{"ID":2881917,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11409","arxiv_id":"2508.11409","title":"RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator","abstract":"Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer and 3D architectures and require multi-frame input, but their large computational cost and memory usage limit real-time deployment, especially in resource-constrained scenarios. In this work, we propose RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator, designed for efficient and temporally consistent video restoration under AT conditions. RMFAT adopts a lightweight recurrent framework that restores each frame using only two inputs at a time, significantly reducing temporal window size and computational burden. It further integrates multi-scale feature encoding and decoding with temporal warping modules at both encoder and decoder stages to enhance spatial detail and temporal coherence. Extensive experiments on synthetic and real-world atmospheric turbulence datasets demonstrate that RMFAT not only outperforms existing methods in terms of clarity restoration (with nearly a 9\\% improvement in SSIM) but also achieves significantly improved inference speed (more than a fourfold reduction in runtime), making it particularly suitable for real-time atmospheric turbulence suppression tasks.","short_abstract":"Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer and 3D architectures and require multi-fram...","url_abs":"https://arxiv.org/abs/2508.11409","url_pdf":"https://arxiv.org/pdf/2508.11409v1","authors":"[\"Zhiming Liu\",\"Nantheera Anantrasirichai\"]","published":"2025-08-15T11:20:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}