用正交视图优化全景光流，显著减少极区畸变
PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View
- 双分支结构融合原始与正交视图信息
- 在多个数据集上达到当前最佳性能
- 适合需要高精度全景运动估计的研究者
全景光流可全面理解大视野下的时序动态，但球面到平面投影（如等距柱状投影）带来的严重畸变，显著降低传统透视光流方法的性能，尤其在极区。为此，我们提出PriOr-Flow，一种利用正交视图低畸变特性的新型双分支框架。引入双代价协同查找（DCCL）算子，联合从原始与正交代价体中检索相关性信息，有效抑制代价体构建中的畸变噪声。此外，正交驱动畸变补偿（ODDC）模块迭代优化双分支运动特征，进一步抑制极区畸变。大量实验表明，PriOr-Flow兼容多种基于透视的迭代光流方法，在公开全景光流数据集上持续取得最先进性能，为宽域运动估计设立新基准。代码已开源：https://github.com/longliangLiu/PriOr-Flow。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。