Deep likelihood network for image restoration with multiple degradation levels

作     者：Guo, Yiwen Lu, Ming Zuo, Wangmeng Zhang, Changshui Chen, Yurong 

作者机构：Bytedance AI Lab School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Intel Labs China Beijing100190 China Department of Automation State Key Lab of Intelligence Technologies and Systems Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing100084 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2019年

核心收录：

主　　题：Image reconstruction 

摘      要：Convolutional neural networks have been proven very effective in a variety of image restoration tasks. Most state-of-the-art solutions, however, are trained using images with a single particular degradation level, and can deteriorate drastically when being applied to some other degradation settings. In this paper, we propose a novel method dubbed deep likelihood network (DL-Net), aiming at generalizing off-the-shelf image restoration networks to succeed over a spectrum of degradation settings while keeping their original learning objectives and core architectures. In particular, we slightly modify the original restoration networks by appending a simple yet effective recursive module, which is derived from a fidelity term for disentangling the effect of degradations. Extensive experimental results on image inpainting, interpolation and super-resolution demonstrate the effectiveness of our DL-Net. Copyright © 2019, The Authors. All rights reserved.