Paper Info
Title
Variational Deep Image Restoration
Abstract
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. Our code and more details are available on our project page, https://github.com/JWSoh/VDIR.
Year
DOI
Venue
2022
10.1109/TIP.2022.3183835
IEEE TRANSACTIONS ON IMAGE PROCESSING
Keywords
DocType
Volume
Image restoration, Degradation, Task analysis, Training, Noise reduction, Superresolution, Image coding, Image restoration, variational approximation, image denoising, image super-resolution, JPEG compression artifacts reduction
Journal
31
Issue
ISSN
Citations 
1
1057-7149
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Jae Woong Soh1266.76
Nam Ik Cho2712106.98