首页|A convergent framework with learnable feasibility for Hadamard-based image recovery

A convergent framework with learnable feasibility for Hadamard-based image recovery

扫码查看
原文链接
  • NETL
  • NSTL
  • Elsevier
In this paper, we propose a framework for recovering image degradations that can be formulated by the Hadamard product of clear images with degradation factors. By training the mapping from datasets, we show that implicit feasibilities can be learned in forms of latent domains. Then with the feasibilities and acknowledged data priors, the recovery problems are formulated as a general optimization model in which the domain knowledge of degradations are also nicely involved. Then we solve the model based on the classical coordinate update with plugged-in networks so that all the variables can be well estimated. Even better, our updating scheme is designed under the guidance of theoretical analyses, thus its stability can always be guaranteed in practice. We show that different recovery problems can be solved under our unified framework, and the extensive experimental results verify that the proposed framework is superior to state-of-the-art methods in both benchmark datasets and real-world images.

Image recoveryHadamard productData-driven feasibilityLearning paradigmCoordinate update

Yiyang Wang、Long Ma、Risheng Liu

展开 >

School of Information Science and Technology, Dalian Maritime University, Dalian, 116026, China

School of Software Technology, Dalian University of Technology, Dalian, 116024, China, Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, Dalian University of Technology, Dalian, 116024, China

DUT-RU International School of Information Science, Dalian University of Technology, Dalian, 116024, China, Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, Dalian University of Technology, Dalian, 116024, China, Peng Cheng Laboratory, Shenzhen, 518000, China

2021

10.1016/j.cviu.2020.103095

Computer vision and image understanding

Computer vision and image understanding

EISCI
ISSN：1077-3142
年,卷(期)：2021.202(Jan.)
  • 71