REPVSR: Efficient Video Super-Resolution via Structural Re-Parameterization

KunLei Hu, Dahai Yu

2025

Abstract

Recent advances in video super-resolution (VSR) explored the power of deep learning to achieve a better reconstruction performance. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we propose a re-parameterization video superresolution(REPVSR) to accelerate the reconstruction speed with efficient and generic network. Specifically, we propose re-parameterizable building blocks, namely Super-Resolution Multi-Branch block (SRMB) for efficient SR part design and FlowNet Multi-Branch block (FNMB) for optical flow estimation part. The blocks extract features in multiple paths in the training stage, and merge the multiple operations into one single 3×3 convolution in the inference stage. We then propose an extremely efficient VSR network based on SRMB and FNMB, namely REPVSR. Extensive experiments demonstrate the effectiveness and efficiency of REPVSR.

Paper Citation

in Harvard Style

Hu K. and Yu D. (2025). REPVSR: Efficient Video Super-Resolution via Structural Re-Parameterization. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 540-546. DOI: 10.5220/0013186900003912

in Bibtex Style

@conference{visapp25,
author={KunLei Hu and Dahai Yu},
title={REPVSR: Efficient Video Super-Resolution via Structural Re-Parameterization},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={540-546},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013186900003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - REPVSR: Efficient Video Super-Resolution via Structural Re-Parameterization
SN - 978-989-758-728-3
AU - Hu K.
AU - Yu D.
PY - 2025
SP - 540
EP - 546
DO - 10.5220/0013186900003912
PB - SciTePress