TL;DR
RMFAT is a lightweight, recurrent video restoration method that effectively reduces atmospheric turbulence distortions, improving clarity and speed for real-time applications.
Contribution
It introduces a novel recurrent multi-scale framework with temporal warping modules, enabling efficient and temporally consistent atmospheric turbulence mitigation.
Findings
Achieves nearly 9% improvement in SSIM over existing methods.
Reduces inference runtime by more than four times.
Outperforms state-of-the-art in clarity restoration and efficiency.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
