Physics-Based Generative Adversarial Models for Image Restoration and Beyond

TL;DR

This paper introduces a physics-constrained GAN framework for various image restoration tasks, leveraging physical models to improve realism and structural preservation in generated images.

Contribution

It proposes a novel physics model constrained learning algorithm within GANs, enabling effective end-to-end training for diverse image restoration problems.

Findings

Outperforms state-of-the-art methods on multiple restoration tasks

Effectively preserves image structures and realism

Applicable to various low-level vision problems

Abstract

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.