Blind image restoration (IR) is a common yet challenging problem in computer vision. Classical model-based methods and recent deep learning (DL)-based methods represent two different methodologies for this problem, each with their own merits and drawbacks. In this paper, we propose a novel blind image restoration method, aiming to integrate both the advantages of them. Specifically, we construct a general Bayesian generative model for the blind IR, which explicitly depicts the degradation process. In this proposed model, a pixel-wise non-i.i.d. Gaussian distribution is employed to fit the image noise. It is with more flexibility than the simple i.i.d. Gaussian or Laplacian distributions as adopted in most of conventional methods, so as to handle more complicated noise types contained in the image degradation. To solve the model, we design a variational inference algorithm where all the expected posteriori distributions are parameterized as deep neural networks to increase their model capability. Notably, such an inference algorithm induces a unified framework to jointly deal with the tasks of degradation estimation and image restoration. Further, the degradation information estimated in the former task is utilized to guide the latter IR process. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.

翻译：盲图像恢复（IR）是计算机视觉中常见且具挑战性的问题。经典基于模型的方法与近期基于深度学习（DL）的方法代表了解决该问题的两种不同方法论，各有优劣。本文提出一种新颖的盲图像恢复方法，旨在融合两者的优势。具体而言，我们构建了一个通用的贝叶斯生成模型用于盲图像恢复，该模型显式描述了退化过程。在该模型中，采用像素级非独立同分布的高斯分布来拟合图像噪声，相较于大多数传统方法中采用的简单独立同分布高斯分布或拉普拉斯分布，该分布具有更高的灵活性，从而能处理图像退化中更复杂的噪声类型。为求解该模型，我们设计了变分推断算法，其中所有期望后验分布均参数化为深度神经网络以增强其模型能力。值得注意的是，该推断算法形成了一个统一框架，可联合处理退化估计与图像恢复任务。此外，前一任务估计的退化信息被用于指导后续的图像恢复过程。在两类典型的盲图像恢复任务（即图像去噪与超分辨率）上的实验表明，所提方法在性能上超越了当前最先进技术。