Papers โ€บ Discrete Rotation Equivariance for Point Cloud Recognition

Discrete Rotation Equivariance for Point Cloud Recognition

31 Mar 2019arXiv:1904.00319archive 2025-07-28

Jiaxin Li, Yingcai Bi, Gim Hee Lee

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 ๐’๐Ž(2)/๐’๐Ž(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 ๐’๐Ž(2) and ๐’๐Ž(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

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lijx10/rot-equ-net officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change ยท a person checks every report against the paper or source before anything changes; decisions are listed on /corrections