Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.00406 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916875102846976 |
|---|---|
| author | Wu, Tao Ye, Jingyuan Fu, Ying |
| author_facet | Wu, Tao Ye, Jingyuan Fu, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00406 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos Wu, Tao Ye, Jingyuan Fu, Ying Computer Vision and Pattern Recognition 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. |
| title | PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00406 |