Learning Super-Resolution Jointly From External and Internal Examples
Zhangyang Wang, Student Member, Yingzhen Yang, Zhaowen Wang, Shiyu Chang, Jianchao Yang, Thomas S. Huang, Life Fellow · 2016
Abstract — Single image super-resolution (SR) aims to esti-mate a high-resolution (HR) image from a low-resolution (LR) input. Image priors are commonly learned to regularize the, otherwise, seriously ill-posed SR problem, either using external LR–HR pairs or internal similar patterns. We propose joint SR to adaptively combine the advantages of both external and internal SR methods. We define two loss functions using sparse coding-based external examples, and epitomic matching based on internal examples, as well as a corresponding adaptive weight to automatically balance their contributions according to their reconstruction errors. Extensive SR results demonstrate the effectiveness of the proposed method over the existing state-of-the-art methods, and is also verified by our subjective evaluation study. Index Terms — Super-resolution, example-based methods, sparse coding, epitome. I.