See More Details: Efficient Image Super-Resolution by Experts Mining
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913379566747648 |
|---|---|
| author | Zamfir, Eduard Wu, Zongwei Mehta, Nancy Zhang, Yulun Timofte, Radu |
| author_facet | Zamfir, Eduard Wu, Zongwei Mehta, Nancy Zhang, Yulun Timofte, Radu |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03412 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | See More Details: Efficient Image Super-Resolution by Experts Mining Zamfir, Eduard Wu, Zongwei Mehta, Nancy Zhang, Yulun Timofte, Radu Image and Video Processing Computer Vision and Pattern Recognition 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 |
| title | See More Details: Efficient Image Super-Resolution by Experts Mining |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.03412 |