针对强湍流下的动态视频模糊与扭曲，提出分阶段物理驱动修复框架。
PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos
- 基于湍流强度、光流和动态区域比例构建动态效率指数，量化视频动态强度。
- 三阶段修复：几何校正→动态区域增强→去模糊，有效恢复边缘细节。
- 轻量级设计+分阶段联合训练，适合真实高湍流复杂动态场景应用。
大气湍流导致远距离动态场景视频出现几何失真和模糊问题。现有方法难以同时恢复边缘细节并消除混合畸变，尤其在强湍流和复杂动态条件下表现不佳。为此，我们提出动态效率指数（DEI），融合湍流强度、光流及动态区域比例，精准量化不同湍流条件下的视频动态强度，并构建了高动态湍流训练数据集。此外，提出物理模型驱动的多阶段视频修复（PMR）框架，包含三个阶段：去倾斜（de-tilting）实现几何稳定，运动分割增强（motion segmentation enhancement）细化动态区域，去模糊（de-blurring）完成质量恢复。PMR采用轻量级主干网络与分阶段联合训练，兼顾效率与高质量修复。实验表明，该方法能有效抑制运动拖尾伪影，恢复边缘细节，且在真实高湍流复杂动态场景中具备强泛化能力。代码与数据集将公开共享。
原文摘要 · Abstract (English)
Geometric distortions and blurring caused by atmospheric turbulence degrade the quality of long-range dynamic scene videos. Existing methods struggle with restoring edge details and eliminating mixed distortions, especially under conditions of strong turbulence and complex dynamics. To address these challenges, we introduce a Dynamic Efficiency Index ($DEI$), which combines turbulence intensity, optical flow, and proportions of dynamic regions to accurately quantify video dynamic intensity under varying turbulence conditions and provide a high-dynamic turbulence training dataset. Additionally, we propose a Physical Model-Driven Multi-Stage Video Restoration ($PMR$) framework that consists of three stages: \textbf{de-tilting} for geometric stabilization, \textbf{motion segmentation enhancement} for dynamic region refinement, and \textbf{de-blurring} for quality restoration. $PMR$ employs lightweight backbones and stage-wise joint training to ensure both efficiency and high restoration quality. Experimental results demonstrate that the proposed method effectively suppresses motion trailing artifacts, restores edge details and exhibits strong generalization capability, especially in real-world scenarios characterized by high-turbulence and complex dynamics. We will make the code and datasets openly available.
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。