Learning Super-Resolution Jointly from External and Internal Examples
This incremental improvement addresses the super-resolution problem for image processing applications by enhancing reconstruction quality.
The paper tackled the single image super-resolution problem by proposing a joint method that adaptively combines external and internal examples, achieving state-of-the-art results as demonstrated in extensive evaluations.
Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a lowresolution (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.