ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2006.06234
46
12
v1v2 (latest)

Revisiting the Continuity of Rotation Representations in Neural Networks

11 June 2020
Sitao Xiang
Hao Li
ArXiv (abs)PDFHTML
Abstract

In this paper, we provide some careful analysis of certain pathological behavior of Euler angles and unit quaternions encountered in previous works related to rotation representation in neural networks. In particular, we show that for certain problems, these two representations will provably produce completely wrong results for some inputs, and that this behavior is inherent in the topological property of the problem itself and is not caused by unsuitable network architectures or training procedures. We further show that previously proposed embeddings of SO(3)\mathrm{SO}(3)SO(3) into higher dimensional Euclidean spaces aimed at fixing this behavior are not universally effective, due to possible symmetry in the input causing changes to the topology of the input space. We propose an ensemble trick as an alternative solution.

View on arXiv
Comments on this paper