This table lists the benchmark results for the 3D semantic label with limited annotations 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
ActiveST0.703 10.977 10.776 20.657 30.707 10.874 10.541 10.744 10.605 10.610 10.968 10.442 30.126 50.705 10.785 10.742 10.791 10.586 10.940 10.839 10.645 1
: ActiveST.
WeakLab-3D-Net(WS3D)permissive0.662 20.812 20.762 30.742 10.635 20.828 40.474 20.736 20.588 20.546 20.947 40.450 20.174 40.536 40.752 20.668 20.735 30.583 20.902 40.797 40.573 3
GaIA0.638 30.536 100.783 10.651 40.600 30.840 20.413 30.728 30.490 50.520 40.948 30.475 10.299 10.518 50.680 30.629 30.729 40.573 30.906 20.815 30.626 2
LE0.608 40.791 30.726 40.651 40.589 40.779 70.346 70.662 60.493 40.524 30.923 110.430 40.234 30.572 20.638 50.411 80.708 50.533 60.855 50.782 50.508 5
One-Thing-One-Click0.594 50.756 40.722 50.494 100.546 60.795 50.371 40.725 40.559 30.488 50.957 20.367 60.261 20.547 30.575 100.225 100.671 80.543 40.904 30.826 20.557 4
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
Spec-Unc Field0.586 60.736 60.623 90.664 20.559 50.840 20.358 50.666 50.447 60.429 80.944 50.421 50.000 110.411 70.629 60.614 40.745 20.541 50.848 70.758 60.493 6
PointContrast_LA_SEM0.550 70.735 70.676 60.601 70.475 70.794 60.288 90.621 80.378 100.430 70.940 60.303 80.089 80.379 80.580 90.531 50.689 70.422 90.852 60.758 60.468 7
Viewpoint_BN_LA_AIR0.548 80.747 50.574 110.631 60.456 80.762 90.355 60.639 70.412 70.404 90.940 60.335 70.107 60.277 100.645 40.495 60.666 90.517 70.818 80.740 90.431 9
Liyi Luo, Beiwen Tian, Hao Zhao, Guyue Zhou: Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck.
CSC_LA_SEM0.531 90.659 80.638 80.578 80.417 90.775 80.254 100.537 90.396 80.439 60.939 80.284 100.083 90.414 60.599 80.488 70.698 60.444 80.785 90.747 80.440 8
SQN_LA0.486 100.587 90.649 70.527 90.372 100.718 100.320 80.510 100.393 90.325 100.924 100.290 90.095 70.287 90.607 70.356 90.626 100.416 100.672 100.680 110.359 10
Scratch_LA_SEM0.382 110.389 110.606 100.401 110.303 110.705 110.169 110.460 110.292 110.282 110.939 80.207 110.004 100.147 110.201 110.184 110.592 110.389 110.409 110.714 100.250 11


This table lists the benchmark results for the 3D semantic instance with limited annotations 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
WLab3D-Net_Ins(WS3D)permissive0.548 11.000 10.690 10.476 20.406 10.756 10.031 10.733 10.215 10.351 10.415 20.319 10.541 11.000 10.477 10.576 20.557 10.941 20.377 1
Box2Mask_LA0.465 20.667 20.591 30.773 10.331 20.682 20.029 20.409 20.122 20.284 20.432 10.253 20.466 21.000 10.127 40.806 10.280 30.821 40.291 2
Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll: Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. ECCV 2022
CSC_LA_INS0.289 30.667 20.580 40.427 30.202 30.424 50.000 30.384 30.015 30.061 40.180 40.014 30.071 40.119 50.173 30.445 30.390 20.938 30.120 3
PointContrast_LA_INS0.259 40.333 50.286 50.334 40.142 40.485 30.000 30.343 40.010 40.127 30.219 30.005 40.324 30.267 30.226 20.402 50.103 50.994 10.069 4
Scratch_LA_INS0.200 50.667 20.673 20.145 50.100 50.430 40.000 30.314 50.004 50.025 50.099 50.000 50.000 50.143 40.076 50.424 40.198 40.297 50.006 5


This table lists the benchmark results for the 3D object detection with limited annotations 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
WLabel3DNet-LA(WS3D)permissive0.341 11.000 10.629 10.426 10.070 10.608 10.063 10.176 10.503 10.132 10.084 10.001 10.337 10.220 10.103 10.628 10.282 10.739 10.131 1
PointContrast_LA_DET0.135 20.667 20.296 30.145 20.002 30.330 30.000 40.000 30.050 30.049 20.023 20.000 30.002 40.006 40.034 30.472 20.052 20.285 40.011 2
CSC_LA_DET0.135 20.444 30.336 20.029 40.001 40.356 20.008 20.000 20.011 40.045 30.010 40.000 20.032 20.011 30.043 20.458 30.028 30.602 20.010 3
Scratch_LA_DET0.098 40.167 40.253 40.074 30.002 20.257 40.004 30.000 40.080 20.038 40.013 30.000 30.006 30.143 20.002 40.243 40.017 40.473 30.001 4


This table lists the benchmark results for the 3D semantic label with limited reconstructions 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
WeakLab3DNet (WS3D)0.682 10.863 10.765 10.782 10.648 10.803 50.438 10.793 10.607 10.589 10.944 10.455 10.223 10.536 10.768 10.726 10.758 10.623 10.906 10.821 10.596 1
CSC_LR_SEM0.575 20.671 60.740 20.727 20.445 40.847 10.380 50.602 30.512 30.447 30.942 20.291 40.184 20.353 60.468 60.508 40.745 20.602 20.855 20.765 30.420 6
CSG_3DSegNet0.570 30.717 40.730 30.697 30.521 20.823 30.377 60.419 60.531 20.452 20.935 60.316 20.147 30.359 50.551 50.551 30.692 50.513 40.797 40.764 40.508 2
Viewpoint_BN_LR_AIR0.566 40.780 20.659 60.677 40.484 30.799 60.419 30.636 20.480 40.432 50.940 30.238 60.124 40.396 30.609 20.432 60.735 30.527 30.787 50.752 60.423 5
PointContrast_LR_SEM0.555 50.711 50.668 40.622 50.425 50.830 20.433 20.552 40.273 60.440 40.938 40.287 50.096 50.470 20.576 30.612 20.687 60.438 60.781 60.785 20.474 3
Scratch_LR_SEM0.531 60.750 30.666 50.553 60.409 60.816 40.387 40.487 50.285 50.368 60.938 40.310 30.074 60.388 40.564 40.468 50.698 40.448 50.804 30.761 50.454 4


This table lists the benchmark results for the 3D semantic instance with limited reconstructions 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
WeakLabel3DNet(WS3D)0.649 11.000 10.800 10.721 10.603 10.807 10.044 20.735 10.377 10.466 10.550 10.605 10.550 21.000 10.506 10.776 10.618 11.000 10.526 1
TWIST+CSC0.481 20.667 20.760 20.468 30.313 20.802 20.008 30.529 20.098 50.364 20.411 20.348 20.500 40.571 20.504 20.646 40.530 20.944 30.201 2
CSC_LR_INS0.440 30.667 20.737 40.418 50.218 50.791 30.094 10.328 40.185 20.251 50.382 30.273 30.565 10.539 30.377 30.588 50.371 51.000 10.128 4
PointContrast_LR_INS0.432 40.667 20.757 30.560 20.278 40.740 40.003 50.435 30.123 40.309 30.347 40.109 50.522 30.429 50.223 50.739 20.434 40.944 30.149 3
Scratch_LR_INS0.413 50.667 20.720 50.442 40.288 30.735 50.005 40.326 50.138 30.302 40.329 50.204 40.445 50.498 40.229 40.657 30.452 30.889 50.115 5


This table lists the benchmark results for the 3D object detection with limited reconstructions 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
WLabel3DNet-LR(WS3D)permissive0.374 10.867 10.797 10.655 10.104 10.678 10.046 10.215 10.406 10.186 10.219 10.034 10.354 10.160 10.101 10.741 10.306 10.679 10.181 1
CSC_LR_DET0.191 20.667 20.468 30.226 20.036 20.420 30.025 20.010 30.081 30.066 30.045 20.000 20.162 30.010 30.017 20.657 20.109 20.420 30.013 2
PointContrast_LR_DET0.187 30.667 20.523 20.109 30.027 30.435 20.005 30.013 20.199 20.070 20.035 30.000 40.183 20.033 20.003 40.497 30.078 30.488 20.005 3
Scratch_LR_DET0.076 40.667 20.099 40.015 40.005 40.190 40.000 40.000 40.033 40.007 40.001 40.000 30.000 40.010 40.004 30.094 40.014 40.237 40.000 4