10.000 10.265 150.483 140.084 150.097 150.044 130.865 150.142 150.588 100.351 130.272 20.596 150.000 10.003 90.622 140.720 90.096 150.000 10.771 140.016 130.772 130.000 10.302 130.194 50.214 120.621 140.197 15
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


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




Method Infoavg aphead apcommon aptail apalarm 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 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 Scannet2000.278 10.383 10.263 10.168 10.506 10.068 10.083 50.000 10.000 10.000 10.023 20.149 40.302 10.778 30.647 10.569 10.500 10.031 10.014 20.027 20.173 10.311 10.195 10.351 30.258 10.000 10.082 10.000 10.003 10.037 20.391 11.000 10.000 10.014 20.000 10.572 10.573 10.661 20.000 10.003 10.005 40.082 40.349 10.028 10.000 10.605 10.515 30.509 10.711 11.000 10.665 30.015 20.107 10.402 40.201 10.083 10.304 10.759 10.491 10.378 10.572 10.119 10.277 10.013 50.089 10.283 20.411 20.267 10.006 30.156 20.000 10.116 10.000 10.105 30.556 10.514 10.396 10.275 10.323 10.215 20.380 10.000 10.000 10.356 10.005 20.208 10.325 10.000 10.050 40.400 10.561 10.258 10.179 10.722 10.147 10.000 10.586 10.063 10.015 20.139 10.016 10.028 10.708 10.418 20.016 10.048 30.500 10.489 10.349 10.001 20.475 20.086 10.365 10.000 10.500 10.000 20.323 30.000 10.222 10.000 10.497 10.626 10.044 30.795 10.556 10.008 20.121 40.265 10.667 10.789 10.568 20.579 10.444 10.176 10.004 20.474 10.752 10.233 20.014 20.002 40.570 20.007 10.377 50.000 10.000 20.000 20.337 10.000 10.000 10.384 10.465 10.287 10.085 10.048 20.816 50.467 10.810 10.377 10.415 10.744 10.000 10.004 10.724 10.778 20.590 10.000 10.032 20.441 10.000 10.377 20.391 10.427 10.321 10.192 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
Minkowski 34D Inst.permissive0.130 40.246 40.083 40.043 50.299 40.000 50.278 10.000 10.000 10.000 10.022 30.175 30.122 20.537 40.521 20.400 30.000 20.000 30.000 30.008 30.000 20.048 40.076 30.182 50.000 40.000 10.022 40.000 10.000 20.000 30.141 50.000 20.000 10.000 30.000 10.210 40.063 20.547 50.000 10.000 20.000 50.100 20.026 50.000 20.000 10.241 40.488 40.000 40.564 51.000 10.672 20.000 30.021 40.486 10.000 30.000 30.067 40.000 30.194 50.033 40.415 40.026 40.025 50.271 10.004 40.094 50.142 50.000 20.000 40.111 30.000 10.000 30.000 10.088 40.083 50.278 20.110 40.000 40.082 50.199 50.137 30.000 10.000 10.000 30.000 30.041 40.000 30.000 10.308 20.067 30.280 30.016 40.101 30.373 50.000 30.000 10.319 40.007 40.000 30.000 30.000 20.000 30.028 50.355 50.000 20.101 10.444 20.289 20.114 50.000 30.394 30.000 20.032 50.000 10.000 30.000 20.201 50.000 10.000 20.000 10.384 20.248 40.000 50.529 40.000 30.000 30.133 30.020 50.089 30.720 30.500 40.099 40.000 20.000 50.000 30.238 40.334 50.190 30.000 30.000 50.317 50.000 30.472 10.000 10.000 20.000 20.094 50.000 10.000 10.082 50.236 40.004 50.019 40.000 30.883 20.061 50.262 20.217 40.000 40.557 50.000 10.000 20.460 40.761 40.156 50.000 10.000 30.259 40.000 10.394 10.019 40.084 40.232 40.000 5
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.123 50.223 50.082 50.046 40.308 30.004 30.278 10.000 10.000 10.000 10.000 50.032 50.105 30.537 40.348 50.378 40.000 20.000 30.000 30.000 50.000 20.000 50.037 50.323 40.000 40.000 10.013 50.000 10.000 20.000 30.235 20.000 20.000 10.000 30.000 10.231 30.045 30.564 40.000 10.000 20.006 30.078 50.065 30.000 20.000 10.259 30.516 20.000 40.600 41.000 10.578 50.000 30.000 50.184 50.000 30.000 30.034 50.000 30.211 40.089 30.394 50.018 50.064 40.171 40.001 50.144 30.172 40.000 20.000 40.044 40.000 10.000 30.000 10.064 50.126 40.278 20.093 50.000 40.094 40.214 30.011 50.000 10.000 10.000 30.000 30.022 50.000 30.000 10.275 30.000 40.275 40.000 50.098 40.407 40.000 30.000 10.250 50.007 50.000 30.000 30.000 20.000 30.333 40.376 40.000 20.000 50.042 50.285 30.119 40.000 30.224 50.000 20.184 30.000 10.000 30.000 20.244 40.000 10.000 20.000 10.377 30.378 20.051 20.424 50.000 30.000 30.116 50.030 40.125 20.441 40.444 50.063 50.000 20.042 30.000 30.297 20.483 30.096 50.000 30.028 20.338 40.000 30.444 30.000 10.000 20.000 20.189 40.000 10.000 10.141 40.152 50.017 40.000 50.000 30.838 40.193 30.111 50.105 50.198 30.588 30.000 10.000 20.542 30.343 50.267 30.000 10.000 30.108 50.000 10.333 40.000 50.228 20.202 50.022 4
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
TD3D Scannet200permissive0.211 20.332 20.177 20.103 20.337 20.036 20.222 40.000 10.000 10.000 10.031 10.342 10.093 40.852 10.452 40.559 20.000 20.004 20.000 30.039 10.000 20.309 20.047 40.380 20.028 20.000 10.080 20.000 10.000 20.147 10.192 30.000 20.000 10.083 10.000 10.395 20.039 40.662 10.000 10.000 20.074 10.135 10.296 20.000 20.000 10.231 50.646 10.139 30.633 31.000 10.705 10.048 10.088 20.439 20.184 20.039 20.266 20.551 20.260 30.026 50.463 20.046 30.252 20.249 30.083 20.372 10.411 10.000 20.414 10.323 10.000 10.052 20.000 10.157 10.278 20.278 20.237 20.015 20.321 20.253 10.060 40.000 10.000 10.272 20.008 10.169 20.032 20.000 10.404 10.356 20.283 20.073 30.028 50.617 20.038 20.000 10.494 20.037 20.215 10.083 20.000 20.003 20.486 30.694 10.000 20.040 40.083 40.219 50.209 20.007 10.483 10.000 20.125 40.000 10.150 20.014 10.544 10.000 10.000 20.000 10.260 50.143 50.200 10.610 30.028 20.032 10.145 10.059 20.046 40.740 20.806 10.543 20.000 20.108 20.008 10.222 50.669 20.456 10.074 10.224 10.586 10.006 20.451 20.000 10.002 10.889 10.282 20.000 10.000 10.252 20.413 20.111 20.074 20.240 10.893 10.266 20.144 30.293 20.281 20.604 20.000 10.000 20.379 50.963 10.250 40.000 10.160 10.420 20.000 10.343 30.207 20.079 50.315 20.052 2
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
LGround Inst.permissive0.154 30.275 30.108 30.060 30.295 50.002 40.278 10.000 10.000 10.000 10.006 40.272 20.064 50.815 20.503 30.333 50.000 20.000 30.556 10.001 40.000 20.148 30.078 20.448 10.007 30.000 10.024 30.000 10.000 20.000 30.190 40.000 20.000 10.000 30.000 10.209 50.031 50.573 30.000 10.000 20.041 20.099 30.037 40.000 20.000 10.327 20.364 50.181 20.642 21.000 10.654 40.000 30.023 30.429 30.000 30.000 30.097 30.000 30.278 20.267 20.434 30.048 20.092 30.257 20.030 30.097 40.189 30.000 20.089 20.000 50.000 10.000 30.000 10.115 20.166 30.222 50.222 30.003 30.127 30.213 40.169 20.000 10.000 10.000 30.000 30.044 30.000 30.000 10.000 50.000 40.268 50.222 20.130 20.494 30.000 30.000 10.363 30.015 30.000 30.000 30.000 20.000 30.611 20.400 30.000 20.056 20.278 30.242 40.180 30.000 30.383 40.000 20.209 20.000 10.000 30.000 20.364 20.000 10.000 20.000 10.323 40.302 30.019 40.654 20.000 30.000 30.141 20.045 30.000 50.427 50.514 30.143 30.000 20.028 40.000 30.252 30.402 40.156 40.000 30.028 20.470 30.000 30.444 30.000 10.000 20.000 20.205 30.000 10.000 10.203 30.381 30.026 30.037 30.000 30.881 30.099 40.135 40.239 30.000 40.585 40.000 10.000 20.616 20.778 20.322 20.000 10.000 30.407 30.000 10.333 40.148 30.177 30.242 30.028 3
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-PPT-ALCcopyleft0.798 10.911 100.812 210.854 70.770 120.856 140.555 150.943 10.660 240.735 20.979 10.606 70.492 10.792 40.934 30.841 20.819 50.716 80.947 100.906 10.822 1
PTv3 ScanNet0.794 20.941 30.813 200.851 90.782 60.890 30.597 10.916 50.696 90.713 50.979 10.635 20.384 30.793 30.907 100.821 50.790 330.696 130.967 30.903 20.805 2
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
DITR ScanNet0.793 30.811 390.852 20.889 10.774 90.907 10.592 20.927 30.719 10.718 30.961 170.652 10.348 120.817 10.927 50.795 90.824 20.749 10.948 90.887 70.771 11
PonderV20.785 40.978 10.800 290.833 260.788 40.853 190.545 190.910 80.713 20.705 60.979 10.596 90.390 20.769 150.832 440.821 50.792 320.730 20.975 10.897 50.785 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.
Mix3Dpermissive0.781 50.964 20.855 10.843 180.781 70.858 130.575 70.831 360.685 150.714 40.979 10.594 100.310 290.801 20.892 180.841 20.819 50.723 50.940 150.887 70.725 27
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 60.861 210.818 150.836 230.790 30.875 50.576 60.905 90.704 60.739 10.969 110.611 30.349 110.756 250.958 10.702 480.805 160.708 90.916 350.898 40.801 3
TTT-KD0.773 70.646 940.818 150.809 380.774 90.878 40.581 30.943 10.687 130.704 70.978 50.607 60.336 180.775 110.912 80.838 40.823 30.694 140.967 30.899 30.794 5
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ResLFE_HDS0.772 80.939 40.824 70.854 70.771 110.840 330.564 110.900 110.686 140.677 140.961 170.537 340.348 120.769 150.903 120.785 130.815 80.676 250.939 160.880 130.772 10
PPT-SpUNet-Joint0.766 90.932 50.794 350.829 280.751 250.854 170.540 230.903 100.630 370.672 170.963 150.565 240.357 90.788 50.900 140.737 280.802 170.685 190.950 70.887 70.780 7
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormerpermissive0.766 90.925 70.808 250.849 110.786 50.846 290.566 100.876 180.690 110.674 160.960 190.576 200.226 700.753 270.904 110.777 150.815 80.722 60.923 300.877 160.776 9
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
CU-Hybrid Net0.764 110.924 80.819 130.840 200.757 200.853 190.580 40.848 290.709 40.643 270.958 230.587 150.295 360.753 270.884 220.758 220.815 80.725 40.927 260.867 250.743 18
OccuSeg+Semantic0.764 110.758 600.796 330.839 210.746 280.907 10.562 120.850 280.680 170.672 170.978 50.610 40.335 200.777 90.819 480.847 10.830 10.691 160.972 20.885 100.727 25
O-CNNpermissive0.762 130.924 80.823 80.844 170.770 120.852 210.577 50.847 310.711 30.640 310.958 230.592 110.217 760.762 200.888 190.758 220.813 120.726 30.932 240.868 240.744 17
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
DiffSegNet0.758 140.725 770.789 400.843 180.762 160.856 140.562 120.920 40.657 270.658 210.958 230.589 130.337 170.782 60.879 230.787 110.779 380.678 210.926 280.880 130.799 4
DTC0.757 150.843 270.820 110.847 140.791 20.862 110.511 360.870 200.707 50.652 230.954 380.604 80.279 470.760 210.942 20.734 290.766 470.701 120.884 570.874 220.736 19
OA-CNN-L_ScanNet200.756 160.783 460.826 60.858 50.776 80.837 360.548 180.896 140.649 290.675 150.962 160.586 160.335 200.771 140.802 520.770 180.787 350.691 160.936 190.880 130.761 13
PNE0.755 170.786 440.835 50.834 250.758 180.849 240.570 90.836 350.648 300.668 190.978 50.581 190.367 70.683 380.856 320.804 70.801 210.678 210.961 50.889 60.716 32
P. Hermosilla: Point Neighborhood Embeddings.
ConDaFormer0.755 170.927 60.822 90.836 230.801 10.849 240.516 330.864 250.651 280.680 130.958 230.584 180.282 440.759 230.855 340.728 310.802 170.678 210.880 620.873 230.756 15
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
PointTransformerV20.752 190.742 680.809 240.872 20.758 180.860 120.552 160.891 160.610 440.687 80.960 190.559 280.304 320.766 180.926 60.767 190.797 250.644 360.942 130.876 190.722 29
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net0.752 190.906 130.793 370.802 440.689 430.825 490.556 140.867 210.681 160.602 470.960 190.555 300.365 80.779 80.859 290.747 250.795 290.717 70.917 340.856 330.764 12
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
BPNetcopyleft0.749 210.909 110.818 150.811 360.752 230.839 350.485 500.842 320.673 190.644 260.957 280.528 400.305 310.773 120.859 290.788 100.818 70.693 150.916 350.856 330.723 28
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer0.749 210.793 420.790 380.807 400.750 270.856 140.524 290.881 170.588 560.642 300.977 90.591 120.274 500.781 70.929 40.804 70.796 260.642 370.947 100.885 100.715 33
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
MSP0.748 230.623 970.804 270.859 40.745 290.824 510.501 400.912 70.690 110.685 100.956 290.567 230.320 260.768 170.918 70.720 360.802 170.676 250.921 320.881 120.779 8
StratifiedFormerpermissive0.747 240.901 140.803 280.845 160.757 200.846 290.512 350.825 390.696 90.645 250.956 290.576 200.262 610.744 320.861 280.742 260.770 450.705 100.899 470.860 300.734 20
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
VMNetpermissive0.746 250.870 190.838 30.858 50.729 340.850 230.501 400.874 190.587 570.658 210.956 290.564 250.299 340.765 190.900 140.716 390.812 130.631 420.939 160.858 310.709 34
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 MVFusion0.746 250.771 540.819 130.848 130.702 400.865 100.397 880.899 120.699 70.664 200.948 580.588 140.330 220.746 310.851 380.764 200.796 260.704 110.935 200.866 260.728 23
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
DiffSeg3D20.745 270.725 770.814 190.837 220.751 250.831 430.514 340.896 140.674 180.684 110.960 190.564 250.303 330.773 120.820 470.713 420.798 240.690 180.923 300.875 200.757 14
Retro-FPN0.744 280.842 280.800 290.767 580.740 300.836 380.541 210.914 60.672 200.626 350.958 230.552 310.272 520.777 90.886 210.696 490.801 210.674 280.941 140.858 310.717 30
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-Net0.743 290.620 980.799 320.849 110.730 330.822 530.493 470.897 130.664 210.681 120.955 320.562 270.378 40.760 210.903 120.738 270.801 210.673 290.907 390.877 160.745 16
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet0.742 300.816 360.806 260.807 400.752 230.828 470.575 70.839 340.699 70.637 320.954 380.520 430.320 260.755 260.834 420.760 210.772 420.676 250.915 370.862 280.717 30
SAT0.742 300.860 220.765 520.819 310.769 140.848 260.533 250.829 370.663 220.631 340.955 320.586 160.274 500.753 270.896 160.729 300.760 530.666 310.921 320.855 350.733 21
LargeKernel3D0.739 320.909 110.820 110.806 420.740 300.852 210.545 190.826 380.594 550.643 270.955 320.541 330.263 600.723 360.858 310.775 170.767 460.678 210.933 220.848 400.694 39
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
MinkowskiNetpermissive0.736 330.859 230.818 150.832 270.709 380.840 330.521 310.853 270.660 240.643 270.951 480.544 320.286 420.731 340.893 170.675 580.772 420.683 200.874 690.852 380.727 25
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
RPN0.736 330.776 500.790 380.851 90.754 220.854 170.491 490.866 230.596 540.686 90.955 320.536 350.342 150.624 530.869 250.787 110.802 170.628 430.927 260.875 200.704 36
IPCA0.731 350.890 150.837 40.864 30.726 350.873 60.530 280.824 400.489 900.647 240.978 50.609 50.336 180.624 530.733 610.758 220.776 400.570 680.949 80.877 160.728 23
PointTransformer++0.725 360.727 760.811 230.819 310.765 150.841 320.502 390.814 450.621 400.623 370.955 320.556 290.284 430.620 550.866 260.781 140.757 570.648 340.932 240.862 280.709 34
SparseConvNet0.725 360.647 930.821 100.846 150.721 360.869 70.533 250.754 610.603 500.614 390.955 320.572 220.325 240.710 370.870 240.724 340.823 30.628 430.934 210.865 270.683 42
MatchingNet0.724 380.812 380.812 210.810 370.735 320.834 400.495 460.860 260.572 640.602 470.954 380.512 450.280 460.757 240.845 400.725 330.780 370.606 530.937 180.851 390.700 38
INS-Conv-semantic0.717 390.751 630.759 550.812 350.704 390.868 80.537 240.842 320.609 460.608 430.953 420.534 370.293 370.616 560.864 270.719 380.793 300.640 380.933 220.845 440.663 48
PointMetaBase0.714 400.835 290.785 410.821 290.684 450.846 290.531 270.865 240.614 410.596 510.953 420.500 480.246 660.674 390.888 190.692 500.764 490.624 450.849 840.844 450.675 44
contrastBoundarypermissive0.705 410.769 570.775 460.809 380.687 440.820 560.439 760.812 460.661 230.591 530.945 660.515 440.171 940.633 500.856 320.720 360.796 260.668 300.889 540.847 410.689 40
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 420.774 520.800 290.793 490.760 170.847 280.471 540.802 490.463 970.634 330.968 130.491 510.271 540.726 350.910 90.706 440.815 80.551 800.878 630.833 460.570 80
RFCR0.702 430.889 160.745 660.813 340.672 480.818 600.493 470.815 440.623 380.610 410.947 600.470 600.249 650.594 590.848 390.705 450.779 380.646 350.892 520.823 520.611 63
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 Click0.701 440.825 330.796 330.723 650.716 370.832 420.433 780.816 420.634 350.609 420.969 110.418 860.344 140.559 710.833 430.715 400.808 150.560 740.902 440.847 410.680 43
JSENetpermissive0.699 450.881 180.762 530.821 290.667 490.800 720.522 300.792 520.613 420.607 440.935 860.492 500.205 810.576 640.853 360.691 520.758 550.652 330.872 720.828 490.649 52
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-Click0.693 460.743 670.794 350.655 880.684 450.822 530.497 450.719 710.622 390.617 380.977 90.447 730.339 160.750 300.664 770.703 470.790 330.596 580.946 120.855 350.647 53
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 470.732 720.772 470.786 500.677 470.866 90.517 320.848 290.509 830.626 350.952 460.536 350.225 720.545 770.704 680.689 550.810 140.564 730.903 430.854 370.729 22
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 480.884 170.754 590.795 470.647 560.818 600.422 800.802 490.612 430.604 450.945 660.462 630.189 890.563 700.853 360.726 320.765 480.632 410.904 410.821 550.606 67
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 490.704 830.741 700.754 620.656 510.829 450.501 400.741 660.609 460.548 610.950 520.522 420.371 50.633 500.756 560.715 400.771 440.623 460.861 800.814 580.658 49
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 500.866 200.748 630.819 310.645 580.794 750.450 660.802 490.587 570.604 450.945 660.464 620.201 840.554 730.840 410.723 350.732 670.602 560.907 390.822 540.603 70
KP-FCNN0.684 510.847 260.758 570.784 520.647 560.814 630.473 530.772 550.605 480.594 520.935 860.450 710.181 920.587 600.805 510.690 530.785 360.614 490.882 590.819 560.632 59
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
VACNN++0.684 510.728 750.757 580.776 550.690 410.804 700.464 590.816 420.577 630.587 540.945 660.508 470.276 490.671 400.710 660.663 630.750 610.589 630.881 600.832 480.653 51
DGNet0.684 510.712 820.784 420.782 540.658 500.835 390.499 440.823 410.641 320.597 500.950 520.487 530.281 450.575 650.619 810.647 710.764 490.620 480.871 750.846 430.688 41
PointContrast_LA_SEM0.683 540.757 610.784 420.786 500.639 600.824 510.408 830.775 540.604 490.541 630.934 900.532 380.269 560.552 740.777 540.645 740.793 300.640 380.913 380.824 510.671 45
Superpoint Network0.683 540.851 250.728 740.800 460.653 530.806 680.468 560.804 470.572 640.602 470.946 630.453 700.239 690.519 820.822 450.689 550.762 520.595 600.895 500.827 500.630 60
VI-PointConv0.676 560.770 560.754 590.783 530.621 640.814 630.552 160.758 590.571 660.557 590.954 380.529 390.268 580.530 800.682 720.675 580.719 700.603 550.888 550.833 460.665 47
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 570.789 430.748 630.763 600.635 620.814 630.407 850.747 630.581 610.573 560.950 520.484 540.271 540.607 570.754 570.649 680.774 410.596 580.883 580.823 520.606 67
SALANet0.670 580.816 360.770 500.768 570.652 540.807 670.451 630.747 630.659 260.545 620.924 960.473 590.149 1040.571 670.811 500.635 770.746 620.623 460.892 520.794 710.570 80
O3DSeg0.668 590.822 340.771 490.496 1080.651 550.833 410.541 210.761 580.555 720.611 400.966 140.489 520.370 60.388 1020.580 840.776 160.751 590.570 680.956 60.817 570.646 54
PointASNLpermissive0.666 600.703 840.781 440.751 640.655 520.830 440.471 540.769 560.474 930.537 650.951 480.475 580.279 470.635 480.698 710.675 580.751 590.553 790.816 910.806 620.703 37
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PointConvpermissive0.666 600.781 470.759 550.699 730.644 590.822 530.475 520.779 530.564 690.504 790.953 420.428 800.203 830.586 620.754 570.661 640.753 580.588 640.902 440.813 600.642 55
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++permissive0.663 620.746 650.708 770.722 660.638 610.820 560.451 630.566 990.599 520.541 630.950 520.510 460.313 280.648 450.819 480.616 820.682 850.590 620.869 760.810 610.656 50
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 630.778 480.702 800.806 420.619 650.813 660.468 560.693 790.494 860.524 710.941 780.449 720.298 350.510 840.821 460.675 580.727 690.568 710.826 890.803 650.637 57
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
MVF-GNN0.658 630.558 1050.751 610.655 880.690 410.722 970.453 620.867 210.579 620.576 550.893 1080.523 410.293 370.733 330.571 860.692 500.659 920.606 530.875 660.804 640.668 46
HPGCNN0.656 650.698 860.743 680.650 900.564 820.820 560.505 380.758 590.631 360.479 830.945 660.480 560.226 700.572 660.774 550.690 530.735 650.614 490.853 830.776 860.597 73
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 660.752 620.734 720.664 860.583 770.815 620.399 870.754 610.639 330.535 670.942 760.470 600.309 300.665 410.539 880.650 670.708 750.635 400.857 820.793 730.642 55
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 670.778 480.731 730.699 730.577 780.829 450.446 680.736 670.477 920.523 730.945 660.454 670.269 560.484 920.749 600.618 800.738 630.599 570.827 880.792 760.621 62
PointConv-SFPN0.641 680.776 500.703 790.721 670.557 850.826 480.451 630.672 840.563 700.483 820.943 750.425 830.162 990.644 460.726 620.659 650.709 740.572 670.875 660.786 810.559 86
MVPNetpermissive0.641 680.831 300.715 750.671 830.590 730.781 810.394 890.679 810.642 310.553 600.937 830.462 630.256 620.649 440.406 1020.626 780.691 820.666 310.877 640.792 760.608 66
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 700.717 810.701 810.692 760.576 790.801 710.467 580.716 720.563 700.459 890.953 420.429 790.169 960.581 630.854 350.605 830.710 720.550 810.894 510.793 730.575 78
FPConvpermissive0.639 710.785 450.760 540.713 710.603 680.798 730.392 900.534 1040.603 500.524 710.948 580.457 650.250 640.538 780.723 640.598 870.696 800.614 490.872 720.799 660.567 83
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 720.797 410.769 510.641 960.590 730.820 560.461 600.537 1030.637 340.536 660.947 600.388 930.206 800.656 420.668 750.647 710.732 670.585 650.868 770.793 730.473 106
PointSPNet0.637 730.734 710.692 880.714 700.576 790.797 740.446 680.743 650.598 530.437 940.942 760.403 890.150 1030.626 520.800 530.649 680.697 790.557 770.846 850.777 850.563 84
SConv0.636 740.830 310.697 840.752 630.572 810.780 830.445 700.716 720.529 760.530 680.951 480.446 740.170 950.507 870.666 760.636 760.682 850.541 870.886 560.799 660.594 74
Supervoxel-CNN0.635 750.656 910.711 760.719 680.613 660.757 920.444 730.765 570.534 750.566 570.928 940.478 570.272 520.636 470.531 900.664 620.645 960.508 940.864 790.792 760.611 63
joint point-basedpermissive0.634 760.614 990.778 450.667 850.633 630.825 490.420 810.804 470.467 950.561 580.951 480.494 490.291 390.566 680.458 970.579 930.764 490.559 760.838 860.814 580.598 72
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 770.731 730.688 910.675 800.591 720.784 800.444 730.565 1000.610 440.492 800.949 560.456 660.254 630.587 600.706 670.599 860.665 910.612 520.868 770.791 790.579 77
3DSM_DMMF0.631 780.626 960.745 660.801 450.607 670.751 930.506 370.729 700.565 680.491 810.866 1110.434 750.197 870.595 580.630 800.709 430.705 770.560 740.875 660.740 960.491 101
PointNet2-SFPN0.631 780.771 540.692 880.672 810.524 900.837 360.440 750.706 770.538 740.446 910.944 720.421 850.219 750.552 740.751 590.591 890.737 640.543 860.901 460.768 880.557 87
APCF-Net0.631 780.742 680.687 930.672 810.557 850.792 780.408 830.665 850.545 730.508 760.952 460.428 800.186 900.634 490.702 690.620 790.706 760.555 780.873 700.798 680.581 76
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv0.630 810.604 1010.741 700.766 590.590 730.747 940.501 400.734 680.503 850.527 690.919 1000.454 670.323 250.550 760.420 1010.678 570.688 830.544 840.896 490.795 700.627 61
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 820.800 400.625 1040.719 680.545 870.806 680.445 700.597 930.448 1000.519 740.938 820.481 550.328 230.489 910.499 950.657 660.759 540.592 610.881 600.797 690.634 58
SegGroup_sempermissive0.627 830.818 350.747 650.701 720.602 690.764 890.385 940.629 900.490 880.508 760.931 930.409 880.201 840.564 690.725 630.618 800.692 810.539 880.873 700.794 710.548 90
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 840.830 310.694 860.757 610.563 830.772 870.448 670.647 880.520 790.509 750.949 560.431 780.191 880.496 890.614 820.647 710.672 890.535 900.876 650.783 820.571 79
dtc_net0.625 840.703 840.751 610.794 480.535 880.848 260.480 510.676 830.528 770.469 860.944 720.454 670.004 1170.464 940.636 790.704 460.758 550.548 830.924 290.787 800.492 100
HPEIN0.618 860.729 740.668 940.647 920.597 710.766 880.414 820.680 800.520 790.525 700.946 630.432 760.215 770.493 900.599 830.638 750.617 1010.570 680.897 480.806 620.605 69
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-GCNpermissive0.610 870.858 240.772 470.489 1090.532 890.792 780.404 860.643 890.570 670.507 780.935 860.414 870.046 1140.510 840.702 690.602 850.705 770.549 820.859 810.773 870.534 93
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 880.760 590.667 950.649 910.521 910.793 760.457 610.648 870.528 770.434 960.947 600.401 900.153 1020.454 950.721 650.648 700.717 710.536 890.904 410.765 890.485 102
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 890.634 950.743 680.697 750.601 700.781 810.437 770.585 960.493 870.446 910.933 910.394 910.011 1160.654 430.661 780.603 840.733 660.526 910.832 870.761 910.480 103
LAP-D0.594 900.720 790.692 880.637 970.456 1010.773 860.391 920.730 690.587 570.445 930.940 800.381 940.288 400.434 980.453 990.591 890.649 940.581 660.777 950.749 950.610 65
DPC0.592 910.720 790.700 820.602 1010.480 970.762 910.380 950.713 750.585 600.437 940.940 800.369 960.288 400.434 980.509 940.590 910.639 990.567 720.772 970.755 930.592 75
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 920.766 580.659 990.683 780.470 1000.740 960.387 930.620 920.490 880.476 840.922 980.355 990.245 670.511 830.511 930.571 940.643 970.493 980.872 720.762 900.600 71
ROSMRF0.580 930.772 530.707 780.681 790.563 830.764 890.362 970.515 1050.465 960.465 880.936 850.427 820.207 790.438 960.577 850.536 970.675 880.486 990.723 1030.779 830.524 96
SD-DETR0.576 940.746 650.609 1080.445 1130.517 920.643 1080.366 960.714 740.456 980.468 870.870 1100.432 760.264 590.558 720.674 730.586 920.688 830.482 1000.739 1010.733 980.537 92
SQN_0.1%0.569 950.676 880.696 850.657 870.497 930.779 840.424 790.548 1010.515 810.376 1010.902 1070.422 840.357 90.379 1030.456 980.596 880.659 920.544 840.685 1060.665 1090.556 88
TextureNetpermissive0.566 960.672 900.664 960.671 830.494 950.719 980.445 700.678 820.411 1060.396 990.935 860.356 980.225 720.412 1000.535 890.565 950.636 1000.464 1020.794 940.680 1060.568 82
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
DVVNet0.562 970.648 920.700 820.770 560.586 760.687 1020.333 1010.650 860.514 820.475 850.906 1040.359 970.223 740.340 1050.442 1000.422 1080.668 900.501 950.708 1040.779 830.534 93
Pointnet++ & Featurepermissive0.557 980.735 700.661 980.686 770.491 960.744 950.392 900.539 1020.451 990.375 1020.946 630.376 950.205 810.403 1010.356 1050.553 960.643 970.497 960.824 900.756 920.515 97
GMLPs0.538 990.495 1100.693 870.647 920.471 990.793 760.300 1040.477 1060.505 840.358 1040.903 1060.327 1020.081 1110.472 930.529 910.448 1060.710 720.509 920.746 990.737 970.554 89
PanopticFusion-label0.529 1000.491 1110.688 910.604 1000.386 1060.632 1090.225 1140.705 780.434 1030.293 1100.815 1120.348 1000.241 680.499 880.669 740.507 990.649 940.442 1080.796 930.602 1130.561 85
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 1010.676 880.591 1110.609 980.442 1020.774 850.335 1000.597 930.422 1050.357 1050.932 920.341 1010.094 1100.298 1070.528 920.473 1040.676 870.495 970.602 1120.721 1010.349 113
Online SegFusion0.515 1020.607 1000.644 1020.579 1030.434 1030.630 1100.353 980.628 910.440 1010.410 970.762 1160.307 1040.167 970.520 810.403 1030.516 980.565 1040.447 1060.678 1070.701 1030.514 98
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 1030.558 1050.608 1090.424 1150.478 980.690 1010.246 1100.586 950.468 940.450 900.911 1020.394 910.160 1000.438 960.212 1120.432 1070.541 1100.475 1010.742 1000.727 990.477 104
PCNN0.498 1040.559 1040.644 1020.560 1050.420 1050.711 1000.229 1120.414 1070.436 1020.352 1060.941 780.324 1030.155 1010.238 1120.387 1040.493 1000.529 1110.509 920.813 920.751 940.504 99
Weakly-Openseg v30.489 1050.749 640.664 960.646 940.496 940.559 1140.122 1170.577 970.257 1170.364 1030.805 1130.198 1150.096 1090.510 840.496 960.361 1120.563 1050.359 1150.777 950.644 1100.532 95
3DMV0.484 1060.484 1120.538 1130.643 950.424 1040.606 1130.310 1020.574 980.433 1040.378 1000.796 1140.301 1050.214 780.537 790.208 1130.472 1050.507 1140.413 1110.693 1050.602 1130.539 91
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 1070.577 1030.611 1070.356 1170.321 1140.715 990.299 1060.376 1110.328 1130.319 1080.944 720.285 1070.164 980.216 1150.229 1100.484 1020.545 1090.456 1040.755 980.709 1020.475 105
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 1080.679 870.604 1100.578 1040.380 1070.682 1030.291 1070.106 1170.483 910.258 1150.920 990.258 1110.025 1150.231 1140.325 1060.480 1030.560 1070.463 1030.725 1020.666 1080.231 117
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 1090.474 1130.623 1050.463 1110.366 1090.651 1060.310 1020.389 1100.349 1110.330 1070.937 830.271 1090.126 1060.285 1080.224 1110.350 1140.577 1030.445 1070.625 1100.723 1000.394 109
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 1100.548 1070.548 1120.597 1020.363 1100.628 1110.300 1040.292 1120.374 1080.307 1090.881 1090.268 1100.186 900.238 1120.204 1140.407 1090.506 1150.449 1050.667 1080.620 1120.462 107
SurfaceConvPF0.442 1100.505 1090.622 1060.380 1160.342 1120.654 1050.227 1130.397 1090.367 1090.276 1120.924 960.240 1120.198 860.359 1040.262 1080.366 1100.581 1020.435 1090.640 1090.668 1070.398 108
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 1120.437 1150.646 1010.474 1100.369 1080.645 1070.353 980.258 1140.282 1150.279 1110.918 1010.298 1060.147 1050.283 1090.294 1070.487 1010.562 1060.427 1100.619 1110.633 1110.352 112
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1130.525 1080.647 1000.522 1060.324 1130.488 1170.077 1180.712 760.353 1100.401 980.636 1180.281 1080.176 930.340 1050.565 870.175 1180.551 1080.398 1120.370 1180.602 1130.361 111
SPLAT Netcopyleft0.393 1140.472 1140.511 1140.606 990.311 1150.656 1040.245 1110.405 1080.328 1130.197 1160.927 950.227 1140.000 1190.001 1190.249 1090.271 1170.510 1120.383 1140.593 1130.699 1040.267 115
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 1150.297 1170.491 1150.432 1140.358 1110.612 1120.274 1080.116 1160.411 1060.265 1130.904 1050.229 1130.079 1120.250 1100.185 1150.320 1150.510 1120.385 1130.548 1140.597 1160.394 109
PointNet++permissive0.339 1160.584 1020.478 1160.458 1120.256 1170.360 1180.250 1090.247 1150.278 1160.261 1140.677 1170.183 1160.117 1070.212 1160.145 1170.364 1110.346 1180.232 1180.548 1140.523 1170.252 116
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 1170.353 1160.290 1180.278 1180.166 1180.553 1150.169 1160.286 1130.147 1180.148 1180.908 1030.182 1170.064 1130.023 1180.018 1190.354 1130.363 1160.345 1160.546 1160.685 1050.278 114
ScanNetpermissive0.306 1180.203 1180.366 1170.501 1070.311 1150.524 1160.211 1150.002 1190.342 1120.189 1170.786 1150.145 1180.102 1080.245 1110.152 1160.318 1160.348 1170.300 1170.460 1170.437 1180.182 118
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 1190.000 1190.041 1190.172 1190.030 1190.062 1190.001 1190.035 1180.004 1190.051 1190.143 1190.019 1190.003 1180.041 1170.050 1180.003 1190.054 1190.018 1190.005 1190.264 1190.082 119


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




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PointRel0.622 10.926 80.710 20.541 80.502 20.772 40.314 40.598 110.425 70.504 70.565 10.650 50.716 20.809 70.476 100.747 40.618 10.963 30.364 18
: Relation3D (PointRel): Enhancing Relation Modeling for Point Cloud Instance Segmentation.
SIM3D0.617 20.952 40.629 140.539 90.426 130.768 80.302 60.681 20.425 80.473 130.511 130.701 10.717 10.821 60.467 130.774 10.559 130.914 150.448 2
Spherical Mask(CtoF)0.616 30.946 50.654 100.555 50.434 100.769 70.271 100.604 80.447 40.505 50.549 20.698 20.716 20.775 140.480 70.747 50.575 90.925 110.436 4
EV3D0.615 40.946 50.652 110.555 50.433 110.773 30.271 110.604 80.447 40.506 40.544 50.698 20.716 20.775 140.480 70.747 50.572 110.925 110.435 5
ExtMask3D0.598 50.852 150.692 60.433 280.461 60.791 10.264 120.488 330.493 10.508 30.528 120.594 100.706 60.791 80.483 50.734 90.595 30.911 170.437 3
MAFT0.596 60.889 130.721 10.448 210.460 70.768 90.251 130.558 210.408 90.504 60.539 70.616 80.618 100.858 30.482 60.684 180.551 150.931 100.450 1
UniPerception0.588 70.963 30.667 80.493 130.472 50.750 120.229 160.528 260.468 30.498 100.542 60.643 60.530 190.661 350.463 140.695 170.599 20.972 10.420 6
MG-Former0.587 80.852 150.639 130.454 200.393 180.758 110.338 20.572 160.480 20.527 20.491 190.671 40.527 200.867 10.485 40.601 280.590 60.938 90.390 10
InsSSM0.586 91.000 10.593 180.440 240.480 30.771 50.345 10.437 370.444 60.495 110.548 40.579 130.621 90.720 260.409 200.712 110.593 40.960 40.395 8
Queryformer0.583 100.926 80.702 40.393 340.504 10.733 180.276 90.527 270.373 150.479 120.534 90.533 200.697 70.720 270.436 180.745 70.592 50.958 50.363 19
Competitor-SPFormer0.580 110.721 310.705 30.593 30.444 90.786 20.286 70.564 190.376 140.498 90.534 100.546 180.390 410.785 100.577 10.708 150.579 80.954 60.388 11
PBNetpermissive0.573 120.926 80.575 230.619 10.472 40.736 160.239 150.487 340.383 130.459 160.506 160.533 190.585 120.767 160.404 210.717 100.559 140.969 20.381 14
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
TST3D0.569 130.778 230.675 70.598 20.451 80.727 190.280 80.476 360.395 100.472 140.457 250.583 110.580 140.777 110.462 160.735 80.547 170.919 140.333 25
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
Mask3D0.566 140.926 80.597 170.408 310.420 150.737 150.239 140.598 110.386 120.458 170.549 20.568 160.716 20.601 410.480 70.646 220.575 90.922 130.364 17
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
OneFormer3Dcopyleft0.566 140.781 220.697 50.562 40.431 120.770 60.331 30.400 430.373 160.529 10.504 170.568 150.475 250.732 240.470 110.762 20.550 160.871 320.379 15
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
ISBNetpermissive0.559 160.939 70.655 90.383 370.426 140.763 100.180 180.534 250.386 110.499 80.509 150.621 70.427 350.704 300.467 120.649 210.571 120.948 70.401 7
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
GraphCut0.552 171.000 10.611 160.438 250.392 190.714 200.139 210.598 130.327 190.389 200.510 140.598 90.427 360.754 190.463 150.761 30.588 70.903 200.329 26
SPFormerpermissive0.549 180.745 260.640 120.484 140.395 170.739 140.311 50.566 180.335 180.468 150.492 180.555 170.478 240.747 210.436 170.712 120.540 180.893 240.343 24
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
DKNet0.532 190.815 190.624 150.517 100.377 210.749 130.107 230.509 300.304 210.437 180.475 200.581 120.539 170.775 130.339 260.640 240.506 210.901 210.385 13
Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu, Zhiguo Cao, Weicai Zhong: 3D Instances as 1D Kernels. ECCV 2022
IPCA-Inst0.520 200.889 130.551 270.548 70.418 160.665 300.064 320.585 140.260 290.277 340.471 220.500 210.644 80.785 90.369 220.591 310.511 190.878 290.362 20
SoftGroup++0.513 210.704 330.578 220.398 330.363 270.704 210.061 330.647 50.297 260.378 230.537 80.343 240.614 110.828 50.295 310.710 140.505 230.875 310.394 9
SSTNetpermissive0.506 220.738 290.549 280.497 120.316 320.693 240.178 190.377 460.198 350.330 250.463 240.576 140.515 210.857 40.494 20.637 250.457 270.943 80.290 35
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SoftGrouppermissive0.504 230.667 400.579 200.372 390.381 200.694 230.072 290.677 30.303 220.387 210.531 110.319 280.582 130.754 180.318 270.643 230.492 240.907 190.388 12
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
DANCENET0.504 230.926 80.579 190.472 160.367 240.626 400.165 200.432 380.221 310.408 190.449 270.411 220.564 150.746 220.421 190.707 160.438 300.846 400.288 36
TD3Dpermissive0.489 250.852 150.511 370.434 260.322 310.735 170.101 260.512 290.355 170.349 240.468 230.283 320.514 220.676 340.268 360.671 190.510 200.908 180.329 27
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
OccuSeg+instance0.486 260.802 210.536 300.428 290.369 230.702 220.205 170.331 510.301 230.379 220.474 210.327 250.437 300.862 20.485 30.601 290.394 380.846 420.273 39
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
TopoSeg0.479 270.704 330.564 240.467 180.366 250.633 380.068 300.554 220.262 280.328 260.447 280.323 260.534 180.722 250.288 330.614 260.482 250.912 160.358 22
DualGroup0.469 280.815 190.552 260.398 320.374 220.683 260.130 220.539 240.310 200.327 270.407 310.276 330.447 290.535 450.342 250.659 200.455 280.900 230.301 31
SSEC0.465 290.667 400.578 210.502 110.362 280.641 370.035 420.605 70.291 270.323 280.451 260.296 300.417 390.677 330.245 400.501 490.506 220.900 220.366 16
HAISpermissive0.457 300.704 330.561 250.457 190.364 260.673 270.046 410.547 230.194 360.308 290.426 290.288 310.454 280.711 280.262 370.563 390.434 320.889 260.344 23
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
DD-UNet+Group0.436 310.630 480.508 400.480 150.310 340.624 420.065 310.638 60.174 370.256 380.384 350.194 450.428 330.759 170.289 320.574 360.400 360.849 390.291 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-instance0.435 320.716 320.495 420.355 410.331 290.689 250.102 250.394 450.208 340.280 320.395 330.250 360.544 160.741 230.309 290.536 450.391 390.842 450.258 43
Mask-Group0.434 330.778 230.516 350.471 170.330 300.658 310.029 440.526 280.249 300.256 370.400 320.309 290.384 440.296 610.368 230.575 350.425 330.877 300.362 21
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
Box2Mask0.433 340.741 270.463 470.433 270.283 370.625 410.103 240.298 560.125 460.260 360.424 300.322 270.472 260.701 310.363 240.711 130.309 550.882 270.272 41
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
RPGN0.428 350.630 480.508 390.367 400.249 440.658 320.016 520.673 40.131 440.234 410.383 360.270 340.434 310.748 200.274 350.609 270.406 350.842 440.267 42
Shichao Dong, Guosheng Lin, Tzu-Yi Hung: Learning Regional Purity for Instance Segmentation on 3D Point Clouds. ECCV 2022
DENet0.413 360.741 270.520 320.237 520.284 360.523 510.097 270.691 10.138 410.209 510.229 530.238 390.390 420.707 290.310 280.448 560.470 260.892 250.310 29
PointGroup0.407 370.639 470.496 410.415 300.243 460.645 360.021 490.570 170.114 470.211 490.359 380.217 430.428 340.660 360.256 380.562 400.341 470.860 350.291 33
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
CSC-Pretrained0.405 380.738 290.465 460.331 450.205 500.655 330.051 370.601 100.092 510.211 500.329 410.198 440.459 270.775 120.195 470.524 470.400 370.878 280.184 52
PE0.396 390.667 400.467 450.446 230.243 450.624 430.022 480.577 150.106 480.219 440.340 390.239 380.487 230.475 520.225 420.541 440.350 450.818 470.273 40
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
Dyco3Dcopyleft0.395 400.642 460.518 340.447 220.259 430.666 290.050 380.251 610.166 380.231 420.362 370.232 400.331 470.535 440.229 410.587 320.438 310.850 370.317 28
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
OSIS0.392 410.778 230.530 310.220 540.278 380.567 480.083 280.330 520.299 240.270 350.310 440.143 510.260 510.624 390.277 340.568 380.361 430.865 340.301 30
AOIA0.387 420.704 330.515 360.385 360.225 490.669 280.005 590.482 350.126 450.181 540.269 500.221 420.426 370.478 510.218 430.592 300.371 410.851 360.242 45
SSEN0.384 430.852 150.494 430.192 550.226 480.648 350.022 470.398 440.299 250.277 330.317 430.231 410.194 580.514 480.196 450.586 330.444 290.843 430.184 51
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
Mask3D_evaluation0.382 440.593 500.520 330.390 350.314 330.600 440.018 510.287 590.151 400.281 310.387 340.169 490.429 320.654 370.172 510.578 340.384 400.670 580.278 38
PCJC0.375 450.704 330.542 290.284 490.197 520.649 340.006 560.426 390.138 420.242 390.304 450.183 480.388 430.629 380.141 580.546 430.344 460.738 530.283 37
ClickSeg_Instance0.366 460.654 440.375 510.184 560.302 350.592 460.050 390.300 550.093 500.283 300.277 470.249 370.426 380.615 400.299 300.504 480.367 420.832 460.191 50
SphereSeg0.357 470.651 450.411 490.345 420.264 420.630 390.059 340.289 580.212 320.240 400.336 400.158 500.305 480.557 420.159 540.455 550.341 480.726 550.294 32
3D-MPA0.355 480.457 600.484 440.299 470.277 390.591 470.047 400.332 490.212 330.217 450.278 460.193 460.413 400.410 550.195 460.574 370.352 440.849 380.213 48
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
NeuralBF0.353 490.593 500.511 380.375 380.264 410.597 450.008 540.332 500.160 390.229 430.274 490.000 720.206 550.678 320.155 550.485 510.422 340.816 480.254 44
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi: NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds. WACV 2023
RWSeg0.348 500.475 570.456 480.320 460.275 400.476 530.020 500.491 320.056 580.212 480.320 420.261 350.302 490.520 460.182 490.557 410.285 570.867 330.197 49
GICN0.341 510.580 520.371 520.344 430.198 510.469 540.052 360.564 200.093 490.212 470.212 550.127 530.347 460.537 430.206 440.525 460.329 500.729 540.241 46
One_Thing_One_Clickpermissive0.326 520.472 580.361 530.232 530.183 530.555 490.000 650.498 310.038 600.195 520.226 540.362 230.168 590.469 530.251 390.553 420.335 490.846 410.117 60
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Occipital-SCS0.320 530.679 390.352 540.334 440.229 470.436 550.025 450.412 420.058 560.161 590.240 520.085 550.262 500.496 500.187 480.467 530.328 510.775 490.231 47
Sparse R-CNN0.292 540.704 330.213 640.153 580.154 550.551 500.053 350.212 620.132 430.174 560.274 480.070 570.363 450.441 540.176 500.424 580.234 590.758 510.161 56
MTML0.282 550.577 530.380 500.182 570.107 610.430 560.001 620.422 400.057 570.179 550.162 580.070 580.229 530.511 490.161 520.491 500.313 520.650 610.162 54
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
SALoss-ResNet0.262 560.667 400.335 550.067 650.123 590.427 570.022 460.280 600.058 550.216 460.211 560.039 610.142 610.519 470.106 620.338 620.310 540.721 560.138 57
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
MASCpermissive0.254 570.463 590.249 630.113 590.167 540.412 590.000 640.374 470.073 520.173 570.243 510.130 520.228 540.368 570.160 530.356 600.208 600.711 570.136 58
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
3D-BoNet0.253 580.519 550.324 580.251 510.137 580.345 640.031 430.419 410.069 530.162 580.131 600.052 590.202 570.338 590.147 570.301 650.303 560.651 600.178 53
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
SPG_WSIS0.251 590.380 620.274 610.289 480.144 560.413 580.000 650.311 530.065 540.113 610.130 610.029 640.204 560.388 560.108 610.459 540.311 530.769 500.127 59
SegGroup_inspermissive0.246 600.556 540.335 560.062 670.115 600.490 520.000 650.297 570.018 640.186 530.142 590.083 560.233 520.216 630.153 560.469 520.251 580.744 520.083 63
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
PanopticFusion-inst0.214 610.250 670.330 570.275 500.103 620.228 700.000 650.345 480.024 620.088 630.203 570.186 470.167 600.367 580.125 590.221 680.112 700.666 590.162 55
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
UNet-backbone0.161 620.519 550.259 620.084 610.059 640.325 660.002 600.093 670.009 660.077 650.064 640.045 600.044 680.161 650.045 640.331 630.180 620.566 620.033 72
3D-SISpermissive0.161 620.407 610.155 690.068 640.043 680.346 630.001 610.134 640.005 670.088 620.106 630.037 620.135 630.321 600.028 680.339 610.116 690.466 650.093 62
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
R-PointNet0.158 640.356 630.173 670.113 600.140 570.359 600.012 530.023 700.039 590.134 600.123 620.008 680.089 640.149 660.117 600.221 670.128 670.563 630.094 61
Region-18class0.146 650.175 710.321 590.080 620.062 630.357 610.000 650.307 540.002 690.066 660.044 660.000 720.018 700.036 710.054 630.447 570.133 650.472 640.060 67
SemRegionNet-20cls0.121 660.296 650.203 650.071 630.058 650.349 620.000 650.150 630.019 630.054 680.034 690.017 670.052 660.042 700.013 710.209 690.183 610.371 660.057 68
Hier3Dcopyleft0.117 670.222 690.161 680.054 690.027 700.289 670.000 650.124 650.001 710.079 640.061 650.027 650.141 620.240 620.005 720.310 640.129 660.153 720.081 64
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
3D-BEVIS0.117 670.250 670.308 600.020 710.009 730.269 690.006 570.008 710.029 610.037 710.014 720.003 700.036 690.147 670.042 660.381 590.118 680.362 670.069 66
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
tmp0.113 690.333 640.151 700.056 680.053 660.344 650.000 650.105 660.016 650.049 690.035 680.020 660.053 650.048 690.013 700.183 710.173 630.344 690.054 69
Sem_Recon_ins0.098 700.295 660.187 660.015 720.036 690.213 710.005 580.038 690.003 680.056 670.037 670.036 630.015 710.051 680.044 650.209 700.098 710.354 680.071 65
ASIS0.085 710.037 720.080 720.066 660.047 670.282 680.000 650.052 680.002 700.047 700.026 700.001 710.046 670.194 640.031 670.264 660.140 640.167 710.047 71
Sgpn_scannet0.049 720.023 730.134 710.031 700.013 720.144 720.006 550.008 720.000 720.028 720.017 710.003 690.009 730.000 720.021 690.122 720.095 720.175 700.054 70
MaskRCNN 2d->3d Proj0.022 730.185 700.000 730.000 730.015 710.000 730.000 630.006 730.000 720.010 730.006 730.107 540.012 720.000 720.002 730.027 730.004 730.022 730.001 73


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 10.337 80.464 120.798 30.632 50.589 30.908 80.420 20.329 120.743 20.594 20.738 20.676 50.527 40.906 20.818 60.715 3
CU-Hybrid-2D Net0.636 30.825 20.820 20.179 230.648 40.463 30.549 20.742 70.676 20.628 20.961 10.420 20.379 60.684 80.381 180.732 30.723 30.599 20.827 160.851 20.634 7
CMX0.613 50.681 80.725 120.502 120.634 60.297 180.478 100.830 20.651 40.537 70.924 40.375 70.315 140.686 70.451 140.714 50.543 210.504 60.894 70.823 50.688 4
DMMF_3d0.605 60.651 90.744 100.782 30.637 50.387 40.536 30.732 80.590 70.540 60.856 210.359 110.306 150.596 140.539 30.627 200.706 40.497 80.785 210.757 190.476 22
EMSANet0.600 70.716 40.746 90.395 180.614 90.382 50.523 40.713 110.571 110.503 100.922 60.404 50.397 40.655 90.400 160.626 210.663 60.469 130.900 40.827 40.577 14
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
MCA-Net0.595 80.533 200.756 80.746 40.590 100.334 100.506 70.670 150.587 80.500 120.905 100.366 100.352 90.601 130.506 80.669 160.648 90.501 70.839 150.769 150.516 21
RFBNet0.592 90.616 110.758 70.659 50.581 110.330 110.469 110.655 180.543 140.524 80.924 40.355 130.336 110.572 170.479 100.671 140.648 90.480 100.814 190.814 70.614 10
FAN_NV_RVC0.586 100.510 210.764 60.079 260.620 80.330 110.494 80.753 50.573 90.556 50.884 160.405 40.303 160.718 30.452 130.672 130.658 70.509 50.898 50.813 80.727 2
DCRedNet0.583 110.682 70.723 130.542 110.510 200.310 150.451 130.668 160.549 130.520 90.920 70.375 70.446 20.528 200.417 150.670 150.577 180.478 110.862 100.806 90.628 9
MIX6D_RVC0.582 120.695 50.687 170.225 210.632 70.328 130.550 10.748 60.623 60.494 150.890 140.350 150.254 230.688 60.454 120.716 40.597 170.489 90.881 80.768 160.575 15
SSMAcopyleft0.577 130.695 50.716 150.439 140.563 140.314 140.444 150.719 90.551 120.503 100.887 150.346 160.348 100.603 120.353 200.709 60.600 150.457 140.901 30.786 110.599 13
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
DMMF0.567 140.623 100.767 50.238 200.571 130.347 60.413 190.719 90.472 200.418 220.895 130.357 120.260 220.696 50.523 70.666 170.642 110.437 180.895 60.793 100.603 12
UNIV_CNP_RVC_UE0.566 150.569 190.686 190.435 150.524 170.294 190.421 180.712 120.543 140.463 170.872 170.320 170.363 80.611 110.477 110.686 110.627 120.443 170.862 100.775 140.639 6
EMSAFormer0.564 160.581 160.736 110.564 100.546 160.219 230.517 50.675 140.486 190.427 210.904 110.352 140.320 130.589 150.528 50.708 70.464 240.413 220.847 140.786 110.611 11
SN_RN152pyrx8_RVCcopyleft0.546 170.572 170.663 210.638 70.518 180.298 170.366 240.633 210.510 170.446 190.864 190.296 200.267 190.542 190.346 210.704 80.575 190.431 190.853 130.766 170.630 8
UDSSEG_RVC0.545 180.610 130.661 220.588 80.556 150.268 210.482 90.642 200.572 100.475 160.836 230.312 180.367 70.630 100.189 230.639 190.495 230.452 150.826 170.756 200.541 17
segfomer with 6d0.542 190.594 150.687 170.146 240.579 120.308 160.515 60.703 130.472 200.498 130.868 180.369 90.282 170.589 150.390 170.701 90.556 200.416 210.860 120.759 180.539 19
FuseNetpermissive0.535 200.570 180.681 200.182 220.512 190.290 200.431 160.659 170.504 180.495 140.903 120.308 190.428 30.523 210.365 190.676 120.621 140.470 120.762 220.779 130.541 17
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
AdapNet++copyleft0.503 210.613 120.722 140.418 170.358 260.337 80.370 230.479 240.443 220.368 240.907 90.207 230.213 250.464 240.525 60.618 220.657 80.450 160.788 200.721 230.408 25
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
3DMV (2d proj)0.498 220.481 240.612 230.579 90.456 220.343 70.384 210.623 220.525 160.381 230.845 220.254 220.264 210.557 180.182 240.581 240.598 160.429 200.760 230.661 250.446 24
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
MSeg1080_RVCpermissive0.485 230.505 220.709 160.092 250.427 230.241 220.411 200.654 190.385 260.457 180.861 200.053 260.279 180.503 220.481 90.645 180.626 130.365 240.748 240.725 220.529 20
John Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
ILC-PSPNet0.475 240.490 230.581 240.289 190.507 210.067 260.379 220.610 230.417 240.435 200.822 250.278 210.267 190.503 220.228 220.616 230.533 220.375 230.820 180.729 210.560 16
Enet (reimpl)0.376 250.264 260.452 260.452 130.365 240.181 240.143 260.456 250.409 250.346 250.769 260.164 240.218 240.359 250.123 260.403 260.381 260.313 260.571 250.685 240.472 23
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
ScanNet (2d proj)permissive0.330 260.293 250.521 250.657 60.361 250.161 250.250 250.004 260.440 230.183 260.836 230.125 250.060 260.319 260.132 250.417 250.412 250.344 250.541 260.427 260.109 26
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17


This table lists the benchmark results for the 2D semantic instance scenario.




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


This table lists the benchmark results for the scene type classification scenario.




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