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
WeakLab-3D-Net(WS3D)permissive0.662 10.812 10.762 10.742 10.635 10.828 20.474 10.736 10.588 10.546 10.947 20.450 10.174 30.536 30.752 10.668 10.735 20.583 10.902 20.797 20.573 1
LE0.608 20.791 20.726 20.651 30.589 20.779 50.346 50.662 40.493 30.524 20.923 90.430 20.234 20.572 10.638 30.411 60.708 30.533 40.855 30.782 30.508 3
One-Thing-One-Click0.594 30.756 30.722 30.494 80.546 40.795 30.371 20.725 20.559 20.488 30.957 10.367 40.261 10.547 20.575 80.225 80.671 60.543 20.904 10.826 10.557 2
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 40.736 50.623 70.664 20.559 30.840 10.358 30.666 30.447 40.429 60.944 30.421 30.000 90.411 50.629 40.614 20.745 10.541 30.848 50.758 40.493 4
PointContrast_LA_SEM0.550 50.735 60.676 40.601 50.475 50.794 40.288 70.621 60.378 80.430 50.940 40.303 60.089 60.379 60.580 70.531 30.689 50.422 70.852 40.758 40.468 5
Viewpoint_BN_LA_AIR0.548 60.747 40.574 90.631 40.456 60.762 70.355 40.639 50.412 50.404 70.940 40.335 50.107 40.277 80.645 20.495 40.666 70.517 50.818 60.740 70.431 7
Liyi Luo, Beiwen Tian, Hao Zhao, Guyue Zhou: Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck.
CSC_LA_SEM0.531 70.659 70.638 60.578 60.417 70.775 60.254 80.537 70.396 60.439 40.939 60.284 80.083 70.414 40.599 60.488 50.698 40.444 60.785 70.747 60.440 6
SQN_LA0.486 80.587 80.649 50.527 70.372 80.718 80.320 60.510 80.393 70.325 80.924 80.290 70.095 50.287 70.607 50.356 70.626 80.416 80.672 80.680 90.359 8
Scratch_LA_SEM0.382 90.389 90.606 80.401 90.303 90.705 90.169 90.460 90.292 90.282 90.939 60.207 90.004 80.147 90.201 90.184 90.592 90.389 90.409 90.714 80.250 9

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 20.327 10.541 11.000 10.477 10.576 20.557 10.941 20.377 1
MaskVoteNet_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
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 40.438 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 50.740 20.727 20.445 30.847 10.380 50.602 30.512 20.447 20.942 20.291 30.184 20.353 50.468 50.508 30.745 20.602 20.855 20.765 30.420 5
Viewpoint_BN_LR_AIR0.566 30.780 20.659 50.677 30.484 20.799 50.419 30.636 20.480 30.432 40.940 30.238 50.124 30.396 30.609 20.432 50.735 30.527 30.787 40.752 50.423 4
PointContrast_LR_SEM0.555 40.711 40.668 30.622 40.425 40.830 20.433 20.552 40.273 50.440 30.938 40.287 40.096 40.470 20.576 30.612 20.687 50.438 50.781 50.785 20.474 2
Scratch_LR_SEM0.531 50.750 30.666 40.553 50.409 50.816 30.387 40.487 50.285 40.368 50.938 40.310 20.074 50.388 40.564 40.468 40.698 40.448 40.804 30.761 40.454 3

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)0.566 10.667 10.755 30.614 10.488 10.767 30.024 20.710 10.392 10.370 10.496 10.306 20.515 30.857 10.496 20.667 20.596 10.990 20.474 1
TWIST+CSC0.481 20.667 10.760 10.468 30.313 20.802 10.008 30.529 20.098 50.364 20.411 20.348 10.500 40.571 20.504 10.646 40.530 20.944 30.201 2
CSC_LR_INS0.440 30.667 10.737 40.418 50.218 50.791 20.094 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 10.757 20.560 20.278 40.740 40.003 50.435 30.123 40.309 30.347 40.109 50.522 20.429 50.223 50.739 10.434 40.944 30.149 3
Scratch_LR_INS0.413 50.667 10.720 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