Results for SALoss-ResNet
Submission data
Full name | 3D Instance Embedding Learning With a Structure-Aware Loss Function |
Description | Structure-Aware Loss Function for Point Cloud Segmentation
@ARTICLE{9126193, author={Z. {Liang} and M. {Yang} and H. {Li} and C. {Wang}}, journal={IEEE Robotics and Automation Letters}, title={3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation}, year={2020}, volume={5}, number={3}, pages={4915-4922},} |
Publication title | 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation |
Publication authors | Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang |
Publication venue | IEEE Robotics and Automation Letters (IROS2020) |
Publication URL | https://ieeexplore.ieee.org/document/9126193?denied= |
Input Data Types | Uses Color,Uses Geometry Uses 3D |
Programming language(s) | python |
Hardware | NVIDIA 1080TI |
Submission creation date | 8 Dec, 2018 |
Last edited | 16 Feb, 2016 |
3D semantic instance results
Info | avg ap 25% | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.695 | 1.000 | 0.855 | 0.579 | 0.589 | 0.735 | 0.484 | 0.588 | 0.856 | 0.634 | 0.571 | 0.298 | 0.500 | 1.000 | 0.824 | 0.818 | 0.702 | 0.935 | 0.545 |