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

CVPR 2020

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

Sep 29, 2020
|
22 views
|
|
Code
Details
Authors: Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, Chiew-Lan Tai Description: 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.

Comments
loading...