UStyle: 通过深度引导的特征合成实现水体风格迁移
UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis
AI总结：
UStyle通过深度引导的特征合成实现水下图像水体风格迁移，无需参考图像，整合物理水体合成以保持结构和感知一致性，引入UF7D数据集提升迁移质量。
摘要：
水体风格迁移的概念在水下成像和视觉文献中仍鲜有探索。传统图像风格迁移（STx）方法主要关注艺术和写实风格的混合，往往无法在高散射介质（如水下）中保留物体和场景的几何结构。波长相关的非线性衰减和深度相关的后向散射伪影进一步复杂了从未配对数据中学习水下图像STx。本文介绍了UStyle，这是首个数据驱动的学习框架，用于在水下图像之间迁移水体风格，而无需先前参考图像或场景信息。我们提出了一种新颖的深度感知白化和着色变换（DA-WCT）机制，该机制整合了基于物理的水体合成，以确保在保持场景结构的同时实现感知一致的风格化。为了提高风格迁移质量，我们引入了精心设计的损失函数，引导UStyle保持色彩丰富性、明度、结构完整性、频域特征以及VGG和CLIP（对比语言-图像预训练）特征空间中的高层内容。通过解决领域特定的挑战，UStyle提供了一个稳健的无参考水下图像STx框架，超越了仅依赖端到端重建损失的最先进（SOTA）方法。此外，我们引入了UF7D数据集，这是一个精心编纂的高分辨率水下图像集合，涵盖七种不同的水体风格，建立了基准以支持未来水下图像STx的研究。UStyle推理流程和UF7D数据集已发布在：https://github.com/uf-robopi/UStyle。
英文摘要：
The concept of waterbody style transfer remains largely unexplored in the underwater imaging and vision literature. Traditional image style transfer (STx) methods primarily focus on artistic and photorealistic blending, often failing to preserve object and scene geometry in images captured in high-scattering mediums such as underwater. The wavelength-dependent nonlinear attenuation and depth-dependent backscattering artifacts further complicate learning underwater image STx from unpaired data. This paper introduces UStyle, the first data-driven learning framework for transferring waterbody styles across underwater images without requiring prior reference images or scene information. We propose a novel depth-aware whitening and coloring transform (DA-WCT) mechanism that integrates physics-based waterbody synthesis to ensure perceptually consistent stylization while preserving scene structure. To enhance style transfer quality, we incorporate carefully designed loss functions that guide UStyle to maintain colorfulness, lightness, structural integrity, and frequency-domain characteristics, as well as high-level content in VGG and CLIP (contrastive language-image pretraining) feature spaces. By addressing domain-specific challenges, UStyle provides a robust framework for no-reference underwater image STx, surpassing state-of-the-art (SOTA) methods that rely solely on end-to-end reconstruction loss. Furthermore, we introduce the UF7D dataset, a curated collection of high-resolution underwater images spanning seven distinct waterbody styles, establishing a benchmark to support future research in underwater image STx. The UStyle inference pipeline and UF7D dataset are released at: https://github.com/uf-robopi/UStyle.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
