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

TL;DR

PriOr-Flow introduces a dual-branch framework utilizing orthogonal views and novel operators to significantly improve panoramic optical flow estimation by reducing distortions, achieving state-of-the-art results.

Contribution

It proposes PriOr-Flow, a dual-branch approach with DCCL and ODDC modules, to effectively mitigate distortions in panoramic optical flow estimation.

Findings

Achieves state-of-the-art performance on panoramic optical flow datasets.

Compatible with various perspective-based optical flow methods.

Effectively reduces polar distortions in wide-field motion estimation.

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.