RefRetouch: Personalized Image Retouching without Test-time Fine-tuning

Personalized image retouching aims to adapt retouching styles 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 RefRetouch, a general framework for personalized image retouching that instantly adapts to user retouching styles without any test-time fine-tuning. It employs an textitasymmetric 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 textitretrieval-augmented retouching (RAR), which retrieves and aggregates style latents from reference pairs most similar in content to the query image. With these components, RefRetouch enables superior and generic content-aware retouching personalization across diverse scenarios, including single-reference, multi-reference, and mixed-style settings, while also generalizing out of the box to photorealistic style transfer.