TSFormer: A Robust Framework for Efficient UHD Image Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Xin, Wu, Chen, Zheng, Zhuoran
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910705502912512
author Su, Xin
Wu, Chen
Zheng, Zhuoran
author_facet Su, Xin
Wu, Chen
Zheng, Zhuoran
contents Ultra-high-definition (UHD) image restoration is vital for applications demanding exceptional visual fidelity, yet existing methods often face a trade-off between restoration quality and efficiency, limiting their practical deployment. In this paper, we propose TSFormer, an all-in-one framework that integrates \textbf{T}rusted learning with \textbf{S}parsification to boost both generalization capability and computational efficiency in UHD image restoration. The key is that only a small amount of token movement is allowed within the model. To efficiently filter tokens, we use Min-$p$ with random matrix theory to quantify the uncertainty of tokens, thereby improving the robustness of the model. Our model can run a 4K image in real time (40fps) with 3.38 M parameters. Extensive experiments demonstrate that TSFormer achieves state-of-the-art restoration quality while enhancing generalization and reducing computational demands. In addition, our token filtering method can be applied to other image restoration models to effectively accelerate inference and maintain performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10951
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TSFormer: A Robust Framework for Efficient UHD Image Restoration
Su, Xin
Wu, Chen
Zheng, Zhuoran
Computer Vision and Pattern Recognition
Ultra-high-definition (UHD) image restoration is vital for applications demanding exceptional visual fidelity, yet existing methods often face a trade-off between restoration quality and efficiency, limiting their practical deployment. In this paper, we propose TSFormer, an all-in-one framework that integrates \textbf{T}rusted learning with \textbf{S}parsification to boost both generalization capability and computational efficiency in UHD image restoration. The key is that only a small amount of token movement is allowed within the model. To efficiently filter tokens, we use Min-$p$ with random matrix theory to quantify the uncertainty of tokens, thereby improving the robustness of the model. Our model can run a 4K image in real time (40fps) with 3.38 M parameters. Extensive experiments demonstrate that TSFormer achieves state-of-the-art restoration quality while enhancing generalization and reducing computational demands. In addition, our token filtering method can be applied to other image restoration models to effectively accelerate inference and maintain performance.
title TSFormer: A Robust Framework for Efficient UHD Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.10951