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

Eduard Zamfir, Zongwei Wu, Nancy Mehta, Yulun Zhang, Radu Timofte
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58158-58173, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-zamfir24a, title = {See More Details: Efficient Image Super-Resolution by Experts Mining}, author = {Zamfir, Eduard and Wu, Zongwei and Mehta, Nancy and Zhang, Yulun and Timofte, Radu}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {58158--58173}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/zamfir24a/zamfir24a.pdf}, url = {https://proceedings.mlr.press/v235/zamfir24a.html}, 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.} }
Endnote
%0 Conference Paper %T See More Details: Efficient Image Super-Resolution by Experts Mining %A Eduard Zamfir %A Zongwei Wu %A Nancy Mehta %A Yulun Zhang %A Radu Timofte %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-zamfir24a %I PMLR %P 58158--58173 %U https://proceedings.mlr.press/v235/zamfir24a.html %V 235 %X 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.
APA
Zamfir, E., Wu, Z., Mehta, N., Zhang, Y. & Timofte, R.. (2024). See More Details: Efficient Image Super-Resolution by Experts Mining. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:58158-58173 Available from https://proceedings.mlr.press/v235/zamfir24a.html.

Related Material