Pan Jinshan, Dong Jiangxin, Liu Yang, Zhang Jiawei, Ren Jimmy, Tang Jinhui, Tai Yu-Wing, Yang Ming-Hsuan
IEEE Trans Pattern Anal Mach Intell. 2021 Jul;43(7):2449-2462. doi: 10.1109/TPAMI.2020.2969348. Epub 2021 Jun 8.
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.
我们提出了一种直接解决众多图像恢复问题（如图像去模糊、图像去雾和图像去雨）的算法。这些问题是不适定的，现有方法的常见假设通常基于启发式图像先验。在本文中，我们表明这些问题可以通过具有对抗学习的生成模型来解决。然而，基于简单生成对抗网络（GAN）的直接公式在这些任务中表现不佳，并且估计图像的一些结构通常不能很好地保留。受一个有趣观察的启发，即在物理模型下估计结果应与观察到的输入一致，我们提出了一种在GAN框架内指导特定任务估计过程的算法。所提出的模型以端到端的方式进行训练，并且可以应用于各种图像恢复和低级视觉问题。大量实验表明，所提出的方法优于现有算法。
