Abstract
Image restoration problems are typically ill-posed requiring the design of suitable priors. These priors are typically hand-designed and are fully instantiated throughout the process. In this paper, we introduce a novel framework for handling inverse problems related to image restoration based on elements from the half quadratic splitting method and proximal operators. Modeling the proximal operator as a convolutional network, we defined an implicit prior on the image space as a function class during training. This is in contrast to the common practice in literature of having the prior to be fixed and fully instantiated even during training stages. Further, we allow this proximal operator to be tuned differently for each iteration which greatly increases modeling capacity and allows us to reduce the number of iterations by an order of magnitude as compared to other approaches. Our final network is an end-to-end one whose run time matches the previous fastest algorithms while outperforming them in recovery fidelity on two image restoration tasks. Indeed, we find our approach achieves state-of-the-art results on benchmarks in image denoising and image super resolution while recovering more complex and finer details.
Abstract (translated)
图像恢复问题通常是不适定的,需要设计合适的先验。这些优先级通常是手工设计的,并在整个过程中被完全实例化。本文介绍了一种新的基于半二次分裂和近端算子的图像恢复逆问题处理框架。将近端算子建模为卷积网络,在训练过程中将图像空间上的隐式先验定义为一个函数类。这与文献中的常见做法相反,即在培训阶段也要固定和充分例示先例。此外,我们允许为每个迭代对这个近端操作符进行不同的调优,这大大提高了建模能力,并允许我们将迭代次数减少一个数量级,与其他方法相比。我们的最终网络是一个端到端的网络,其运行时间与以前最快的算法匹配,同时在两个图像恢复任务的恢复保真度方面优于它们。事实上,我们发现我们的方法在图像去噪和图像超分辨率的基准上达到了最先进的结果,同时恢复了更复杂和更精细的细节。
URL
https://arxiv.org/abs/1903.07154