See More Details: Efficient Image Super-Resolution by Experts Mining

TL;DR

SeemoRe is an efficient image super-resolution model that uses expert mining to balance high performance with low computational cost by leveraging specialized experts at multiple levels.

Contribution

The paper introduces SeemoRe, a novel SR model that employs a collaborative expert mining strategy to improve accuracy while reducing computational complexity.

Findings

Achieves high-quality super-resolution with minimal computational cost

Effectively captures intra-feature details through expert collaboration

Outperforms existing methods in efficiency and accuracy

Abstract

Reconstructing high-resolution (HR) images from low-resolution (LR) inputs poses a significant challenge in image super-resolution (SR). While recent approaches have demonstrated the efficacy of intricate operations customized for various objectives, the straightforward stacking of these disparate operations can result in a substantial computational burden, hampering their practical utility. In response, we introduce SeemoRe, an efficient SR model employing expert mining. Our approach strategically incorporates experts at different levels, adopting a collaborative methodology. At the macro scale, our experts address rank-wise and spatial-wise informative features, providing a holistic understanding. Subsequently, the model delves into the subtleties of rank choice by leveraging a mixture of low-rank experts. By tapping into experts specialized in distinct key factors crucial for accurate SR, our model excels in uncovering intricate intra-feature details. This collaborative approach is reminiscent of the concept of "see more", allowing our model to achieve an optimal performance with minimal computational costs in efficient settings. The source will be publicly made available at https://github.com/eduardzamfir/seemoredetails