Frequency-Integrated Transformer for Arbitrary-Scale Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xufei, Ge, Fei, Zhu, Jinchen, Zhang, Mingjian, Wu, Qi, Weng, Jifeng Ren Shizhuang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918001072144384
author Wang, Xufei
Ge, Fei
Zhu, Jinchen
Zhang, Mingjian
Wu, Qi
Weng, Jifeng Ren Shizhuang
author_facet Wang, Xufei
Ge, Fei
Zhu, Jinchen
Zhang, Mingjian
Wu, Qi
Weng, Jifeng Ren Shizhuang
contents Methods based on implicit neural representation have demonstrated remarkable capabilities in arbitrary-scale super-resolution (ASSR) tasks, but they neglect the potential value of the frequency domain, leading to sub-optimal performance. We proposes a novel network called Frequency-Integrated Transformer (FIT) to incorporate and utilize frequency information to enhance ASSR performance. FIT employs Frequency Incorporation Module (FIM) to introduce frequency information in a lossless manner and Frequency Utilization Self-Attention module (FUSAM) to efficiently leverage frequency information by exploiting spatial-frequency interrelationship and global nature of frequency. FIM enriches detail characterization by incorporating frequency information through a combination of Fast Fourier Transform (FFT) with real-imaginary mapping. In FUSAM, Interaction Implicit Self-Attention (IISA) achieves cross-domain information synergy by interacting spatial and frequency information in subspace, while Frequency Correlation Self-attention (FCSA) captures the global context by computing correlation in frequency. Experimental results demonstrate FIT yields superior performance compared to existing methods across multiple benchmark datasets. Visual feature map proves the superiority of FIM in enriching detail characterization. Frequency error map validates IISA productively improve the frequency fidelity. Local attribution map validates FCSA effectively captures global context.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18818
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frequency-Integrated Transformer for Arbitrary-Scale Super-Resolution
Wang, Xufei
Ge, Fei
Zhu, Jinchen
Zhang, Mingjian
Wu, Qi
Weng, Jifeng Ren Shizhuang
Machine Learning
Methods based on implicit neural representation have demonstrated remarkable capabilities in arbitrary-scale super-resolution (ASSR) tasks, but they neglect the potential value of the frequency domain, leading to sub-optimal performance. We proposes a novel network called Frequency-Integrated Transformer (FIT) to incorporate and utilize frequency information to enhance ASSR performance. FIT employs Frequency Incorporation Module (FIM) to introduce frequency information in a lossless manner and Frequency Utilization Self-Attention module (FUSAM) to efficiently leverage frequency information by exploiting spatial-frequency interrelationship and global nature of frequency. FIM enriches detail characterization by incorporating frequency information through a combination of Fast Fourier Transform (FFT) with real-imaginary mapping. In FUSAM, Interaction Implicit Self-Attention (IISA) achieves cross-domain information synergy by interacting spatial and frequency information in subspace, while Frequency Correlation Self-attention (FCSA) captures the global context by computing correlation in frequency. Experimental results demonstrate FIT yields superior performance compared to existing methods across multiple benchmark datasets. Visual feature map proves the superiority of FIM in enriching detail characterization. Frequency error map validates IISA productively improve the frequency fidelity. Local attribution map validates FCSA effectively captures global context.
title Frequency-Integrated Transformer for Arbitrary-Scale Super-Resolution
topic Machine Learning
url https://arxiv.org/abs/2504.18818