Research map / Image generation / Editing and style transfer
PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching
Zewei Chang, Zheng-Peng Duan, Jianxing Zhang, Chun-Le Guo, Siyu Liu, Hyungju Chun, Hyunhee Park, Zikun Liu, Chongyi Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use PerTouch instead of DiffRetouch | image retouching · FiveK expert A | PSNR: 24.5082 -> 25.1430 | Improved |
| use PerTouch instead of DiffRetouch | image retouching · FiveK expert D | PSNR: 24.5087 -> 25.9726 | Improved |
| use PerTouch instead of DiffRetouch | image retouching · FiveK expert C | LPIPS: 0.0684 -> 0.0844 | Hurt |
| use PerTouch instead of TSFlow | image retouching · FiveK expert B | PSNR: 25.2474 -> 27.4733 | Improved |
| add semantic replacement module during training (ablation) | PerTouch · qualitative local retouching | region control | Improved |
| add parameter perturbation (channel shift, blur) during training (ablation) | PerTouch · qualitative user-guided edits | global visual coherence | Improved |
| add feedback-driven rethinking and scene-aware memory in the VLM agent | PerTouch agent · user instructions | alignment with user intent | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DiffRetouch — DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts (AAAI 2025) · better on 6 of 10 shared results
- StarEnhancer — StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement (ICCV 2021) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward (CVPR 2026 · similarity 0.89)
- JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent (NeurIPS 2025 · similarity 0.88)
- Guiding Instruction-based Image Editing via Multimodal Large Language Models (ICLR 2024 · similarity 0.85)
- RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers (NeurIPS 2025 · similarity 0.85)
- MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation (AAAI 2026 · similarity 0.85)
- DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
