The reviewed record of science sign in
Pith

arxiv: 2506.23897 · v3 · pith:6D5Q7FCJ · submitted 2025-06-30 · cs.CV

PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View

Reviewed by Pithpith:6D5Q7FCJopen to challenge →

classification cs.CV
keywords flowopticalprior-floworthogonalpanoramicviewavailablecost
0
0 comments X
read the original abstract

Panoramic optical flow enables a comprehensive understanding of temporal dynamics across wide fields of view. However, severe distortions caused by sphere-to-plane projections, such as the equirectangular projection (ERP), significantly degrade the performance of conventional perspective-based optical flow methods, especially in polar regions. To address this challenge, we propose PriOr-Flow, a novel dual-branch framework that leverages the low-distortion nature of the orthogonal view to enhance optical flow estimation in these regions. Specifically, we introduce the Dual-Cost Collaborative Lookup (DCCL) operator, which jointly retrieves correlation information from both the primitive and orthogonal cost volumes, effectively mitigating distortion noise during cost volume construction. Furthermore, our Ortho-Driven Distortion Compensation (ODDC) module iteratively refines motion features from both branches, further suppressing polar distortions. Extensive experiments demonstrate that PriOr-Flow is compatible with various perspective-based iterative optical flow methods and consistently achieves state-of-the-art performance on publicly available panoramic optical flow datasets, setting a new benchmark for wide-field motion estimation. The code is publicly available at: https://github.com/longliangLiu/PriOr-Flow.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.