English

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

Computer Vision and Pattern Recognition 2020-03-17 v2

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.

Keywords

Cite

@article{arxiv.2003.05855,
  title  = {End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds},
  author = {Lei Li and Siyu Zhu and Hongbo Fu and Ping Tan and Chiew-Lan Tai},
  journal= {arXiv preprint arXiv:2003.05855},
  year   = {2020}
}

Comments

CVPR 2020. Webpage: https://github.com/craigleili/3DLocalMultiViewDesc

R2 v1 2026-06-23T14:12:58.752Z