SeemoRe

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

Eduard Zamfir¹, Zongwei Wu^1*, Nancy Mehta¹, Yulun Zhang^2,3* and Radu Timofte^1,2

¹ University of Würzburg, Germany - ² ETH Zürich, Switzerland - ³ Shanghai Jiao Tong University, China

^* Corresponding authors

Latest

• 02/05/2024: Technical report released on arxiv.

Method:

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 **S**eemo**R**e, 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.

Mixture of Low Rank Experts:

Visual Comparisons:

HR	Bicubic	SwinIR-Light	DAT-Light	SeemoRe (ours)

Citation

If you find our work helpful, please consider citing the following paper and/or ⭐ the repo.

@misc{zamfir2024details,
      title={See More Details: Efficient Image Super-Resolution by Experts Mining}, 
      author={Eduard Zamfir and Zongwei Wu and Nancy Mehta and Yulun Zhang and Radu Timofte},
      year={2024},
}

Acknowledgements

This code is built on BasicSR.