# Real-Time Underwater Image Enhancement via Frequency-Guided Dual-Path Attention

arXiv: https://arxiv.org/abs/2606.30314 · HTML: https://mlsanity.com/paper/2606.30314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [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)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [Toward Sufficient Spatial-Frequency Interaction for Gradient-aware Underwater Image Enhancement](https://mlsanity.com/paper/2309.04089/) (2023)
- [NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results](https://mlsanity.com/paper/2404.14248/) (2024)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices](https://mlsanity.com/paper/2507.04277/) (2025)
- [AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?](https://mlsanity.com/paper/2602.20664/) (2026)
- [IGDNet: Zero-Shot Robust Underexposed Image Enhancement via Illumination-Guided and Denoising](https://mlsanity.com/paper/2507.02445/) (2025)
- [A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior](https://mlsanity.com/paper/2405.16197/) (2024)
- [NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results](https://mlsanity.com/paper/2510.13670/) (2025)
- [AquaDiff: Diffusion-Based Underwater Image Enhancement for Addressing Color Distortion](https://mlsanity.com/paper/2512.14760/) (2025)
- [Revisiting Lightweight Low-Light Image Enhancement: From a YUV Color Space Perspective](https://mlsanity.com/paper/2601.17349/) (2026)

## Abstract (arXiv)

Real-time underwater image enhancement (UIE) is crucial for mobile underwater photography and autonomous robotic systems, where practical deployment typically requires low latency and compact models under constrained computational resources. Recent ultra-lightweight CNNs based on structural re-parameterization meet these constraints but operate purely in the spatial domain, ignoring the frequency-sensitive nature of underwater degradation. To address this, we propose a lightweight UIE framework that integrates two key components: a Multi-Branch Reparameterizable Convolution with Fixed DCT Priors (MBRConv-DCT) that injects structured directional frequency priors during training, and a Frequency-Guided Dual-Path Attention (FGDPA) module that fuses spatial and spectral cues via a dual-path design for adaptive feature modulation. Both components are fully compatible with structural re-parameterization: the convolution branch introduces zero additional inference cost after re-parameterization, while the attention module incurs only a minimal computational overhead. Experiments show our model achieves state-of-the-art performance with only 4.23K parameters and 600+ FPS, outperforming much larger methods in both quantitative metrics and visual quality. Code is available at https://github.com/LethyZhang/FGDPA.