无需训练，用代码实现可解释的图像润色，像人一样分步调整。
RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models
- 通过视觉评鉴与代码生成双模块，实现无训练的代码化润色
- 支持高分辨率图像处理，能适配多种润色风格
- 用户可用自然语言控制，操作透明可追溯
图像润色不仅能提升视觉质量，还能表达个人偏好与情感。然而，现有基于学习的方法依赖大规模成对数据，且为黑箱模型，过程不透明，难以适应多样化、用户或图像特定的调整需求。本文提出RetouchLLM，一种无需训练的白盒图像润色系统，直接在高分辨率图像上进行可解释的代码化润色。该框架采用渐进式增强策略，模拟人类多步润色过程，支持探索多样调整路径。其核心包含两个模块：视觉评鉴器用于识别输入图与参考图之间的差异，代码生成器则输出可执行代码。实验表明，该方法在多种润色风格间具有良好的泛化能力，结合自然语言交互，可实现符合用户意图的可解释、可控调整。
原文摘要 · Abstract (English)
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.
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。