Skip to main navigation Skip to search Skip to main content

RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

2 Citations (Scopus)
9 Downloads (Pure)

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, 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 conducted 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 (achieving a more than fourfold reduction), making it particularly suitable for real-time atmospheric turbulence suppression tasks.
Original languageEnglish
Title of host publicationProceedings of the 40th Annual AAAI Conference on Artificial Intelligence
PublisherAAAI Press
Chapter9
Pages7476-7484
Number of pages9
Volume40
Edition9
ISBN (Electronic)9781577359067
DOIs
Publication statusPublished - 14 Mar 2026
EventThe 40th Annual AAAI Conference on Artificial Intelligence - , Singapore
Duration: 20 Jan 2026 → 27 Jan 2026
https://aaai.org/conference/aaai/aaai-26/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAAAI Press
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

ConferenceThe 40th Annual AAAI Conference on Artificial Intelligence
Country/TerritorySingapore
Period20/01/26 → 27/01/26
Internet address

Bibliographical note

Publisher Copyright:
© 2026, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Keywords

  • cs.CV

Fingerprint

Dive into the research topics of 'RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator'. Together they form a unique fingerprint.

Cite this