# Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model

arXiv: https://arxiv.org/abs/2207.10040 · HTML: https://mlsanity.com/paper/2207.10040/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 20 Jul 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://mlsanity.com/paper/1609.03605/) (2016)
- [Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform](https://mlsanity.com/paper/2107.11627/) (2021)
- [Image Reconstruction of Static and Dynamic Scenes through Anisoplanatic Turbulence](https://mlsanity.com/paper/2009.00071/) (2020)
- [Simulating Anisoplanatic Turbulence by Sampling Inter-modal and Spatially Correlated Zernike Coefficients](https://mlsanity.com/paper/2004.11210/) (2020)
- [Learning to restore images degraded by atmospheric turbulence using uncertainty](https://mlsanity.com/paper/2207.03447/) (2022)
- [Subsampled Turbulence Removal Network](https://mlsanity.com/paper/1807.04418/) (2018)
- [Restoration of Atmospheric Turbulence-distorted Images via RPCA and Quasiconformal Maps](https://mlsanity.com/paper/1704.03140/) (2017)
- [Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs](https://mlsanity.com/paper/2007.08404/) (2020)

## Built on by (most cited first, 30 of 37)

- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy](https://mlsanity.com/paper/2310.01334/) (2023)
- [Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers](https://mlsanity.com/paper/2303.01610/) (2023)
- [The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter](https://mlsanity.com/paper/2306.03805/) (2023)
- [Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation](https://mlsanity.com/paper/2305.00909/) (2023)
- [Physics-Driven Turbulence Image Restoration with Stochastic Refinement](https://mlsanity.com/paper/2307.10603/) (2023)
- [FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping](https://mlsanity.com/paper/2404.03865/) (2024)
- [Spatio-Temporal Turbulence Mitigation: A Translational Perspective](https://mlsanity.com/paper/2401.04244/) (2024)
- [Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models](https://mlsanity.com/paper/2306.10460/) (2023)
- [Deep Learning Techniques for Atmospheric Turbulence Removal: A Review](https://mlsanity.com/paper/2409.14587/) (2024)
- [Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation](https://mlsanity.com/paper/2504.02697/) (2025)
- [Deformation-Invariant Neural Network and Its Applications in Distorted Image Restoration and Analysis](https://mlsanity.com/paper/2310.02641/) (2023)
- [Long-range Turbulence Mitigation: A Large-scale Dataset and A Coarse-to-fine Framework](https://mlsanity.com/paper/2407.08377/) (2024)
- [Atmospheric Turbulence Correction via Variational Deep Diffusion](https://mlsanity.com/paper/2305.05077/) (2023)
- [Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence](https://mlsanity.com/paper/2404.13605/) (2024)
- [Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation](https://mlsanity.com/paper/2405.03662/) (2024)
- [DeTurb: Atmospheric Turbulence Mitigation with Deformable 3D Convolutions and 3D Swin Transformers](https://mlsanity.com/paper/2407.20855/) (2024)
- [Weakly Supervised Face and Whole Body Recognition in Turbulent Environments](https://mlsanity.com/paper/2308.11757/) (2023)
- [Real-World Atmospheric Turbulence Correction via Domain Adaptation](https://mlsanity.com/paper/2402.07371/) (2024)
- [All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networks](https://mlsanity.com/paper/2407.14996/) (2024)
- [Expanding on the BRIAR Dataset: A Comprehensive Whole Body Biometric Recognition Resource at Extreme Distances and Real-World Scenarios (Collections 1-4)](https://mlsanity.com/paper/2501.14070/) (2025)
- [EvTurb: Event Camera Guided Turbulence Removal](https://mlsanity.com/paper/2508.10582/) (2025)
- [EGTM: Event-guided Efficient Turbulence Mitigation](https://mlsanity.com/paper/2509.03808/) (2025)
- [Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication](https://mlsanity.com/paper/2306.10466/) (2023)
- [NeRT: Implicit Neural Representations for General Unsupervised Turbulence Mitigation](https://mlsanity.com/paper/2308.00622/) (2023)
- [DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection](https://mlsanity.com/paper/2507.04323/) (2025)
- [Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques](https://mlsanity.com/paper/2507.08375/) (2025)
- [JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detection](https://mlsanity.com/paper/2507.19780/) (2025)
- [Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis](https://mlsanity.com/paper/2603.01398/) (2026)
- [Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence](https://mlsanity.com/paper/2311.03572/) (2023)

## Abstract (arXiv)

Image restoration algorithms for atmospheric turbulence are known to be much more challenging to design than traditional ones such as blur or noise because the distortion caused by the turbulence is an entanglement of spatially varying blur, geometric distortion, and sensor noise. Existing CNN-based restoration methods built upon convolutional kernels with static weights are insufficient to handle the spatially dynamical atmospheric turbulence effect. To address this problem, in this paper, 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 and restore a turbulence-free image. In addition, recognizing the lack of a comprehensive dataset, we collect and present two new real-world turbulence datasets that allow for evaluation with both classical objective metrics (e.g., PSNR and SSIM) and a new task-driven metric using text recognition accuracy. Both real testing sets and all related code will be made publicly available.