RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator

• URL: http://arxiv.org/abs/2508.11409v1
• Date: Fri, 15 Aug 2025 11:20:18 GMT
• Title: RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator
• Authors: Zhiming Liu, Nantheera Anantrasirichai,
• Abstract summary: Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering.<n>We propose RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator, designed for efficient and temporally consistent video restoration under AT conditions.
• Score: 4.021926055330021
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis [65.19146708498346]
  Atmospheric turbulence significantly degrades long-range imaging by introducing geometric warping and exposure-timedependent blur.<n>Existing methods for turbulence effects often oversimplify the relationship between blur and exposure-time.<n>We construct ET-Turb, a large-scale synthetic turbulence dataset that explicitly incorporates continuous exposure-time modeling.
  arXiv  Detail & Related papers  (2026-03-02T02:58:44Z)
• OSDEnhancer: Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion [64.10689934231165]
  Video super-resolution models (DMs) have demonstrated exceptional success in video super-resolution (VSR)<n>Their potential for space-time video super-resolution (STVSR) necessitates recovering realistic visual content from low to high-resolution but also improving the frame rate with coherent dynamics.<n>We propose OSDEnhancer, a framework that represents the first method to initialize real-world STVSR through an efficient one-step diffusion process.<n> Experiments demonstrate that the proposed method achieves state-of-the-art performance while maintaining superior capability in real-world scenarios.
  arXiv  Detail & Related papers  (2026-01-28T06:59:55Z)
• Sliding Window Attention for Learned Video Compression [67.57073402826292]
  This work introduces 3D Sliding Window Attention (SWA), a patchless form of local attention.<n>Our method significantly improves rate-distortion performance, achieving Bjorntegaard Delta-rate savings of up to 18.6 %.
  arXiv  Detail & Related papers  (2025-10-04T20:11:43Z)
• EGTM: Event-guided Efficient Turbulence Mitigation [19.09752432962073]
  Turbulence mitigation (TM) aims to remove the distortions and blurs introduced by atmospheric turbulence into frame cameras.<n>We present a novel EGTM framework that extracts pixel-level reliable turbulence-free guidance from noisy turbulent events for temporal lucky fusion.<n>We build the first turbulence data acquisition system to contribute the first real-world event-driven TM dataset.
  arXiv  Detail & Related papers  (2025-09-04T01:49:13Z)
• FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution [68.77813885751308]
  State-of-the-art (SOTA) compressed video super-resolution (CVSR) models face persistent challenges, including prolonged inference time, complex training pipelines, and reliance on auxiliary information.<n>We propose an efficient and scalable solution inspired by the structural and statistical similarities between hyperspectral images (HSI) and video data.<n>Our approach introduces a compression-driven dimensionality reduction strategy that reduces computational complexity, accelerates inference, and enhances the extraction of temporal information across frames.
  arXiv  Detail & Related papers  (2025-06-13T07:59:52Z)
• Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation [13.073844945948132]
  Atmospheric turbulence is a major source of image degradation in long-range imaging systems.<n>Many deep learning-based turbulence mitigation (TM) methods have been proposed, but they are slow, memory-hungry, and do not generalize well.<n>We present a new TM method based on two concepts: (1) A turbulence mitigation network based on the Selective State Space Model (MambaTM) and (2) Learned Latent Phase Distortion (LPD)<n>Our proposed method exceeds current state-of-the-art networks on various synthetic and real-world TM benchmarks with significantly faster inference speed.
  arXiv  Detail & Related papers  (2025-04-03T15:33:18Z)
• Temporal-Consistent Video Restoration with Pre-trained Diffusion Models [51.47188802535954]
  Video restoration (VR) aims to recover high-quality videos from degraded ones.<n>Recent zero-shot VR methods using pre-trained diffusion models (DMs) suffer from approximation errors during reverse diffusion and insufficient temporal consistency.<n>We present a novel a Posterior Maximum (MAP) framework that directly parameterizes video frames in the seed space of DMs, eliminating approximation errors.
  arXiv  Detail & Related papers  (2025-03-19T03:41:56Z)
• Temporal Feature Matters: A Framework for Diffusion Model Quantization [105.3033493564844]
  Diffusion models rely on the time-step for the multi-round denoising.<n>We introduce a novel quantization framework that includes three strategies.<n>This framework preserves most of the temporal information and ensures high-quality end-to-end generation.
  arXiv  Detail & Related papers  (2024-07-28T17:46:15Z)
• Spatio-Temporal Turbulence Mitigation: A Translational Perspective [13.978156774471744]
  We present the Deep Atmospheric TUrbulence Mitigation network ( DATUM) DATUM aims to overcome major challenges when transitioning from classical to deep learning approaches. A large-scale training dataset, ATSyn, is presented as a co-invention to enable generalization in real turbulence.
  arXiv  Detail & Related papers  (2024-01-08T21:35:05Z)
• StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences [31.210626775505407]
  Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. We present a Streamlined In-batch Multi-frame (SIM) pipeline tailored to video input, attaining a similar level of time efficiency to two-frame networks. StreamFlow not only excels in terms of performance on challenging KITTI and Sintel datasets, with particular improvement in occluded areas.
  arXiv  Detail & Related papers  (2023-11-28T07:53:51Z)
• Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model [82.23276183684001]
  We propose a physics-inspired transformer model for imaging through atmospheric turbulence. The proposed network utilizes the power of transformer blocks to jointly extract a dynamical turbulence distortion map. We present two new real-world turbulence datasets that allow for evaluation with both classical objective metrics and a new task-driven metric using text recognition accuracy.
  arXiv  Detail & Related papers  (2022-07-20T17:09:16Z)
• Atmospheric Turbulence Removal with Complex-Valued Convolutional Neural Network [2.657505380055164]
  Atmospheric turbulence distorts visual imagery and is always problematic for information interpretation by both human and machine. Deep learning-based approaches have gained more attention but currently work efficiently only on static scenes. This paper presents a novel learning-based framework offering short temporal spanning to support dynamic scenes.
  arXiv  Detail & Related papers  (2022-04-14T14:29:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.