UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis
- 21 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 51 (2) , 1574-1591
Abstract
The concept of “waterbody style” transfer remains largely unexplored in the underwater imaging literature. Traditional image style transfer (STx) methods emphasize artistic and photorealistic blending that fails to preserve geometry in high-scattering underwater environments. The wavelength-dependent attenuation and depth-dependent backscattering of underwater optics further complicate STx learning from unpaired data. We introduce UStyle, the first data-driven framework for transferring waterbody styles across underwater images without needing reference images or explicit scene information. We propose a novel depth-aware whitening and coloring transform that incorporates physics-based waterbody synthesis for perceptually consistent stylization while preserving scene structure. We also integrate carefully designed loss functions to maintain color, lightness, structural integrity, frequency-domain features, and high-level content in VGG and CLIP spaces. Comprehensive experimental analyses show that UStyle surpasses state-of-the-art methods that rely solely on reconstruction loss. In addition, we present the UF7D data set, a curated benchmark of high-resolution underwater images across seven waterbody styles.Keywords
All Related Versions
Funding Information
- National Science Foundation (2330416)
- University of Florida (132763)
This publication has 115 references indexed in Scilit:
- GAN‐Based Multi‐Decomposition Photo CartoonizationComputer Animation and Virtual Worlds, 2024
- Language-Driven Artistic Style Transfer2022
- ResNet 502021
- Deformable Style Transfer2020
- RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering2020
- Fusion and Enhancement Techniques for Processing of Multispectral Images2019
- Multi-style Generative Network for Real-Time Transfer2019
- A Closed-Form Solution to Photorealistic Image Stylization2018
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- Microsoft COCO: Common Objects in Context2014