PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos

TL;DR

This paper introduces a multi-stage, physics-inspired video restoration framework that effectively reduces turbulence distortions, enhances details, and handles complex dynamic scenes in long-range videos affected by atmospheric turbulence.

Contribution

The paper proposes a novel Physical Model-Driven Multi-Stage Restoration framework and a Dynamic Efficiency Index for better turbulence quantification and restoration in dynamic videos.

Findings

Effective suppression of motion trailing artifacts

Restoration of edge details in turbulent videos

Strong generalization in real-world high-turbulence scenarios

Abstract

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.