Variational Deep Image Restoration
This work addresses the problem of robust image restoration for real-world applications where degradation models are unknown or varied, representing an incremental advance over prior CNN-based methods.
The paper tackles the challenge of image restoration under diverse and unknown degradations by proposing a new variational inference framework that reformulates the posterior inference into manageable sub-problems, achieving state-of-the-art performance on tasks like Gaussian denoising, real-world noise reduction, blind super-resolution, and JPEG artifact reduction.
This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described by the proposed framework. Earlier CNN-based image restoration methods primarily focused on network architecture design or training strategy with non-blind scenarios where the degradation models are known or assumed. For a step closer to real-world applications, CNNs are also blindly trained with the whole dataset, including diverse degradations. However, the conditional distribution of a high-quality image given a diversely degraded one is too complicated to be learned by a single CNN. Therefore, there have also been some methods that provide additional prior information to train a CNN. Unlike previous approaches, we focus more on the objective of restoration based on the Bayesian perspective and how to reformulate the objective. Specifically, our method relaxes the original posterior inference problem to better manageable sub-problems and thus behaves like a divide-and-conquer scheme. As a result, the proposed framework boosts the performance of several restoration problems compared to the previous ones. Specifically, our method delivers state-of-the-art performance on Gaussian denoising, real-world noise reduction, blind image super-resolution, and JPEG compression artifacts reduction.