3D Semantic Label with Limited Annotations Benchmark

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
ActiveST0.748 10.984 10.804 30.759 50.720 20.849 50.516 20.791 30.670 10.654 20.974 10.495 50.382 10.811 10.828 50.787 10.780 60.640 20.952 10.861 30.701 1
Gengxin Liu, Oliver van Kaick, Hui Huang, Ruizhen Hu: Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation.
Q2E0.743 20.984 10.803 40.770 10.725 10.881 10.572 10.806 20.663 20.665 10.972 20.506 30.305 20.652 60.829 40.761 20.809 20.660 10.951 20.862 20.682 2
DE-3DLearner LA0.709 30.877 40.772 80.744 90.694 30.836 70.453 60.787 40.623 40.598 40.953 40.490 70.216 110.682 50.879 10.727 30.802 30.604 50.922 30.845 40.676 3
Ping-Chung Yu, Cheng Sun, Min Sun: Data Efficient 3D Learner via Knowledge Transferred from 2D Model. ECCV 2022
WS3D_LA_Sempermissive0.694 40.895 30.743 100.767 20.675 60.826 100.496 30.817 10.612 50.613 30.947 100.460 90.254 60.558 110.811 70.710 50.776 80.616 30.874 110.822 60.603 12
Kangcheng Liu: WS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination. European Conference on Computer Vision (ECCV), 2022
One-Thing-One-Click0.694 40.760 90.815 20.706 130.684 50.840 60.492 40.701 90.557 70.596 50.972 20.497 40.281 40.709 20.757 80.689 60.789 40.600 70.907 70.864 10.671 4
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
VIBUSpermissive0.691 60.860 50.731 120.738 100.672 70.860 20.470 50.766 50.625 30.547 110.949 50.491 60.255 50.693 40.715 100.712 40.778 70.597 80.911 50.816 90.635 7
Beiwen Tian,Liyi Luo,Hao Zhao,Guyue Zhou: VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling. ISPRS Journal of Photogrammetry and Remote Sensing
LE0.688 70.856 70.779 60.754 70.687 40.834 80.438 80.732 70.536 90.577 60.948 60.508 20.248 70.699 30.831 30.636 80.752 110.586 90.895 90.821 70.643 6
GaIA0.685 80.759 100.834 10.759 50.650 80.859 30.427 100.694 100.524 100.575 70.948 60.537 10.304 30.534 120.853 20.678 70.820 10.581 100.914 40.828 50.626 8
Min Seok Lee*, Seok Woo Yang*, and Sung Won Han: GaIA: Graphical Information gain based Attention Network for Weakly Supervised 3D Point Cloud Semantic Segmentation. WACV 2023
Viewpoint_BN_LA_AIR0.669 90.847 80.732 110.724 110.613 120.827 90.443 70.742 60.562 60.551 100.947 100.441 120.218 100.650 70.753 90.621 90.765 100.601 60.905 80.814 120.618 9
Liyi Luo, Beiwen Tian, Hao Zhao, Guyue Zhou: Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck.
CSC_LA_SEM0.665 100.857 60.756 90.763 40.647 90.852 40.432 90.684 120.543 80.514 120.948 60.469 80.179 120.599 90.702 110.620 100.789 40.614 40.911 50.815 110.607 11
PointContrast_LA_SEM0.653 110.717 120.775 70.754 70.626 110.804 130.391 120.689 110.485 130.572 90.945 120.448 100.232 90.603 80.813 60.591 120.775 90.537 120.885 100.816 90.608 10
Scratch_LA_SEM0.643 120.699 130.793 50.718 120.636 100.816 110.411 110.707 80.490 120.574 80.948 60.448 100.173 130.559 100.689 120.604 110.722 120.556 110.853 120.820 80.651 5
SQN_LA0.598 130.741 110.681 130.766 30.482 130.805 120.389 130.658 130.499 110.437 130.936 130.386 130.243 80.422 130.663 130.552 130.700 130.519 130.809 130.750 130.515 13


3D Semantic Instance with Limited Annotations Benchmark

This table lists the benchmark results for the 3D semantic instance with limited annotations 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
WS3D_LA_Inspermissive0.442 10.787 10.554 10.488 10.363 10.651 10.035 10.440 10.202 10.307 10.417 10.253 20.329 30.617 10.243 10.594 10.467 10.867 10.348 1
Kangcheng Liu: WS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination. European Conference on Computer Vision (ECCV), 2022
Box2Mask_LA0.341 20.667 20.265 50.385 20.200 20.536 20.026 20.314 30.074 20.159 40.402 20.281 10.335 20.450 50.170 30.570 20.241 50.836 30.221 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_INS0.293 30.485 30.397 30.333 30.168 30.415 30.010 30.337 20.018 40.168 30.263 30.057 30.193 50.495 30.141 40.525 40.318 20.837 20.120 5
PointContrast_LA_INS0.278 40.472 40.427 20.229 50.121 50.327 40.009 40.257 40.021 30.180 20.176 50.019 50.350 10.460 40.098 50.563 30.292 30.834 40.163 3
Scratch_LA_INS0.248 50.122 50.376 40.319 40.158 40.319 50.006 50.239 50.013 50.138 50.206 40.029 40.299 40.506 20.183 20.441 50.259 40.738 50.121 4


3D Object Detection with Limited Annotations Benchmark

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
WS3D_LA_ODpermissive0.341 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
Kangcheng Liu: WS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination. European Conference on Computer Vision (ECCV), 2022
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


3D Semantic Label with Limited Reconstructions Benchmark

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
WS3D_LR_Sem0.682 10.864 20.766 40.785 10.645 10.805 70.443 20.793 10.600 10.588 10.944 70.457 10.222 10.537 30.773 20.724 10.755 20.622 10.907 20.821 30.597 3
Kangcheng Liu: WS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination. European Conference on Computer Vision (ECCV), 2022
NWSYY0.670 20.745 40.784 20.780 30.611 30.829 50.463 10.692 20.585 30.542 30.948 20.448 20.219 20.554 20.828 10.702 20.758 10.573 30.844 70.825 20.674 1
DE-3DLearner LR0.663 30.851 30.770 30.760 40.615 20.830 40.439 30.670 30.546 50.587 20.955 10.406 40.177 40.627 10.758 30.606 40.740 30.549 40.888 30.840 10.652 2
Ping-Chung Yu, Cheng Sun, Min Sun: Data Efficient 3D Learner via Knowledge Transferred from 2D Model. ECCV 2022
Viewpoint_BN_LR_AIR0.625 40.873 10.727 60.709 50.535 70.820 60.402 60.643 50.540 60.501 60.946 40.352 80.181 30.535 40.594 70.596 50.685 80.543 50.927 10.792 40.592 4
CSC_LR_SEM0.612 50.739 70.794 10.687 80.564 40.850 10.347 80.590 70.587 20.521 40.945 60.358 70.140 60.522 60.496 80.627 30.725 50.598 20.850 40.792 40.508 5
PointContrast_LR_SEM0.603 60.740 60.700 80.700 60.546 60.843 20.419 40.592 60.462 70.513 50.946 40.374 50.104 80.530 50.687 40.571 80.694 70.519 70.850 40.781 70.484 8
Scratch_LR_SEM0.596 70.745 40.722 70.783 20.486 80.834 30.414 50.667 40.398 80.492 70.948 20.359 60.124 70.406 80.636 50.574 60.708 60.503 80.849 60.784 60.490 7
CSG_3DSegNet0.594 80.732 80.755 50.697 70.548 50.790 80.363 70.432 80.576 40.448 80.933 80.414 30.168 50.486 70.621 60.574 60.727 40.539 60.807 80.779 80.498 6


3D Semantic Instance with Limited Reconstructions Benchmark

This table lists the benchmark results for the 3D semantic instance with limited reconstructions 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
InstTeacher3D0.473 10.778 30.635 10.331 40.322 20.732 10.089 10.502 10.200 10.350 10.440 10.507 10.489 10.493 30.327 10.655 10.469 10.924 10.268 2
WS3D_LR_Ins0.440 20.704 40.533 20.485 10.335 10.659 20.025 50.460 20.156 20.315 20.412 20.254 20.383 20.638 20.278 20.653 20.431 20.869 20.330 1
Kangcheng Liu: WS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination. European Conference on Computer Vision (ECCV), 2022
TWIST+CSC0.342 30.796 20.412 60.233 60.170 30.637 30.028 20.292 40.089 30.214 30.320 30.133 30.337 40.444 40.242 30.458 50.328 60.852 30.179 3
Ruihang Chu: TWIST: Two-Way Inter-label Self-Training for Semi-supervised 3D Instance Segmentation. CVPR 2022
CSC_LR_INS0.322 40.824 10.433 40.288 50.169 40.610 50.028 20.302 30.084 40.174 50.274 40.061 50.370 30.358 50.142 50.507 40.367 30.701 60.097 6
PointContrast_LR_INS0.304 50.233 60.418 50.389 20.136 60.596 60.006 60.274 50.038 60.140 60.265 50.052 60.314 50.647 10.149 40.533 30.350 50.806 40.132 4
Scratch_LR_INS0.287 60.485 50.438 30.362 30.154 50.614 40.028 20.218 60.058 50.191 40.247 60.065 40.272 60.271 60.109 60.433 60.355 40.766 50.102 5


3D Object Detection with Limited Reconstructions Benchmark

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
WS3D_LR_ODpermissive0.374 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
Kangcheng Liu: WS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination. European Conference on Computer Vision (ECCV), 2022
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