用几何感知扩散模型提升水下光场成像质量
Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process
- 基于光场空间角度结构，设计几何引导的扩散框架
- 在多个水下数据集上显著改善色彩失真，优于现有方法
- 适合需要高保真水下图像的科研与海洋探测应用
本文研究通过4维光场（LF）成像获取高质量水下图像的挑战性问题。为此，我们提出GeoDiff-LF，一种基于SD-Turbo的新型扩散框架，利用光场的空间-角度结构增强水下4维光场成像。GeoDiff-LF包含三项关键改进：(1) 采用带卷积与注意力适配器的修改版U-Net架构以建模几何线索；(2) 设计几何引导损失函数，结合张量分解与渐进加权以正则化全局结构；(3) 优化采样策略并引入噪声预测以提升效率。通过融合扩散先验与光场几何特性，GeoDiff-LF有效缓解了水下场景中的色彩失真。大量实验表明，该框架在视觉保真度与定量指标上均超越现有方法，推动了水下成像增强技术的最新进展。代码将公开于https://github.com/linlos1234/GeoDiff-LF。
原文摘要 · Abstract (English)
This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end, we propose GeoDiff-LF, a novel diffusion-based framework built upon SD-Turbo to enhance underwater 4-D LF imaging by leveraging its spatial-angular structure. GeoDiff-LF consists of three key adaptations: (1) a modified U-Net architecture with convolutional and attention adapters to model geometric cues, (2) a geometry-guided loss function using tensor decomposition and progressive weighting to regularize global structure, and (3) an optimized sampling strategy with noise prediction to improve efficiency. By integrating diffusion priors and LF geometry, GeoDiff-LF effectively mitigates color distortion in underwater scenes. Extensive experiments demonstrate that our framework outperforms existing methods across both visual fidelity and quantitative performance, advancing the state-of-the-art in enhancing underwater imaging. The code will be publicly available at https://github.com/linlos1234/GeoDiff-LF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。