Learning Super-Resolution Jointly from External and Internal Examples

TL;DR

This paper introduces a joint super-resolution approach that adaptively combines external and internal example-based methods, leveraging sparse coding and epitomic matching to improve image quality.

Contribution

It proposes a novel adaptive framework that effectively integrates external and internal super-resolution techniques using combined loss functions and dynamic weighting.

Findings

Outperforms existing state-of-the-art SR methods

Demonstrates significant quality improvements in SR results

Validated by subjective evaluation studies

Abstract

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.