papers AI Learner
The Github is limit! Click to go to the new site.

Discrete Rotation Equivariance for Point Cloud Recognition

2019-03-31
Jiaxin Li, Yingcai Bi, Gim Hee Lee

Abstract

Despite the recent active research on processing point clouds with deep networks, few attention has been on the sensitivity of the networks to rotations. In this paper, we propose a deep learning architecture that achieves discrete $\mathbf{SO}(2)$/$\mathbf{SO}(3)$ rotation equivariance for point cloud recognition. Specifically, the rotation of an input point cloud with elements of a rotation group is similar to shuffling the feature vectors generated by our approach. The equivariance is easily reduced to invariance by eliminating the permutation with operations such as maximum or average. Our method can be directly applied to any existing point cloud based networks, resulting in significant improvements in their performance for rotated inputs. We show state-of-the-art results in the classification tasks with various datasets under both $\mathbf{SO}(2)$ and $\mathbf{SO}(3)$ rotations. In addition, we further analyze the necessary conditions of applying our approach to PointNet based networks. Source codes at https://github.com/lijx10/rot-equ-net

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.00319

PDF

http://arxiv.org/pdf/1904.00319


Similar Posts

Comments