SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Xin, Lei, Yingtie, Zhang, Xiujun, Li, Zimeng, Pun, Chi-Man, Chen, Xuhang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911121540120576
author Tian, Xin
Lei, Yingtie
Zhang, Xiujun
Li, Zimeng
Pun, Chi-Man
Chen, Xuhang
author_facet Tian, Xin
Lei, Yingtie
Zhang, Xiujun
Li, Zimeng
Pun, Chi-Man
Chen, Xuhang
contents Recent learning-based underwater image enhancement (UIE) methods have advanced by incorporating physical priors into deep neural networks, particularly using the signal-to-noise ratio (SNR) prior to reduce wavelength-dependent attenuation. However, spatial domain SNR priors have two limitations: (i) they cannot effectively separate cross-channel interference, and (ii) they provide limited help in amplifying informative structures while suppressing noise. To overcome these, we propose using the SNR prior in the frequency domain, decomposing features into amplitude and phase spectra for better channel modulation. We introduce the Fourier Attention SNR-prior Transformer (FAST), combining spectral interactions with SNR cues to highlight key spectral components. Additionally, the Frequency Adaptive Transformer (FAT) bottleneck merges low- and high-frequency branches using a gated attention mechanism to enhance perceptual quality. Embedded in a unified U-shaped architecture, these modules integrate a conventional RGB stream with an SNR-guided branch, forming SFormer. Trained on 4,800 paired images from UIEB, EUVP, and LSUI, SFormer surpasses recent methods with a 3.1 dB gain in PSNR and 0.08 in SSIM, successfully restoring colors, textures, and contrast in underwater scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain
Tian, Xin
Lei, Yingtie
Zhang, Xiujun
Li, Zimeng
Pun, Chi-Man
Chen, Xuhang
Computer Vision and Pattern Recognition
Recent learning-based underwater image enhancement (UIE) methods have advanced by incorporating physical priors into deep neural networks, particularly using the signal-to-noise ratio (SNR) prior to reduce wavelength-dependent attenuation. However, spatial domain SNR priors have two limitations: (i) they cannot effectively separate cross-channel interference, and (ii) they provide limited help in amplifying informative structures while suppressing noise. To overcome these, we propose using the SNR prior in the frequency domain, decomposing features into amplitude and phase spectra for better channel modulation. We introduce the Fourier Attention SNR-prior Transformer (FAST), combining spectral interactions with SNR cues to highlight key spectral components. Additionally, the Frequency Adaptive Transformer (FAT) bottleneck merges low- and high-frequency branches using a gated attention mechanism to enhance perceptual quality. Embedded in a unified U-shaped architecture, these modules integrate a conventional RGB stream with an SNR-guided branch, forming SFormer. Trained on 4,800 paired images from UIEB, EUVP, and LSUI, SFormer surpasses recent methods with a 3.1 dB gain in PSNR and 0.08 in SSIM, successfully restoring colors, textures, and contrast in underwater scenes.
title SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.18664