RetouchLLM：基于视觉语言模型的无训练代码图像修饰
RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models
AI总结：
提出无训练白盒图像修饰系统RetouchLLM，通过视觉批评器与代码生成器实现可解释、可控的代码化修饰，泛化于多种风格。
摘要：
图像修饰不仅能提升视觉质量，还能作为表达个人偏好和情感的手段。然而，现有的基于学习的方法需要大规模配对数据，且作为黑盒运行，使得修饰过程不透明，并限制了其适应多样化、用户或图像特定调整的能力。在这项工作中，我们提出了RetouchLLM，一个无训练的白色盒图像修饰系统，它不需要训练数据，并直接在高质量图像上执行可解释的、基于代码的修饰。我们的框架以类似于人类进行多步修饰的方式逐步增强图像，允许探索多样化的调整路径。它包含两个主要模块：一个视觉批评器，用于识别输入图像与参考图像之间的差异，以及一个代码生成器，用于生成可执行的代码。实验表明，我们的方法在多种修饰风格上具有良好的泛化能力，而基于自然语言的用户交互使得可解释且可控的调整能够适应用户意图。
英文摘要：
Image retouching not only enhances visual quality but also serves as a means of expressing personal preferences and emotions. However, existing learning-based approaches require large-scale paired data and operate as black boxes, making the retouching process opaque and limiting their adaptability to handle diverse, user- or image-specific adjustments. In this work, we propose RetouchLLM, a training-free white-box image retouching system, which requires no training data and performs interpretable, code-based retouching directly on high-resolution images. Our framework progressively enhances the image in a manner similar to how humans perform multi-step retouching, allowing exploration of diverse adjustment paths. It comprises of two main modules: a visual critic that identifies differences between the input and reference images, and a code generator that produces executable codes. Experiments demonstrate that our approach generalizes well across diverse retouching styles, while natural language-based user interaction enables interpretable and controllable adjustments tailored to user intent.
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。
