{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/discrete-rotation-equivariance-for-point","title":"Discrete Rotation Equivariance for Point Cloud Recognition","arxiv_id":"1904.00319","date":"2019-03-31","proceeding":null,"authors":["Jiaxin Li","Yingcai Bi","Gim Hee Lee"],"abstract":"Despite the recent active research on processing point clouds with deep\nnetworks, few attention has been on the sensitivity of the networks to\nrotations. In this paper, we propose a deep learning architecture that achieves\ndiscrete $\\mathbf{SO}(2)$/$\\mathbf{SO}(3)$ rotation equivariance for point\ncloud recognition. Specifically, the rotation of an input point cloud with\nelements of a rotation group is similar to shuffling the feature vectors\ngenerated by our approach. The equivariance is easily reduced to invariance by\neliminating the permutation with operations such as maximum or average. Our\nmethod can be directly applied to any existing point cloud based networks,\nresulting in significant improvements in their performance for rotated inputs.\nWe show state-of-the-art results in the classification tasks with various\ndatasets under both $\\mathbf{SO}(2)$ and $\\mathbf{SO}(3)$ rotations. In\naddition, we further analyze the necessary conditions of applying our approach\nto PointNet based networks. Source codes at\nhttps://github.com/lijx10/rot-equ-net","url_abs":"http://arxiv.org/abs/1904.00319v1","url_pdf":"http://arxiv.org/pdf/1904.00319v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"discrete-rotation-equivariance-for-point","repo_url":"https://github.com/lijx10/rot-equ-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00319","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}