Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds

27 May 2020Zhongpai GaoGuangtao ZhaiJunchi YanXiaokang Yang

It has witnessed a growing demand for efficient representation learning on point clouds in many 3D computer vision applications. Behind the success story of convolutional neural networks (CNNs) is that the data (e.g., images) are Euclidean structured... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper