{"ID":2858076,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08054","arxiv_id":"2510.08054","title":"RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models","abstract":"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.","short_abstract":"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, us...","url_abs":"https://arxiv.org/abs/2510.08054","url_pdf":"https://arxiv.org/pdf/2510.08054v2","authors":"[\"Moon Ye-Bin\",\"Roy Miles\",\"Tae-Hyun Oh\",\"Ismail Elezi\",\"Jiankang Deng\"]","published":"2025-10-09T10:40:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}