Presenting the ScanNet200 Benchmark

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

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

ScanNet200 Benchmark

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




Method Infoavg iouhead ioucommon ioutail iouwallchairfloortabledoorcouchcabinetshelfdeskoffice chairbedpillowsinkpicturewindowtoiletbookshelfmonitorcurtainbookarmchaircoffee tableboxrefrigeratorlampkitchen cabinettowelclothestvnightstandcounterdresserstoolcushionplantceilingbathtubend tabledining tablekeyboardbagbackpacktoilet paperprintertv standwhiteboardblanketshower curtaintrash canclosetstairsmicrowavestoveshoecomputer towerbottlebinottomanbenchboardwashing machinemirrorcopierbasketsofa chairfile cabinetfanlaptopshowerpaperpersonpaper towel dispenserovenblindsrackplateblackboardpianosuitcaserailradiatorrecycling bincontainerwardrobesoap dispensertelephonebucketclockstandlightlaundry basketpipeclothes dryerguitartoilet paper holderseatspeakercolumnbicycleladderbathroom stallshower wallcupjacketstorage bincoffee makerdishwasherpaper towel rollmachinematwindowsillbartoasterbulletin boardironing boardfireplacesoap dishkitchen counterdoorframetoilet paper dispensermini fridgefire extinguisherballhatshower curtain rodwater coolerpaper cuttertrayshower doorpillarledgetoaster ovenmousetoilet seat cover dispenserfurniturecartstorage containerscaletissue boxlight switchcratepower outletdecorationsignprojectorcloset doorvacuum cleanercandleplungerstuffed animalheadphonesdish rackbroomguitar caserange hooddustpanhair dryerwater bottlehandicap barpurseventshower floorwater pitchermailboxbowlpaper bagalarm clockmusic standprojector screendividerlaundry detergentbathroom counterobjectbathroom vanitycloset walllaundry hamperbathroom stall doorceiling lighttrash bindumbbellstair railtubebathroom cabinetcd casecloset rodcoffee kettlestructureshower headkeyboard pianocase of water bottlescoat rackstorage organizerfolded chairfire alarmpower stripcalendarposterpotted plantluggagemattress
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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 bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort 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
CSC-Pretrainpermissive0.249 160.455 160.171 150.079 160.766 160.659 140.930 160.494 130.542 160.700 160.314 160.215 160.430 160.121 10.697 160.441 150.683 150.235 130.609 160.895 150.476 150.816 150.770 160.186 130.634 50.216 160.734 80.340 150.471 150.307 150.293 160.591 160.542 140.076 70.205 150.464 130.000 10.484 160.832 160.766 70.052 140.000 70.413 150.059 150.418 150.222 150.318 160.609 140.206 130.112 100.743 120.625 130.076 100.579 150.548 110.590 150.371 150.552 160.081 150.003 20.142 130.201 150.638 160.233 150.686 160.000 40.142 80.444 160.375 120.247 160.198 130.000 10.128 160.454 160.019 20.097 10.000 10.000 60.553 130.557 150.373 120.545 150.164 140.014 140.547 150.174 140.000 30.002 50.000 10.037 40.000 40.063 100.664 140.000 10.000 100.130 20.170 130.152 160.335 100.079 120.110 140.175 130.098 90.175 160.166 140.045 160.207 20.014 130.465 50.000 10.001 160.001 160.046 110.299 140.327 150.537 120.033 150.012 160.186 100.000 10.205 150.377 130.463 150.000 10.058 30.000 110.055 140.041 20.000 90.105 150.000 110.000 70.000 110.000 20.000 30.398 140.000 10.308 160.000 10.000 120.319 140.000 10.543 130.000 10.000 10.062 130.004 110.862 150.000 80.000 80.000 10.000 60.000 10.123 40.316 150.225 140.250 120.094 40.180 60.332 140.441 100.000 120.000 10.310 160.000 20.000 20.000 110.592 120.000 20.000 10.000 10.203 20.000 80.000 40.000 100.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
ALS-MinkowskiNetcopyleft0.414 10.610 20.322 30.271 10.852 10.710 30.973 10.572 30.719 30.795 10.477 50.506 20.601 10.000 110.804 50.646 20.804 10.344 20.777 10.984 10.671 10.879 20.936 10.342 50.632 60.449 30.817 30.475 70.723 20.798 10.376 90.832 30.693 10.031 100.564 10.510 120.000 10.893 20.905 10.672 160.314 20.000 70.718 10.153 20.542 20.397 20.726 30.752 90.252 80.226 10.916 20.800 10.047 150.807 40.769 10.709 30.630 20.769 10.217 90.000 30.285 20.598 30.846 100.535 20.956 30.000 40.137 90.784 20.464 70.463 120.230 110.000 10.598 30.662 80.000 40.087 20.000 10.135 20.900 10.780 130.703 20.741 10.571 20.149 90.697 30.646 10.000 30.076 10.000 10.025 80.000 40.106 40.981 10.000 10.043 60.113 30.888 10.248 150.404 40.252 60.314 10.220 60.245 10.466 70.366 20.159 20.000 50.149 70.690 20.000 10.531 30.253 20.285 70.460 10.440 40.813 10.230 20.283 60.159 110.000 10.728 10.666 50.958 10.000 10.021 40.252 40.118 40.000 60.445 30.223 120.285 10.194 30.390 20.000 20.475 20.842 80.000 10.455 40.000 10.250 50.458 80.000 10.865 10.000 10.000 10.635 10.359 20.972 10.087 30.447 20.000 10.000 60.000 10.129 20.532 70.446 80.503 30.071 120.135 130.699 30.717 20.097 20.000 10.665 10.000 20.000 21.000 10.752 60.000 20.000 10.000 10.142 90.200 10.259 11.000 10.000 1
GSTran0.339 70.536 100.273 60.169 70.811 70.690 50.949 50.506 120.690 40.765 20.397 120.235 150.480 130.014 80.788 90.593 70.746 80.282 50.696 50.913 130.538 70.853 110.889 60.286 110.670 30.310 120.682 130.445 90.638 50.598 40.358 100.841 20.643 40.061 80.373 70.614 40.000 10.786 110.876 80.754 80.357 10.000 70.535 80.071 120.491 90.369 40.487 110.698 110.317 30.202 30.659 160.666 80.086 80.832 10.461 150.597 130.455 120.731 30.156 130.000 30.316 10.318 130.784 130.348 100.896 70.000 40.084 140.648 80.514 50.470 110.368 60.000 10.441 80.705 60.000 40.079 30.000 10.021 30.872 20.872 30.621 90.589 80.144 150.129 110.648 120.459 60.000 30.000 70.000 10.022 100.289 20.096 50.667 130.000 10.000 100.000 100.834 50.682 50.178 160.033 150.256 50.196 80.000 140.473 60.279 80.079 150.008 40.495 10.425 80.000 10.228 120.009 140.564 30.410 40.366 130.665 60.161 100.615 20.365 30.000 10.609 60.386 100.681 70.000 10.000 80.199 70.093 110.497 10.109 70.252 110.161 40.118 50.000 110.000 20.000 30.857 60.000 10.495 10.000 10.162 70.412 120.000 10.563 120.000 10.000 10.000 160.012 70.877 130.004 70.000 80.000 10.002 50.000 10.109 80.458 130.358 120.246 130.060 130.139 100.466 90.803 10.097 20.000 10.517 80.000 20.000 20.060 100.413 140.000 20.000 10.000 10.183 40.024 60.000 40.297 70.000 1
PTv3 ScanNet2000.393 30.592 30.330 20.216 20.851 20.687 80.971 20.586 20.755 10.752 90.505 10.404 70.575 40.000 110.848 20.616 40.761 30.349 10.738 20.978 20.546 60.860 80.926 20.346 40.654 40.384 60.828 10.523 30.699 30.583 60.387 80.822 50.688 20.118 50.474 20.603 50.000 10.832 50.903 20.753 90.140 90.000 70.650 30.109 40.520 40.457 10.497 100.871 40.281 40.192 40.887 40.748 30.168 10.727 70.733 20.740 10.644 10.714 50.190 110.000 30.256 50.449 70.914 10.514 30.759 140.337 20.172 40.692 60.617 20.636 10.325 70.000 10.641 20.782 10.000 40.065 40.000 10.000 60.842 50.903 20.661 40.662 40.612 10.405 20.731 10.566 30.000 30.000 70.000 10.017 140.301 10.088 60.941 20.000 10.077 30.000 100.717 70.790 20.310 120.026 160.264 40.349 10.220 30.397 120.366 20.115 110.000 50.337 20.463 60.000 10.531 30.218 30.593 20.455 20.469 10.708 40.210 40.592 30.108 150.000 10.728 10.682 30.671 80.000 10.000 80.407 10.136 30.022 30.575 10.436 50.259 30.428 10.048 50.000 20.000 30.879 50.000 10.480 30.000 10.133 80.597 10.000 10.690 20.000 10.000 10.009 140.000 140.921 40.000 80.151 40.000 10.000 60.000 10.109 80.494 120.622 20.394 80.073 110.141 80.798 10.528 70.026 50.000 10.551 50.000 20.000 20.134 60.717 80.000 20.000 10.000 10.188 30.000 80.000 40.791 20.000 1
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
IMFSegNet0.337 80.535 110.266 100.169 80.810 80.715 20.947 60.545 80.675 50.759 50.418 90.406 60.493 110.000 110.803 70.571 90.755 50.264 90.644 120.953 50.366 160.840 130.831 120.357 30.564 90.317 110.699 110.422 110.633 70.509 90.424 50.824 40.637 50.001 160.382 60.383 140.000 10.810 80.884 50.678 150.311 30.000 70.469 130.072 110.527 30.300 80.576 90.769 70.177 150.181 50.829 80.642 110.095 60.791 50.655 60.645 80.524 80.692 80.208 100.000 30.264 30.398 100.867 40.343 110.915 50.000 40.036 160.551 140.442 90.432 130.568 10.000 10.359 100.660 90.000 40.040 50.000 10.000 60.853 40.821 100.469 110.546 140.361 90.000 150.683 50.373 100.000 30.000 70.000 10.038 30.000 40.054 120.472 160.000 10.026 70.000 100.868 20.708 40.341 80.263 50.170 110.263 40.109 70.426 100.228 120.143 50.000 50.251 50.442 70.000 10.447 50.187 60.544 40.311 130.396 120.728 30.211 30.066 120.147 120.000 10.505 120.378 110.743 40.000 10.000 80.204 60.118 40.000 60.000 90.297 90.122 50.133 40.004 100.032 10.667 10.839 90.000 10.380 100.000 10.051 90.492 70.000 10.572 100.000 10.000 10.196 100.004 110.910 80.000 80.000 80.000 10.000 60.000 10.112 50.544 50.497 40.152 150.095 20.132 150.277 160.634 50.031 40.000 10.592 30.000 20.000 20.119 70.786 50.000 20.000 10.000 10.126 150.177 20.094 20.274 80.000 1
OctFormer ScanNet200permissive0.326 120.539 90.265 110.131 110.806 100.670 120.943 110.535 100.662 60.705 150.423 80.407 50.505 100.003 90.765 120.582 80.686 140.227 150.680 80.943 90.601 30.854 100.892 50.335 60.417 160.357 90.724 90.453 80.632 80.596 50.432 30.783 100.512 150.021 130.244 140.637 10.000 10.787 100.873 110.743 110.000 160.000 70.534 90.110 30.499 70.289 90.626 60.620 130.168 160.204 20.849 70.679 70.117 40.633 110.684 30.650 70.552 50.684 100.312 30.000 30.175 100.429 80.865 50.413 40.837 110.000 40.145 70.626 90.451 80.487 90.513 20.000 10.529 70.613 120.000 40.033 60.000 10.000 60.828 60.871 40.622 80.587 90.411 70.137 100.645 130.343 110.000 30.000 70.000 10.022 100.000 40.026 160.829 100.000 10.022 80.089 60.842 40.253 140.318 110.296 30.178 90.291 30.224 20.584 20.200 130.132 90.000 50.128 100.227 150.000 10.230 110.047 110.149 90.331 100.412 90.618 80.164 80.102 90.522 10.000 10.655 40.378 110.469 140.000 10.000 80.000 110.105 90.000 60.000 90.483 30.000 110.000 70.028 70.000 20.000 30.906 10.000 10.339 140.000 10.000 120.457 90.000 10.612 70.000 10.000 10.408 30.000 140.900 90.000 80.000 80.000 10.029 40.000 10.074 150.455 140.479 60.427 60.079 90.140 90.496 70.414 130.022 60.000 10.471 130.000 20.000 20.000 110.722 70.000 20.000 10.000 10.138 120.000 80.000 40.000 100.000 1
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
L3DETR-ScanNet_2000.336 90.533 120.279 50.155 90.801 110.689 60.946 80.539 90.660 90.759 50.380 130.333 120.583 30.000 110.788 90.529 110.740 90.261 110.679 90.940 110.525 110.860 80.883 70.226 120.613 80.397 50.720 100.512 40.565 110.620 30.417 60.775 120.629 70.158 20.298 110.579 90.000 10.835 30.883 60.927 10.114 100.079 40.511 100.073 100.508 60.312 60.629 50.861 50.192 140.098 140.908 30.636 120.032 160.563 160.514 130.664 50.505 100.697 70.225 80.000 30.264 30.411 90.860 80.321 120.960 20.058 30.109 110.776 30.526 40.557 20.303 90.000 10.339 110.712 50.000 40.014 70.000 10.000 60.638 110.856 50.641 70.579 110.107 160.119 120.661 90.416 70.000 30.000 70.000 10.007 160.000 40.067 90.910 50.000 10.000 100.000 100.463 100.448 80.294 140.324 20.293 20.211 70.108 80.448 90.068 160.141 70.000 50.330 30.699 10.000 10.256 90.192 50.000 140.355 80.418 70.209 160.146 110.679 10.101 160.000 10.503 140.687 20.671 80.000 10.000 80.174 90.117 60.000 60.122 60.515 20.104 60.259 20.312 30.000 20.000 30.765 110.000 10.369 130.000 10.183 60.422 110.000 10.646 30.000 10.000 10.565 20.001 130.125 160.010 50.002 70.000 10.487 10.000 10.075 140.548 40.420 90.233 140.082 80.138 120.430 110.427 120.000 120.000 10.549 60.000 20.000 20.074 90.409 150.000 20.000 10.000 10.152 70.051 40.000 40.598 40.000 1
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12
CeCo0.340 60.551 80.247 120.181 50.784 120.661 130.939 120.564 50.624 120.721 110.484 40.429 40.575 40.027 60.774 110.503 130.753 60.242 120.656 110.945 80.534 80.865 60.860 90.177 160.616 70.400 40.818 20.579 10.615 100.367 130.408 70.726 140.633 60.162 10.360 80.619 20.000 10.828 60.873 110.924 20.109 110.083 30.564 50.057 160.475 120.266 100.781 10.767 80.257 70.100 120.825 90.663 100.048 140.620 130.551 100.595 140.532 70.692 80.246 50.000 30.213 70.615 10.861 70.376 70.900 60.000 40.102 130.660 70.321 140.547 40.226 120.000 10.311 120.742 30.011 30.006 80.000 10.000 60.546 140.824 90.345 130.665 30.450 50.435 10.683 50.411 80.338 10.000 70.000 10.030 70.000 40.068 80.892 70.000 10.063 40.000 100.257 120.304 130.387 50.079 120.228 60.190 110.000 140.586 10.347 40.133 80.000 50.037 120.377 110.000 10.384 70.006 150.003 120.421 30.410 100.643 70.171 70.121 70.142 130.000 10.510 110.447 90.474 130.000 10.000 80.286 30.083 120.000 60.000 90.603 10.096 70.063 60.000 110.000 20.000 30.898 30.000 10.429 70.000 10.400 10.550 30.000 10.633 60.000 10.000 10.377 40.000 140.916 50.000 80.000 80.000 10.000 60.000 10.102 120.499 100.296 130.463 50.089 60.304 10.740 20.401 150.010 70.000 10.560 40.000 20.000 20.709 20.652 100.000 20.000 10.000 10.143 80.000 80.000 40.609 30.000 1
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023
DITR0.409 20.616 10.351 10.215 30.831 30.791 10.947 60.619 10.730 20.762 30.494 20.571 10.597 20.000 110.853 10.625 30.796 20.301 30.723 30.959 40.617 20.862 70.917 30.573 10.562 100.591 10.784 70.504 50.757 10.737 20.429 40.853 10.662 30.135 30.459 30.558 100.000 10.913 10.878 70.687 140.008 150.000 70.615 40.238 10.651 10.370 30.742 20.925 20.360 10.167 60.938 10.752 20.118 30.827 20.670 40.723 20.614 30.628 140.372 10.000 30.143 120.175 160.873 30.652 10.991 10.340 10.148 60.814 10.656 10.524 60.491 30.000 10.743 10.752 20.000 40.000 90.000 10.399 10.865 30.953 10.833 10.694 20.444 60.000 150.688 40.609 20.000 30.053 20.000 10.022 100.000 40.053 130.940 30.000 10.186 10.093 50.854 30.877 10.534 20.404 10.270 30.191 100.198 40.461 80.375 10.152 30.921 10.132 90.235 140.000 10.617 10.330 10.896 10.399 60.431 50.597 100.759 10.554 40.400 20.000 10.559 90.699 10.852 20.000 10.000 80.091 100.385 10.000 60.000 90.478 40.077 90.000 70.140 40.000 20.000 30.670 130.000 10.452 50.000 10.263 30.361 130.000 10.643 40.000 10.000 10.357 50.005 100.928 20.362 10.496 10.000 10.000 60.000 10.072 160.585 20.587 30.476 40.037 150.191 50.410 130.629 60.118 10.000 10.479 110.000 20.000 20.107 80.839 30.000 20.000 10.000 10.139 110.036 50.000 40.247 90.000 1
BFANet ScanNet200permissive0.360 40.553 60.293 40.193 40.827 40.689 60.970 30.528 110.661 80.753 80.436 70.378 80.469 140.042 50.810 30.654 10.760 40.266 80.659 100.973 30.574 40.849 120.897 40.382 20.546 120.372 80.698 120.491 60.617 90.526 80.436 10.764 130.476 160.101 60.409 40.585 80.000 10.835 30.901 30.810 50.102 120.000 70.688 20.096 50.483 100.264 110.612 80.591 150.358 20.161 70.863 50.707 40.128 20.814 30.669 50.629 100.563 40.651 130.258 40.000 30.194 90.494 60.806 120.394 60.953 40.000 40.233 10.757 40.508 60.556 30.476 40.000 10.573 50.741 40.000 40.000 90.000 10.000 60.000 160.852 60.678 30.616 50.460 40.338 30.710 20.534 40.000 30.025 40.000 10.043 20.000 40.056 110.493 150.000 10.000 100.109 40.785 60.590 60.298 130.282 40.143 120.262 50.053 110.526 40.337 50.215 10.000 50.135 80.510 40.000 10.596 20.043 120.511 50.321 120.459 20.772 20.124 120.060 130.266 60.000 10.574 80.568 70.653 100.000 10.093 10.298 20.239 20.000 60.516 20.129 130.284 20.000 70.431 10.000 20.000 30.848 70.000 10.492 20.000 10.376 20.522 50.000 10.469 160.000 10.000 10.330 60.151 60.875 140.000 80.254 30.000 10.000 60.000 10.088 130.661 10.481 50.255 110.105 10.139 100.666 40.641 40.000 120.000 10.614 20.000 20.000 20.000 110.921 10.000 20.000 10.000 10.497 10.000 80.000 40.000 100.000 1
PonderV2 ScanNet2000.346 50.552 70.270 80.175 60.810 80.682 90.950 40.560 60.641 110.761 40.398 110.357 100.570 70.113 20.804 50.603 60.750 70.283 40.681 70.952 60.548 50.874 40.852 110.290 100.700 20.356 100.792 40.445 90.545 120.436 110.351 120.787 90.611 90.050 90.290 130.519 110.000 10.825 70.888 40.842 30.259 50.100 20.558 60.070 130.497 80.247 130.457 120.889 30.248 90.106 110.817 110.691 60.094 70.729 60.636 70.620 120.503 110.660 120.243 60.000 30.212 80.590 40.860 80.400 50.881 80.000 40.202 20.622 100.408 100.499 80.261 100.000 10.385 90.636 100.000 40.000 90.000 10.000 60.433 150.843 70.660 60.574 120.481 30.336 40.677 70.486 50.000 30.030 30.000 10.034 60.000 40.080 70.869 90.000 10.000 100.000 100.540 90.727 30.232 150.115 90.186 80.193 90.000 140.403 110.326 60.103 120.000 50.290 40.392 100.000 10.346 80.062 100.424 60.375 70.431 50.667 50.115 130.082 100.239 70.000 10.504 130.606 60.584 110.000 10.002 60.186 80.104 100.000 60.394 40.384 70.083 80.000 70.007 80.000 20.000 30.880 40.000 10.377 110.000 10.263 30.565 20.000 10.608 80.000 10.000 10.304 70.009 80.924 30.000 80.000 80.000 10.000 60.000 10.128 30.584 30.475 70.412 70.076 100.269 30.621 50.509 80.010 70.000 10.491 100.063 10.000 20.472 40.880 20.000 20.000 10.000 10.179 50.125 30.000 40.441 60.000 1
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
OA-CNN-L_ScanNet2000.333 100.558 40.269 90.124 120.821 50.703 40.946 80.569 40.662 60.748 100.487 30.455 30.572 60.000 110.789 80.534 100.736 100.271 60.713 40.949 70.498 140.877 30.860 90.332 70.706 10.474 20.788 60.406 120.637 60.495 100.355 110.805 70.592 130.015 140.396 50.602 60.000 10.799 90.876 80.713 130.276 40.000 70.493 110.080 80.448 140.363 50.661 40.833 60.262 60.125 80.823 100.665 90.076 100.720 80.557 90.637 90.517 90.672 110.227 70.000 30.158 110.496 50.843 110.352 90.835 120.000 40.103 120.711 50.527 30.526 50.320 80.000 10.568 60.625 110.067 10.000 90.000 10.001 50.806 70.836 80.621 90.591 70.373 80.314 50.668 80.398 90.003 20.000 70.000 10.016 150.024 30.043 140.906 60.000 10.052 50.000 100.384 110.330 120.342 70.100 100.223 70.183 120.112 60.476 50.313 70.130 100.196 30.112 110.370 120.000 10.234 100.071 90.160 80.403 50.398 110.492 140.197 50.076 110.272 50.000 10.200 160.560 80.735 60.000 10.000 80.000 110.110 80.002 50.021 80.412 60.000 110.000 70.000 110.000 20.000 30.794 100.000 10.445 60.000 10.022 100.509 60.000 10.517 140.000 10.000 10.001 150.245 30.915 60.024 40.089 50.000 10.262 20.000 10.103 110.524 80.392 110.515 20.013 160.251 40.411 120.662 30.001 110.000 10.473 120.000 20.000 20.150 50.699 90.000 20.000 10.000 10.166 60.000 80.024 30.000 100.000 1
PPT-SpUNet-F.T.0.332 110.556 50.270 70.123 130.816 60.682 90.946 80.549 70.657 100.756 70.459 60.376 90.550 80.001 100.807 40.616 40.727 110.267 70.691 60.942 100.530 100.872 50.874 80.330 80.542 130.374 70.792 40.400 130.673 40.572 70.433 20.793 80.623 80.008 150.351 90.594 70.000 10.783 120.876 80.833 40.213 60.000 70.537 70.091 60.519 50.304 70.620 70.942 10.264 50.124 90.855 60.695 50.086 80.646 100.506 140.658 60.535 60.715 40.314 20.000 30.241 60.608 20.897 20.359 80.858 100.000 40.076 150.611 110.392 110.509 70.378 50.000 10.579 40.565 150.000 40.000 90.000 10.000 60.755 80.806 110.661 40.572 130.350 100.181 70.660 100.300 130.000 30.000 70.000 10.023 90.000 40.042 150.930 40.000 10.000 100.077 70.584 80.392 100.339 90.185 80.171 100.308 20.006 130.563 30.256 90.150 40.000 50.002 150.345 130.000 10.045 130.197 40.063 100.323 110.453 30.600 90.163 90.037 140.349 40.000 10.672 30.679 40.753 30.000 10.000 80.000 110.117 60.000 60.000 90.291 100.000 110.000 70.039 60.000 20.000 30.899 20.000 10.374 120.000 10.000 120.545 40.000 10.634 50.000 10.000 10.074 110.223 40.914 70.000 80.021 60.000 10.000 60.000 10.112 50.498 110.649 10.383 90.095 20.135 130.449 100.432 110.008 90.000 10.518 70.000 20.000 20.000 110.796 40.000 20.000 10.000 10.138 120.000 80.000 40.000 100.000 1
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
AWCS0.305 130.508 130.225 130.142 100.782 130.634 160.937 130.489 140.578 130.721 110.364 140.355 110.515 90.023 70.764 130.523 120.707 130.264 90.633 130.922 120.507 130.886 10.804 140.179 140.436 150.300 130.656 150.529 20.501 140.394 120.296 150.820 60.603 100.131 40.179 160.619 20.000 10.707 150.865 130.773 60.171 70.010 60.484 120.063 140.463 130.254 120.332 150.649 120.220 110.100 120.729 130.613 140.071 120.582 140.628 80.702 40.424 140.749 20.137 140.000 30.142 130.360 110.863 60.305 130.877 90.000 40.173 30.606 120.337 130.478 100.154 140.000 10.253 130.664 70.000 40.000 90.000 10.000 60.626 120.782 120.302 150.602 60.185 130.282 60.651 110.317 120.000 30.000 70.000 10.022 100.000 40.154 10.876 80.000 10.014 90.063 90.029 160.553 70.467 30.084 110.124 130.157 150.049 120.373 130.252 100.097 130.000 50.219 60.542 30.000 10.392 60.172 80.000 140.339 90.417 80.533 130.093 140.115 80.195 90.000 10.516 100.288 150.741 50.000 10.001 70.233 50.056 130.000 60.159 50.334 80.077 90.000 70.000 110.000 20.000 30.749 120.000 10.411 80.000 10.008 110.452 100.000 10.595 90.000 10.000 10.220 90.006 90.894 110.006 60.000 80.000 10.000 60.000 10.112 50.504 90.404 100.551 10.093 50.129 160.484 80.381 160.000 120.000 10.396 140.000 20.000 20.620 30.402 160.000 20.000 10.000 10.142 90.000 80.000 40.512 50.000 1
LGroundpermissive0.272 140.485 140.184 140.106 140.778 140.676 110.932 140.479 160.572 140.718 130.399 100.265 130.453 150.085 30.745 140.446 140.726 120.232 140.622 140.901 140.512 120.826 140.786 150.178 150.549 110.277 140.659 140.381 140.518 130.295 160.323 130.777 110.599 110.028 110.321 100.363 150.000 10.708 140.858 140.746 100.063 130.022 50.457 140.077 90.476 110.243 140.402 130.397 160.233 100.077 160.720 150.610 150.103 50.629 120.437 160.626 110.446 130.702 60.190 110.005 10.058 150.322 120.702 150.244 140.768 130.000 40.134 100.552 130.279 150.395 140.147 150.000 10.207 140.612 130.000 40.000 90.000 10.000 60.658 100.566 140.323 140.525 160.229 120.179 80.467 160.154 150.000 30.002 50.000 10.051 10.000 40.127 20.703 110.000 10.000 100.216 10.112 150.358 110.547 10.187 70.092 150.156 160.055 100.296 140.252 100.143 50.000 50.014 130.398 90.000 10.028 150.173 70.000 140.265 150.348 140.415 150.179 60.019 150.218 80.000 10.597 70.274 160.565 120.000 10.012 50.000 110.039 150.022 30.000 90.117 140.000 110.000 70.000 110.000 20.000 30.324 150.000 10.384 90.000 10.000 120.251 160.000 10.566 110.000 10.000 10.066 120.404 10.886 120.199 20.000 80.000 10.059 30.000 10.136 10.540 60.127 160.295 100.085 70.143 70.514 60.413 140.000 120.000 10.498 90.000 20.000 20.000 110.623 110.000 20.000 10.000 10.132 140.000 80.000 40.000 100.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv
Minkowski 34Dpermissive0.253 150.463 150.154 160.102 150.771 150.650 150.932 140.483 150.571 150.710 140.331 150.250 140.492 120.044 40.703 150.419 160.606 160.227 150.621 150.865 160.531 90.771 160.813 130.291 90.484 140.242 150.612 160.282 160.440 160.351 140.299 140.622 150.593 120.027 120.293 120.310 160.000 10.757 130.858 140.737 120.150 80.164 10.368 160.084 70.381 160.142 160.357 140.720 100.214 120.092 150.724 140.596 160.056 130.655 90.525 120.581 160.352 160.594 150.056 160.000 30.014 160.224 140.772 140.205 160.720 150.000 40.159 50.531 150.163 160.294 150.136 160.000 10.169 150.589 140.000 40.000 90.000 10.002 40.663 90.466 160.265 160.582 100.337 110.016 130.559 140.084 160.000 30.000 70.000 10.036 50.000 40.125 30.670 120.000 10.102 20.071 80.164 140.406 90.386 60.046 140.068 160.159 140.117 50.284 150.111 150.094 140.000 50.000 160.197 160.000 10.044 140.013 130.002 130.228 160.307 160.588 110.025 160.545 50.134 140.000 10.655 40.302 140.282 160.000 10.060 20.000 110.035 160.000 60.000 90.097 160.000 110.000 70.005 90.000 20.000 30.096 160.000 10.334 150.000 10.000 120.274 150.000 10.513 150.000 10.000 10.280 80.194 50.897 100.000 80.000 80.000 10.000 60.000 10.108 100.279 160.189 150.141 160.059 140.272 20.307 150.445 90.003 100.000 10.353 150.000 20.026 10.000 110.581 130.001 10.000 10.000 10.093 160.002 70.000 40.000 100.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019


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




Method Infoavg ap 50%head ap 50%common ap 50%tail ap 50%chairtabledoorcouchcabinetshelfdeskoffice chairbedpillowsinkpicturewindowtoiletbookshelfmonitorcurtainbookarmchaircoffee tableboxrefrigeratorlampkitchen cabinettowelclothestvnightstandcounterdresserstoolcushionplantceilingbathtubend tabledining tablekeyboardbagbackpacktoilet paperprintertv standwhiteboardblanketshower curtaintrash canclosetstairsmicrowavestoveshoecomputer towerbottlebinottomanbenchboardwashing machinemirrorcopierbasketsofa chairfile cabinetfanlaptopshowerpaperpersonpaper towel dispenserovenblindsrackplateblackboardpianosuitcaserailradiatorrecycling bincontainerwardrobesoap dispensertelephonebucketclockstandlightlaundry basketpipeclothes dryerguitartoilet paper holderseatspeakercolumnbicycleladderbathroom stallshower wallcupjacketstorage bincoffee makerdishwasherpaper towel rollmachinematwindowsillbartoasterbulletin boardironing boardfireplacesoap dishkitchen counterdoorframetoilet paper dispensermini fridgefire extinguisherballhatshower curtain rodwater coolerpaper cuttertrayshower doorpillarledgetoaster ovenmousetoilet seat cover dispenserfurniturecartstorage containerscaletissue boxlight switchcratepower outletdecorationsignprojectorcloset doorvacuum cleanercandleplungerstuffed animalheadphonesdish rackbroomguitar caserange hooddustpanhair dryerwater bottlehandicap barpurseventshower floorwater pitchermailboxbowlpaper bagalarm clockmusic standprojector screendividerlaundry detergentbathroom counterobjectbathroom vanitycloset walllaundry hamperbathroom stall doorceiling lighttrash bindumbbellstair railtubebathroom cabinetcd casecloset rodcoffee kettlestructureshower headkeyboard pianocase of water bottlescoat rackstorage organizerfolded chairfire alarmpower stripcalendarposterpotted plantluggagemattress
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 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 by
Mask3D Scannet2000.388 10.542 10.357 10.237 10.808 20.676 20.741 10.832 40.496 10.151 30.628 20.021 20.955 10.578 10.753 10.612 10.591 10.822 50.609 30.926 10.614 30.291 10.725 40.163 10.890 20.380 50.615 10.517 10.130 30.806 10.857 20.024 20.511 10.412 50.226 10.597 20.756 11.000 10.111 10.792 10.736 10.091 10.610 10.527 20.323 41.000 10.504 10.063 21.000 10.853 10.010 10.974 30.839 10.667 10.301 10.883 10.266 10.039 10.640 10.311 20.739 20.463 11.000 10.000 10.287 20.715 20.313 20.600 11.000 10.027 10.076 40.502 50.500 10.409 10.000 10.194 10.125 20.500 10.491 10.748 10.050 40.042 20.776 20.352 10.008 10.000 10.033 10.254 10.000 10.005 20.552 10.008 20.020 20.750 10.500 10.409 20.065 30.511 10.107 10.178 20.000 11.000 10.400 10.016 10.000 10.400 10.571 10.000 10.060 20.044 20.000 10.514 10.278 11.000 10.258 10.017 30.125 50.000 10.792 30.399 31.000 10.000 10.013 20.265 10.018 20.000 21.000 10.335 10.381 10.500 10.250 10.004 20.000 10.727 10.000 10.497 10.000 10.188 10.677 20.000 10.708 20.000 10.000 10.945 10.391 10.123 40.000 10.028 10.000 11.000 10.000 10.099 10.451 10.400 10.668 10.573 10.606 10.077 50.003 40.004 10.000 10.042 30.000 10.000 11.000 11.000 10.000 10.042 10.000 20.200 20.302 10.000 21.000 10.000 1
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
TD3D Scannet200permissive0.320 20.501 20.264 20.164 20.841 10.679 10.716 20.879 20.280 30.192 10.634 10.231 10.733 30.459 20.565 30.498 50.560 21.000 10.686 10.890 20.708 10.123 40.820 10.152 20.967 10.456 10.458 20.387 20.194 10.435 50.906 10.077 10.396 20.509 10.217 20.715 10.619 21.000 10.099 20.792 10.513 20.062 20.506 30.549 10.605 11.000 10.123 40.106 11.000 10.744 40.000 21.000 10.504 50.525 20.185 20.790 40.101 20.008 20.587 20.356 10.817 10.083 51.000 10.000 10.621 10.842 10.415 10.268 40.083 40.000 20.098 30.881 10.125 20.000 20.000 10.000 20.000 30.125 40.332 30.448 50.202 20.196 10.798 10.264 20.000 20.000 10.017 20.233 20.000 10.063 10.333 20.038 10.111 10.250 30.000 20.516 10.208 10.470 20.094 30.218 10.000 10.667 20.033 50.000 20.000 10.400 10.156 20.000 10.267 10.226 10.000 10.104 20.159 20.299 50.095 30.458 10.500 10.000 11.000 10.472 10.792 30.000 10.022 10.061 20.250 10.008 10.250 20.333 20.143 20.396 20.049 20.012 10.000 10.283 40.000 10.241 40.000 10.101 20.331 40.000 10.629 30.000 10.000 10.857 20.222 30.677 10.000 10.003 20.000 10.000 20.000 10.076 20.252 30.400 10.431 20.061 30.328 30.331 40.500 10.000 20.000 10.167 10.000 10.000 10.000 20.500 20.000 10.000 21.000 10.542 10.000 20.063 10.000 20.000 1
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
Minkowski 34D Inst.permissive0.203 50.369 40.134 50.078 50.706 40.382 40.693 30.845 30.221 50.150 40.158 40.000 30.746 20.369 40.545 40.595 20.387 40.997 30.413 50.720 50.636 20.165 30.732 30.070 40.851 40.402 40.251 40.313 40.123 40.583 40.696 30.000 30.051 50.500 20.000 30.500 40.372 50.667 40.009 40.000 30.307 50.003 40.479 40.107 50.226 50.903 40.109 50.031 30.981 30.726 50.000 20.522 50.669 20.282 50.052 50.778 50.000 40.000 30.400 30.074 40.333 40.218 41.000 10.000 10.250 30.406 50.118 50.317 20.100 30.000 20.191 10.596 20.000 30.000 20.000 10.000 20.000 30.500 10.178 50.701 20.000 50.000 30.522 50.018 50.000 20.000 10.000 30.060 40.000 10.000 30.033 50.000 30.000 30.000 40.000 20.281 30.100 20.000 50.090 40.133 40.000 10.422 50.050 40.000 20.000 10.200 30.000 50.000 10.000 30.000 30.000 10.000 40.123 40.677 20.021 40.000 40.500 10.000 10.500 40.442 20.125 50.000 10.000 30.000 30.000 30.000 20.000 30.056 40.000 30.000 30.000 30.000 30.000 10.200 50.000 10.143 50.000 10.000 30.250 50.000 10.511 40.000 10.000 10.286 30.083 40.396 20.000 10.000 30.000 10.000 20.000 10.025 40.300 20.000 30.371 30.070 20.000 40.385 30.000 50.000 20.000 10.000 50.000 10.000 10.000 20.500 20.000 10.000 20.000 20.200 20.000 20.000 20.000 20.000 1
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
CSC-Pretrain Inst.permissive0.209 40.361 50.157 40.085 40.700 50.248 50.634 50.776 50.322 20.135 50.103 50.000 30.524 50.364 50.618 20.592 30.381 50.997 30.589 40.747 40.340 50.109 50.768 20.059 50.702 50.448 20.188 50.149 50.091 50.636 30.573 50.000 30.246 30.500 20.000 30.450 50.405 30.667 40.006 50.000 30.356 40.007 30.506 20.420 30.340 30.667 50.294 20.004 40.571 40.748 20.000 21.000 10.573 40.502 40.094 40.807 30.000 40.000 30.400 30.000 50.278 50.228 31.000 10.000 10.115 50.432 40.198 30.050 50.125 20.000 20.000 50.573 30.000 30.000 20.000 10.000 20.000 30.125 40.312 40.610 30.221 10.000 30.667 40.050 40.000 20.000 10.000 30.032 50.000 10.000 30.083 30.000 30.000 30.000 40.000 20.220 40.000 50.125 30.000 50.111 50.000 10.667 20.200 30.000 20.000 10.000 40.110 30.000 10.000 30.000 30.000 10.000 40.053 50.500 40.000 50.000 40.500 10.000 10.500 40.333 40.500 40.000 10.000 30.000 30.000 30.000 20.000 30.000 50.000 30.000 30.000 30.000 30.000 10.600 20.000 10.364 20.000 10.000 30.750 10.000 10.833 10.000 10.000 10.143 50.000 50.396 20.000 10.000 30.000 10.000 20.000 10.021 50.221 40.000 30.093 50.055 40.451 20.677 20.125 20.000 20.000 10.028 40.000 10.000 10.000 20.500 20.000 10.000 20.000 20.050 40.000 20.000 20.000 20.000 1
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021
LGround Inst.permissive0.246 30.413 30.170 30.130 30.754 30.541 30.682 40.903 10.264 40.164 20.234 30.000 30.681 40.452 30.464 50.541 40.399 31.000 10.637 20.772 30.588 40.190 20.589 50.081 30.857 30.426 30.373 30.318 30.135 20.690 20.653 40.000 30.159 40.500 20.000 30.581 30.387 41.000 10.046 30.000 30.402 30.003 50.455 50.196 40.571 21.000 10.270 30.003 50.530 50.748 30.000 20.744 40.575 30.511 30.112 30.815 20.067 30.000 30.400 30.167 30.667 30.241 21.000 10.000 10.208 40.660 30.125 40.317 20.000 50.000 20.100 20.561 40.000 30.000 20.000 10.000 21.000 10.500 10.344 20.568 40.167 30.000 30.706 30.068 30.000 20.000 10.000 30.063 30.000 10.000 30.056 40.000 30.000 30.500 20.000 20.143 50.017 40.125 30.097 20.164 30.000 10.582 40.400 10.000 20.000 10.000 40.083 40.000 10.000 30.000 30.000 10.025 30.156 30.533 30.250 20.200 20.500 10.000 11.000 10.333 41.000 10.000 10.000 30.000 30.000 30.000 20.000 30.333 20.000 30.000 30.000 30.000 30.000 10.400 30.000 10.364 20.000 10.000 30.500 30.000 10.511 40.000 10.000 10.286 30.333 20.000 50.000 10.000 30.000 10.000 20.000 10.034 30.111 50.000 30.333 40.031 50.000 40.750 10.125 20.000 20.000 10.151 20.000 10.000 10.000 20.500 20.000 10.000 20.000 20.000 50.000 20.000 20.000 20.000 1
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild.


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 70.770 110.856 140.555 150.943 10.660 240.735 20.979 10.606 60.492 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 20.597 10.916 50.696 90.713 50.979 10.635 10.384 30.793 30.907 100.821 50.790 330.696 130.967 30.903 20.805 3
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 ScanNet0.789 30.763 580.858 10.875 10.769 130.859 120.557 130.930 30.757 10.716 30.963 150.604 70.351 110.817 10.930 40.782 130.835 10.751 10.952 70.897 50.808 2
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 7
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
Mix3Dpermissive0.781 50.964 20.855 20.843 180.781 70.858 130.575 60.831 360.685 150.714 40.979 10.594 100.310 290.801 20.892 180.841 20.819 50.723 50.940 150.887 80.725 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 40.576 50.905 90.704 60.739 10.969 110.611 20.349 120.756 250.958 10.702 480.805 160.708 90.916 350.898 40.801 4
TTT-KD0.773 70.646 940.818 150.809 380.774 90.878 30.581 20.943 10.687 130.704 70.978 50.607 50.336 180.775 110.912 80.838 40.823 30.694 140.967 30.899 30.794 6
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ResLFE_HDS0.772 80.939 40.824 70.854 70.771 100.840 330.564 100.900 110.686 140.677 140.961 180.537 340.348 130.769 150.903 120.785 120.815 80.676 250.939 160.880 130.772 11
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 80.887 80.780 8
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormerpermissive0.766 90.925 70.808 250.849 110.786 50.846 290.566 90.876 180.690 110.674 160.960 190.576 200.226 700.753 270.904 110.777 150.815 80.722 60.923 300.877 160.776 10
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 30.848 290.709 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 10.562 110.850 280.680 170.672 170.978 50.610 30.335 200.777 90.819 480.847 10.830 20.691 160.972 20.885 100.727 25
O-CNNpermissive0.762 130.924 80.823 80.844 170.770 110.852 210.577 40.847 310.711 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
DiffSegNet0.758 140.725 770.789 400.843 180.762 160.856 140.562 110.920 40.657 270.658 210.958 230.589 130.337 170.782 60.879 230.787 100.779 380.678 210.926 280.880 130.799 5
DTC0.757 150.843 270.820 110.847 140.791 20.862 100.511 360.870 200.707 50.652 230.954 380.604 70.279 470.760 210.942 20.734 290.766 470.701 120.884 570.874 220.736 19
OA-CNN-L_ScanNet200.756 160.783 450.826 60.858 50.776 80.837 360.548 180.896 140.649 290.675 150.962 170.586 160.335 200.771 140.802 520.770 180.787 350.691 160.936 190.880 130.761 13
PNE0.755 170.786 430.835 50.834 250.758 180.849 240.570 80.836 350.648 300.668 190.978 50.581 190.367 70.683 380.856 320.804 70.801 210.678 210.961 50.889 70.716 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 20.758 180.860 110.552 160.891 160.610 440.687 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 90.818 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)
PointConvFormer0.749 210.793 410.790 380.807 400.750 270.856 140.524 290.881 170.588 560.642 300.977 90.591 120.274 500.781 70.929 50.804 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 9
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 MVFusion0.746 250.771 530.819 130.848 130.702 400.865 90.397 880.899 120.699 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 60.839 340.699 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
SAT0.742 300.860 220.765 520.819 310.769 130.848 260.533 250.829 370.663 220.631 340.955 320.586 160.274 500.753 270.896 160.729 300.760 530.666 310.921 320.855 350.733 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
RPN0.736 330.776 490.790 380.851 90.754 220.854 170.491 490.866 230.596 540.686 90.955 320.536 350.342 150.624 530.869 250.787 100.802 170.628 430.927 260.875 200.704 36
IPCA0.731 350.890 150.837 40.864 30.726 350.873 50.530 280.824 400.489 900.647 240.978 50.609 40.336 180.624 530.733 610.758 220.776 400.570 680.949 90.877 160.728 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 60.533 250.754 610.603 500.614 390.955 320.572 220.325 240.710 370.870 240.724 340.823 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 70.537 240.842 320.609 460.608 430.953 420.534 370.293 370.616 560.864 270.719 380.793 300.640 380.933 220.845 440.663 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
contrastBoundarypermissive0.705 410.769 560.775 460.809 380.687 440.820 560.439 760.812 460.661 230.591 530.945 660.515 440.171 940.633 500.856 320.720 360.796 260.668 300.889 540.847 410.689 40
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 420.774 510.800 290.793 490.760 170.847 280.471 540.802 490.463 970.634 330.968 130.491 510.271 540.726 350.910 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 80.517 320.848 290.509 830.626 350.952 460.536 350.225 720.545 770.704 680.689 550.810 140.564 730.903 430.854 370.729 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-PointConv0.676 560.770 550.754 590.783 530.621 640.814 630.552 160.758 590.571 660.557 590.954 380.529 390.268 580.530 800.682 720.675 580.719 700.603 550.888 550.833 460.665 47
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 570.789 420.748 630.763 600.635 620.814 630.407 850.747 630.581 610.573 560.950 520.484 540.271 540.607 570.754 570.649 680.774 410.596 580.883 580.823 520.606 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
PointConvpermissive0.666 600.781 460.759 550.699 730.644 590.822 530.475 520.779 530.564 690.504 790.953 420.428 800.203 830.586 620.754 570.661 640.753 580.588 640.902 440.813 600.642 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-Net0.658 630.778 470.702 800.806 420.619 650.813 660.468 560.693 790.494 860.524 710.941 780.449 720.298 350.510 840.821 460.675 580.727 690.568 710.826 890.803 650.637 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-Netpermissive0.645 670.778 470.731 730.699 730.577 780.829 450.446 680.736 670.477 920.523 730.945 660.454 670.269 560.484 920.749 600.618 800.738 630.599 570.827 880.792 760.621 62
PointConv-SFPN0.641 680.776 490.703 790.721 670.557 850.826 480.451 630.672 840.563 700.483 820.943 750.425 830.162 990.644 460.726 620.659 650.709 740.572 670.875 660.786 810.559 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
FPConvpermissive0.639 710.785 440.760 540.713 710.603 680.798 730.392 900.534 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-Net0.638 720.797 400.769 510.641 960.590 730.820 560.461 600.537 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-SFPN0.631 780.771 530.692 880.672 810.524 900.837 360.440 750.706 770.538 740.446 910.944 720.421 850.219 750.552 740.751 590.591 890.737 640.543 860.901 460.768 880.557 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
DenSeR0.628 820.800 390.625 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
CCRFNet0.589 920.766 570.659 990.683 780.470 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
ROSMRF0.580 930.772 520.707 780.681 790.563 830.764 890.362 970.515 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 ap 50%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PointRel0.816 11.000 10.971 60.908 60.743 20.923 50.573 60.714 220.695 160.734 80.747 20.725 90.809 11.000 10.814 70.899 30.820 31.000 10.610 16
: Relation3D (PointRel): Enhancing Relation Modeling for Point Cloud Instance Segmentation.
Spherical Mask(CtoF)0.812 21.000 10.973 50.852 130.718 50.917 70.574 40.677 280.748 100.729 120.715 60.795 20.809 11.000 10.831 30.854 90.787 101.000 10.638 5
EV3D0.811 31.000 10.968 70.852 130.717 60.921 60.574 50.677 280.748 100.730 110.703 110.795 20.809 11.000 10.831 30.854 90.778 141.000 10.638 6
SIM3D0.803 41.000 10.967 80.863 120.692 160.924 40.552 90.732 210.667 200.732 100.662 140.796 10.789 91.000 10.803 80.864 60.766 191.000 10.643 4
OneFormer3Dcopyleft0.801 51.000 10.973 40.909 50.698 130.928 20.582 30.668 330.685 170.780 20.687 120.698 170.702 141.000 10.794 100.900 20.784 120.986 500.635 7
Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: OneFormer3D: One Transformer for Unified Point Cloud Segmentation.
Competitor-SPFormer0.800 61.000 10.986 20.845 150.705 110.915 80.532 110.733 200.757 90.733 90.708 80.698 160.648 330.981 360.890 10.830 180.796 70.997 370.644 3
UniPerception0.800 61.000 10.930 100.872 100.727 40.862 220.454 170.764 130.820 10.746 60.706 90.750 50.772 100.926 430.764 160.818 260.826 10.997 370.660 2
InsSSM0.799 81.000 10.915 120.710 390.729 30.925 30.664 10.670 310.770 60.766 30.739 30.737 60.700 151.000 10.792 110.829 200.815 40.997 370.625 9
Lei Yao, Yi Wang, Moyun Liu, Lap-Pui Chau: SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation. TCSVT, 2024
TST3D0.795 91.000 10.929 110.918 40.709 90.884 170.596 20.704 250.769 70.734 70.644 190.699 150.751 121.000 10.794 90.876 50.757 210.997 370.550 30
Duc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee: MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation. ACM Multimedia 2024
MG-Former0.791 101.000 10.980 30.837 180.626 240.897 100.543 100.759 150.800 50.766 40.659 150.769 40.697 181.000 10.791 120.707 460.791 91.000 10.610 15
ExtMask3D0.789 111.000 10.988 10.756 320.706 100.912 90.429 180.647 380.806 40.755 50.673 130.689 180.772 111.000 10.789 130.852 110.811 51.000 10.617 12
Queryformer0.787 121.000 10.933 90.601 480.754 10.886 150.558 80.661 350.767 80.665 170.716 50.639 230.808 51.000 10.844 20.897 40.804 61.000 10.624 10
MAFT0.786 131.000 10.894 170.807 220.694 150.893 130.486 130.674 300.740 120.786 10.704 100.727 80.739 131.000 10.707 220.849 130.756 221.000 10.685 1
Mask3D0.780 141.000 10.786 410.716 370.696 140.885 160.500 120.714 220.810 30.672 160.715 60.679 190.809 11.000 10.831 30.833 170.787 101.000 10.602 18
Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe: Mask3D for 3D Semantic Instance Segmentation. ICRA 2023
SPFormerpermissive0.770 150.903 540.903 140.806 230.609 300.886 140.568 70.815 60.705 150.711 130.655 160.652 220.685 211.000 10.789 140.809 270.776 161.000 10.583 23
Sun Jiahao, Qing Chunmei, Tan Junpeng, Xu Xiangmin: Superpoint Transformer for 3D Scene Instance Segmentation. AAAI 2023 [Oral]
SoftGroup++0.769 161.000 10.803 340.937 10.684 170.865 190.213 330.870 20.664 210.571 230.758 10.702 130.807 61.000 10.653 290.902 10.792 81.000 10.626 8
SoftGrouppermissive0.761 171.000 10.808 300.845 150.716 70.862 210.243 300.824 40.655 230.620 180.734 40.699 140.791 80.981 360.716 200.844 140.769 171.000 10.594 21
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
ISBNetpermissive0.757 181.000 10.904 130.731 350.678 180.895 110.458 150.644 400.670 190.710 140.620 240.732 70.650 231.000 10.756 170.778 300.779 131.000 10.614 13
Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen: ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution. CVPR 2023
TD3Dpermissive0.751 191.000 10.774 420.867 110.621 260.934 10.404 190.706 240.812 20.605 210.633 220.626 240.690 201.000 10.640 310.820 230.777 151.000 10.612 14
Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich: Top-Down Beats Bottom-Up in 3D Instance Segmentation. WACV 2024
PBNetpermissive0.747 201.000 10.818 260.837 190.713 80.844 240.457 160.647 380.711 140.614 190.617 260.657 210.650 231.000 10.692 230.822 220.765 201.000 10.595 20
W.Zhao, Y.Yan, C.Yang, J.Ye,X.Yang,K.Huang: Divide and Conquer: 3D Instance Segmentation With Point-Wise Binarization. ICCV 2023
GraphCut0.732 211.000 10.788 390.724 360.642 230.859 230.248 290.787 110.618 260.596 220.653 180.722 110.583 451.000 10.766 150.861 70.825 21.000 10.504 36
IPCA-Inst0.731 221.000 10.788 40