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

arXiv: https://arxiv.org/abs/2508.18664 · HTML: https://mlsanity.com/paper/2508.18664/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 84 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 30 of 36)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [Explicit Visual Prompting for Low-Level Structure Segmentations](https://mlsanity.com/paper/2303.10883/) (2023)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs](https://mlsanity.com/paper/2411.09968/) (2024)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying](https://mlsanity.com/paper/2303.08524/) (2023)
- [Toward Sufficient Spatial-Frequency Interaction for Gradient-aware Underwater Image Enhancement](https://mlsanity.com/paper/2309.04089/) (2023)
- [Depth-aware Test-Time Training for Zero-shot Video Object Segmentation](https://mlsanity.com/paper/2403.04258/) (2024)
- [DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer](https://mlsanity.com/paper/2407.15130/) (2024)
- [SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images](https://mlsanity.com/paper/2302.08269/) (2023)
- [SiENet: Siamese Expansion Network for Image Extrapolation](https://mlsanity.com/paper/2007.03851/) (2020)
- [Underwater Image Restoration Through a Prior Guided Hybrid Sense Approach and Extensive Benchmark Analysis](https://mlsanity.com/paper/2501.02701/) (2025)
- [Image Fusion for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2502.15694/) (2024)
- [A Wavelet-based Dual-stream Network for Underwater Image Enhancement](https://mlsanity.com/paper/2202.08758/) (2022)
- [A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement](https://mlsanity.com/paper/2308.05447/) (2023)
- [Prompt Categories Cluster for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.13823/) (2024)
- [Image Augmentation Agent for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.20439/) (2024)
- [SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2409.00346/) (2024)
- [MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2507.09184/) (2025)
- [Test-Time Intensity Consistency Adaptation for Shadow Detection](https://mlsanity.com/paper/2410.07695/) (2024)
- [Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2310.09828/) (2023)
- [UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer](https://mlsanity.com/paper/2310.20210/) (2023)
- [ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training](https://mlsanity.com/paper/2410.04032/) (2024)

## Abstract (arXiv)

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.