SA-LUT: 用于真实感风格迁移的空间自适应四维查找表
SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
AI总结：
针对现有真实感风格迁移方法在内容完整性、效率与局部自适应能力间难以平衡的问题，提出结合LUT效率与神经网络自适应能力的SA-LUT方法，还推出首个专用PST评估基准PST50，实验证明其性能优于现有最优方法且能保持实时处理速度。
摘要：
真实感风格迁移（PST）通过适配参考图像的色彩同时保留内容结构，可实现现实场景中的调色工作。现有方法主要分为两类：一类是基于生成的方法，这类方法以内容完整性和效率为代价优先保障风格保真度；另一类是如LUT（查找表）这类全局色彩变换方法，这类方法能保留结构但缺乏局部自适应能力。为弥补这一缺陷，我们提出空间自适应四维查找表（SA-LUT），将LUT的高效性与神经网络的自适应能力相结合。SA-LUT包含两大核心模块：（1）风格引导的4D LUT生成器，该模块从风格图像中提取多尺度特征以预测4D LUT；（2）上下文生成器，其采用内容-风格交叉注意力机制生成上下文图。该上下文图可实现空间自适应调整，使我们的4D LUT在保留结构完整性的同时执行精准的色彩变换。为建立严谨的真实感风格迁移评估框架，我们推出PST50，这是首个专门为PST评估设计的基准数据集。实验表明，SA-LUT的性能大幅优于当前最优方法，与3D LUT方法相比，其LPIPS得分降低了66.7%，同时在视频风格化任务中可保持16 FPS的实时性能。我们的代码和基准数据集可在https://github.com/Ry3nG/SA-LUT获取。
英文摘要：
Photorealistic style transfer (PST) enables real-world color grading by adapting reference image colors while preserving content structure. Existing methods mainly follow either approaches: generation-based methods that prioritize stylistic fidelity at the cost of content integrity and efficiency, or global color transformation methods such as LUT, which preserve structure but lack local adaptability. To bridge this gap, we propose Spatial Adaptive 4D Look-Up Table (SA-LUT), combining LUT efficiency with neural network adaptability. SA-LUT features: (1) a Style-guided 4D LUT Generator that extracts multi-scale features from the style image to predict a 4D LUT, and (2) a Context Generator using content-style cross-attention to produce a context map. This context map enables spatially-adaptive adjustments, allowing our 4D LUT to apply precise color transformations while preserving structural integrity. To establish a rigorous evaluation framework for photorealistic style transfer, we introduce PST50, the first benchmark specifically designed for PST assessment. Experiments demonstrate that SA-LUT substantially outperforms state-of-the-art methods, achieving a 66.7% reduction in LPIPS score compared to 3D LUT approaches, while maintaining real-time performance at 16 FPS for video stylization. Our code and benchmark are available at https://github.com/Ry3nG/SA-LUT
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。
