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

• URL: http://arxiv.org/abs/2508.18664v1
• Date: Tue, 26 Aug 2025 04:10:55 GMT
• Title: SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain
• Abstract summary: Recent learning-based underwater image enhancement (UIE) methods have advanced by incorporating physical priors into deep neural networks.<n>We propose using the signal-to-noise ratio prior in the frequency domain, decomposing features into amplitude and phase spectra for better channel modulation.<n>We trained on 4,800 paired images from UIEB, EUVP, and LSUI, and 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.
• Score: 32.62223991134511
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ScaLe-INR: Scale and Learn Implicit Neural Representations [0.0]
  Implicit Neural Representations (INRs) parameterized by multilayer perceptrons excel at modeling continuous signals.<n>High-frequency weight updates destructively interfere with the underlying low-frequency structural approximation.<n>ScaLe-INR explicitly matches the signal's frequency spectrum with the optimal operating region of the INR.
  arXiv  Detail & Related papers  (2026-06-26T09:02:48Z)
• DST-Net: A Dual-Stream Transformer with Illumination-Independent Feature Guidance and Multi-Scale Spatial Convolution for Low-Light Image Enhancement [9.193933558950341]
  Low-light image enhancement aims to restore the visibility of images captured by visual sensors in dim environments.<n>We propose a Dual-Stream Transformer Network (DST-Net) based on illumination-agnostic signal prior guidance and multi-scale spatial convolutions.<n>Our method achieves a PSNR of 25.64 dB on the LOL dataset.
  arXiv  Detail & Related papers  (2026-03-17T13:07:32Z)
• Towards Frequency-Adaptive Learning for SAR Despeckling [10.764049665817629]
  We propose a frequency-adaptive heterogeneous despeckling model based on a divide-and-conquer architecture.<n>Inspired by their differing noise characteristics, we design specialized sub-networks for different frequency components.<n>For high-frequency sub-bands rich in edges and textures, we introduce an enhanced U-Net with deformable convolutions for noise suppression and enhanced features.
  arXiv  Detail & Related papers  (2025-11-08T07:08:22Z)
• FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution [70.61549422952193]
  Face super-resolution (FSR) under limited computational costs remains an open problem.<n>Existing approaches typically treat all facial pixels equally, resulting in suboptimal allocation of computational resources.<n>We propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components.
  arXiv  Detail & Related papers  (2025-06-17T02:33:42Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• snnTrans-DHZ: A Lightweight Spiking Neural Network Architecture for Underwater Image Dehazing [6.780557477791034]
  This paper introduces snnTrans-DHZ, a lightweight Spiking Neural Network (SNN) specifically designed for underwater dehazing.<n>The architecture features three key modules: (i) a K estimator that extracts features from multiple color space representations; (ii) a Background Light Estor that jointly infers the background light component from the RGB-LAB images; and (iii) a soft image reconstruction module that produces haze-free, visibility-enhanced outputs.
  arXiv  Detail & Related papers  (2025-04-13T19:03:33Z)
• FUSION: Frequency-guided Underwater Spatial Image recOnstructioN [0.0]
  Underwater images suffer from severe degradations, including color distortions, reduced visibility, and loss of structural details due to wavelength-dependent attenuation and scattering.<n>Existing enhancement methods primarily focus on spatial-domain processing, neglecting the frequency domain's potential to capture global color distributions and long-range dependencies.<n>We propose fusion, a dual-domain deep learning framework that jointly leverages spatial and frequency domain information.
  arXiv  Detail & Related papers  (2025-04-01T23:16:19Z)
• SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models [52.40011613324083]
  Joint source-channel coding systems (DeepJSCC) have recently demonstrated remarkable performance in wireless image transmission.<n>Existing methods focus on minimizing distortion between the transmitted image and the reconstructed version at the receiver, often overlooking perceptual quality.<n>We propose SING, a novel framework that formulates the recovery of high-quality images from corrupted reconstructions as an inverse problem.
  arXiv  Detail & Related papers  (2025-03-16T12:32:11Z)
• Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising [94.09442506816724]
  Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID)<n>We build a Transformer-based Blind-Spot Network (TBSN) which shows strong local fitting and global perspective abilities.
  arXiv  Detail & Related papers  (2024-04-11T15:39:10Z)
• Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks [15.700048595212051]
  We introduce a self-modulating convolutional neural network which utilizes correlated spectral and spatial information. At the core of the model lies a novel block, which allows the network to transform the features in an adaptive manner based on the adjacent spectral data. Experimental analysis on both synthetic and real data shows that the proposed SM-CNN outperforms other state-of-the-art HSI denoising methods.
  arXiv  Detail & Related papers  (2023-09-15T06:57:43Z)
• Low-Light Enhancement in the Frequency Domain [24.195131201768096]
  Decreased visibility, intensive noise, and biased color are the common problems existing in low-light images. We propose a novel residual recurrent multi-wavelet convolutional neural network R2-MWCNN learned in the frequency domain. This end-to-end trainable network utilizes a multi-level discrete wavelet transform to divide input feature maps into distinct frequencies, resulting in a better denoise impact.
  arXiv  Detail & Related papers  (2023-06-29T08:39:34Z)
• Multi-stage image denoising with the wavelet transform [125.2251438120701]
  Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
  arXiv  Detail & Related papers  (2022-09-26T03:28:23Z)
• Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces [99.34306447202546]
  This paper proposes a deep denoising neural network assisted compressive channel estimation for mmWave IRS systems. We first introduce a hybrid passive/active IRS architecture, where very few receive chains are employed to estimate the uplink user-to-IRS channels. The complete channel matrix can be reconstructed from the limited measurements based on compressive sensing.
  arXiv  Detail & Related papers  (2020-06-03T12:18:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.