InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning Using an Asymmetric Auto-Encoder
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908840574844928 |
|---|---|
| author | Weldengus, Temesgen Muruts Liu, Binnan Kou, Fei Lyu, Youwei Chen, Jinwei Fan, Qingnan Zou, Changqing |
| author_facet | Weldengus, Temesgen Muruts Liu, Binnan Kou, Fei Lyu, Youwei Chen, Jinwei Fan, Qingnan Zou, Changqing |
| contents | Personalized image retouching aims to adapt retouching style of individual users from reference examples, but existing methods often require user-specific fine-tuning or fail to generalize effectively. To address these challenges, we introduce $\textbf{InstantRetouch}$, a general framework for personalized image retouching that instantly adapts to user retouching styles without any test-time fine-tuning. It employs an $\textit{asymmetric auto-encoder}$ to encode the retouching style from paired examples into a content disentangled latent representation that enables faithful transfer of the retouching style to new images. To adaptively apply the encoded retouching style to new images, we further propose $\textit{retrieval-augmented retouching}$ (RAR), which retrieves and aggregates style latents from reference pairs most similar in content to the query image. With these components, $\textbf{InstantRetouch}$ enables superior and generic content-aware retouching personalization across diverse scenarios, including single-reference, multi-reference, and mixed-style setups, while also generalizing out of the box to photorealistic style transfer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17044 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning Using an Asymmetric Auto-Encoder Weldengus, Temesgen Muruts Liu, Binnan Kou, Fei Lyu, Youwei Chen, Jinwei Fan, Qingnan Zou, Changqing Graphics Personalized image retouching aims to adapt retouching style of individual users from reference examples, but existing methods often require user-specific fine-tuning or fail to generalize effectively. To address these challenges, we introduce $\textbf{InstantRetouch}$, a general framework for personalized image retouching that instantly adapts to user retouching styles without any test-time fine-tuning. It employs an $\textit{asymmetric auto-encoder}$ to encode the retouching style from paired examples into a content disentangled latent representation that enables faithful transfer of the retouching style to new images. To adaptively apply the encoded retouching style to new images, we further propose $\textit{retrieval-augmented retouching}$ (RAR), which retrieves and aggregates style latents from reference pairs most similar in content to the query image. With these components, $\textbf{InstantRetouch}$ enables superior and generic content-aware retouching personalization across diverse scenarios, including single-reference, multi-reference, and mixed-style setups, while also generalizing out of the box to photorealistic style transfer. |
| title | InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning Using an Asymmetric Auto-Encoder |
| topic | Graphics |
| url | https://arxiv.org/abs/2602.17044 |