4.8 Article

Physics-Based Generative Adversarial Models for Image Restoration and Beyond

Journal

Publisher

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.2969348

Keywords

Image restoration; Generative adversarial networks; Gallium nitride; Physics; Task analysis; Mathematical model; Degradation; Generative adversarial network; physics model; low-level vision; image restoration

Funding

  1. National Natural Science Foundation of China [61922043, 61872421, 61732007]
  2. Natural Science Foundation of Jiangsu Province [BK20180471]
  3. National Science Foundation CAREER [1149783]

Ask authors/readers for more resources

This study proposes an algorithm that addresses image restoration problems using generative models with adversarial learning, guided by physics models and trained in an end-to-end fashion for various low-level vision tasks, demonstrating superior performance compared to existing algorithms through extensive experiments.
We present an algorithm to directly solve numerous image restoration problems (e.g., image deblurring, image dehazing, and image deraining). These problems are ill-posed, and the common assumptions for existing methods are usually based on heuristic image priors. In this paper, we show that these problems can be solved by generative models with adversarial learning. However, a straightforward formulation based on a straightforward generative adversarial network (GAN) does not perform well in these tasks, 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 an algorithm that guides the estimation process of a specific task within the GAN framework. The proposed model is trained in an end-to-end fashion and can be applied to a variety of image restoration and low-level vision problems. Extensive experiments demonstrate that the proposed method performs favorably against state-of-the-art algorithms.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available