ML Anthology

End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds

Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, Chiew-Lan Tai
CVPR 2020
doi:10.1109/CVPR42600.2020.00199 /cvpr/2020/li2020cvpr-endtoend/

Abstract

In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

PDF CVPR Semantic Scholar

Cite

Text

Li et al. "End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00199

Markdown

[Li et al. "End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/li2020cvpr-endtoend/) doi:10.1109/CVPR42600.2020.00199

BibTeX

@inproceedings{li2020cvpr-endtoend,
  title     = {{End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds}},
  author    = {Li, Lei and Zhu, Siyu and Fu, Hongbo and Tan, Ping and Tai, Chiew-Lan},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00199},
  url       = {https://mlanthology.org/cvpr/2020/li2020cvpr-endtoend/}
}