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

ArXiv CS.CV2026-06-30PAPERen作者: Leshen Zhang, Ao Li, Ce Zhu

详细信息

来源站点
ArXiv CS.CV
作者
Leshen Zhang, Ao Li, Ce Zhu
文章类型
PAPER
语言
en
发布日期
2026-06-30

摘要

arXiv:2606.30314v1 Announce Type: new Abstract: 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.