PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917153023721472 |
|---|---|
| author | Chang, Zewei Duan, Zheng-Peng Zhang, Jianxing Guo, Chun-Le Liu, Siyu Chun, Hyungju Park, Hyunhee Liu, Zikun Li, Chongyi |
| author_facet | Chang, Zewei Duan, Zheng-Peng Zhang, Jianxing Guo, Chun-Le Liu, Siyu Chun, Hyungju Park, Hyunhee Liu, Zikun Li, Chongyi |
| contents | Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivity, we propose a unified diffusion-based image retouching framework called PerTouch. Our method supports semantic-level image retouching while maintaining global aesthetics. Using parameter maps containing attribute values in specific semantic regions as input, PerTouch constructs an explicit parameter-to-image mapping for fine-grained image retouching. To improve semantic boundary perception, we introduce semantic replacement and parameter perturbation mechanisms during training. To connect natural language instructions with visual control, we develop a VLM-driven agent to handle both strong and weak user instructions. Equipped with mechanisms of feedback-driven rethinking and scene-aware memory, PerTouch better aligns with user intent and captures long-term preferences. Extensive experiments demonstrate each component's effectiveness and the superior performance of PerTouch in personalized image retouching. Code Pages: https://github.com/Auroral703/PerTouch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12998 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching Chang, Zewei Duan, Zheng-Peng Zhang, Jianxing Guo, Chun-Le Liu, Siyu Chun, Hyungju Park, Hyunhee Liu, Zikun Li, Chongyi Computer Vision and Pattern Recognition Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivity, we propose a unified diffusion-based image retouching framework called PerTouch. Our method supports semantic-level image retouching while maintaining global aesthetics. Using parameter maps containing attribute values in specific semantic regions as input, PerTouch constructs an explicit parameter-to-image mapping for fine-grained image retouching. To improve semantic boundary perception, we introduce semantic replacement and parameter perturbation mechanisms during training. To connect natural language instructions with visual control, we develop a VLM-driven agent to handle both strong and weak user instructions. Equipped with mechanisms of feedback-driven rethinking and scene-aware memory, PerTouch better aligns with user intent and captures long-term preferences. Extensive experiments demonstrate each component's effectiveness and the superior performance of PerTouch in personalized image retouching. Code Pages: https://github.com/Auroral703/PerTouch. |
| title | PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.12998 |