English

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

Computer Vision and Pattern Recognition 2025-07-04 v3

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.

Keywords

Cite

@article{arxiv.2506.23897,
  title  = {PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View},
  author = {Longliang Liu and Miaojie Feng and Junda Cheng and Jijun Xiang and Xuan Zhu and Xin Yang},
  journal= {arXiv preprint arXiv:2506.23897},
  year   = {2025}
}
R2 v1 2026-07-01T03:39:36.587Z