Multi-Reference Image Super-Resolution: A Posterior Fusion Approach

TL;DR

This paper introduces a novel 2-step-weighting posterior fusion method for multi-reference image super-resolution, enhancing existing models by effectively combining multiple high-resolution references to improve image quality.

Contribution

It proposes a new posterior fusion approach that can be integrated with various RefSR models to leverage multiple references for better super-resolution results.

Findings

Consistent improvement in image quality across multiple models

Effective utilization of multiple references in super-resolution

Validated on CUFED5 dataset

Abstract

Reference-based Super-resolution (RefSR) approaches have recently been proposed to overcome the ill-posed problem of image super-resolution by providing additional information from a high-resolution image. Multi-reference super-resolution extends this approach by allowing more information to be incorporated. This paper proposes a 2-step-weighting posterior fusion approach to combine the outputs of RefSR models with multiple references. Extensive experiments on the CUFED5 dataset demonstrate that the proposed methods can be applied to various state-of-the-art RefSR models to get a consistent improvement in image quality.