Blind Image Deblurring via Adaptive Optimization with Flexible Sparse St rue ture Control

作     者：Ri-Sheng Liu Cai-Sheng Mao Zhi-Hui Wang Hao-Jie Li 

作者机构：International School of Information Science and EngineeringDalian University of TechnologyDalian 116620China Key Laboratory for Ubiquitous Network and Service Software of Liaoning ProvinceDalian 116620China 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2019年第34卷第3期

页      面：609-621页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Natural Science Foundation of China under Grant Nos.61672125 and 61772108. 

主　　题：blind image deblurring conv olutio nal neural net work(CNN) non-convex optimization sparse structure control(SSC) 

摘      要：Blind image deblurring is a long-standing ill-posed inverse problem which aims to recover a latent sharp image given only a blurry observation.So far,existing studies have designed many effective priors w.***.t.the latent image within the maximum a posteriori(MAP)framework in order to narrow down the solution space.These non-convex priors are always integrated into the final deblurring model,which makes the optimization challenging.However,due to unknown image distribution,complex kernel structure and non-uniform noises in real-world scenarios,it is indeed challenging to explicitly design a fixed prior for all cases.Thus we adopt the idea of adaptive optimization and propose the sparse structure control(SSC)for the latent image during the optimization process.In this paper,we only formulate the necessary optiinization constraints in a lightweight MAP model with no priors.Then we develop an inexact projected gradient scheme to incorporate flexible SSC in MAP inference.Besides Zp-norm based SSC in our previous work,we also train a group of denoising convolutional neural networks(CNNs)to learn the sparse image structure automatically from the training data under different noise levels,and we show that CNNs-based SSC can achieve similar results compared with Zp-norm but are more robust to noise.Extensive experiments demonstrate that the proposed adaptive optimization scheme with two types of SSC achieves the state-of-the-art results on both synthetic data and real-world images.