Centralized Sparse Representation for Image Restoration
主 题: Centralized Sparse Representation for Image Restoration
报告人: Dr. Lei Zhang (Dept. of Computing, The Hong Kong Polytechnic University)
时 间: 2011-09-15 10:00-11:00
地 点: 理科一号楼1569（1572）
This talk will introduce some of our recent research progress in sparse representation based image reconstruction. We will first introduce the adaptive sparse domain selection and regularization scheme, and then present the centralized sparse representation (CSR) model we recently developed. The CSR effectively exploits the image local and nonlocal sparsity and combines them into the same energy model. It is very simple but very powerful, and shows state-of-the-art results in image restoration such as deblurring and super-resolution.