# Physics-Based Generative Adversarial Models for Image Restoration and Beyond

arXiv: https://arxiv.org/abs/1808.00605 · HTML: https://mlsanity.com/paper/1808.00605/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2018.

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

- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)
- [Restricted Black-box Adversarial Attack Against DeepFake Face Swapping](https://mlsanity.com/paper/2204.12347/) (2022)
- [SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency](https://mlsanity.com/paper/2303.07033/) (2023)
- [Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration](https://mlsanity.com/paper/2411.01656/) (2024)
- [CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising](https://mlsanity.com/paper/2207.07798/) (2022)
- [Online-updated High-order Collaborative Networks for Single Image Deraining](https://mlsanity.com/paper/2202.06568/) (2022)
- [Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration](https://mlsanity.com/paper/2405.02843/) (2024)
- [RCRN: Real-world Character Image Restoration Network via Skeleton Extraction](https://mlsanity.com/paper/2207.07795/) (2022)
- [Taming Diffusion Models for Image Restoration: A Review](https://mlsanity.com/paper/2409.10353/) (2024)
- [Blind Image Deblurring with Unknown Kernel Size and Substantial Noise](https://mlsanity.com/paper/2208.09483/) (2022)
- [SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining](https://mlsanity.com/paper/2111.08892/) (2021)
- [A generative model for surrogates of spatial-temporal wildfire nowcasting](https://mlsanity.com/paper/2308.02810/) (2023)
- [DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models](https://mlsanity.com/paper/2502.03810/) (2025)
- [Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement](https://mlsanity.com/paper/2603.00853/) (2026)
- [Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization](https://mlsanity.com/paper/2201.01034/) (2022)
- [RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image Dehazing](https://mlsanity.com/paper/2405.09083/) (2024)
- [Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal](https://mlsanity.com/paper/2503.09013/) (2025)
- [A Deep Variational Bayesian Framework for Blind Image Deblurring](https://mlsanity.com/paper/2106.02884/) (2021)
- [Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement](https://mlsanity.com/paper/2207.07828/) (2022)
- [Learning to See Through Dazzle](https://mlsanity.com/paper/2402.15919/) (2024)
- [Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding](https://mlsanity.com/paper/2407.14816/) (2024)
- [Manifold-preserved GANs](https://mlsanity.com/paper/2109.08955/) (2021)
- [Physics-Infused Fuzzy Generative Adversarial Network for Robust Failure Prognosis](https://mlsanity.com/paper/2206.07762/) (2022)
- [TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image](https://mlsanity.com/paper/2609.04911/) (2026)
- [Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration](https://mlsanity.com/paper/2207.08808/) (2022)
- [TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation](https://mlsanity.com/paper/2302.08047/) (2023)
- [A Diffusion-Based Generative Prior Approach to Sparse-view Computed Tomography](https://mlsanity.com/paper/2602.10722/) (2026)

## Abstract (arXiv)

We present an algorithm to directly solve numerous image restoration problems (e.g., image deblurring, image dehazing, image deraining, etc.). These problems are highly ill-posed, and the common assumptions for existing methods are usually based on heuristic image priors. In this paper, we find that these problems can be solved by generative models with adversarial learning. However, the basic formulation of generative adversarial networks (GANs) does not generate realistic images, and some structures of the estimated images are usually not preserved well. Motivated by an interesting observation that the estimated results should be consistent with the observed inputs under the physics models, we propose a physics model constrained learning algorithm so that it can guide the estimation of the specific task in the conventional GAN framework. The proposed algorithm is trained in an end-to-end fashion and can be applied to a variety of image restoration and related low-level vision problems. Extensive experiments demonstrate that our method performs favorably against the state-of-the-art algorithms.