Image Style Transfer

Ask about this topic

Overview

Image style transfer studies how to change an image’s appearance—such as its brushwork, color, texture, or makeup—while retaining important content like objects, faces, and layout. Methods range from feed-forward neural networks and color transforms to pretrained diffusion models controlled through attention, feature alignment, adapters, masks, or optimization. Current work emphasizes fine-grained regional control, multiple style references, and applications such as video, 3D scenes, and medical imaging. A central challenge is balancing faithful style matching with content preservation and limited semantic leakage, while evaluation metrics still do not fully capture human judgments of artistic similarity.

Latest papers

CardsList

61 papers9 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

May 22, 2025

CDST: Color Disentangled Style Transfer for Universal Style Reference Customization

We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm which completely isolates color from style and forces the style stream to be color-blinded. With one same model, CDST unlocks universal style transfer capabilities in a tuning-free manner during inference. Especially, the characteristics-preserved style transfer with style and content references is solved in the tuning-free way for the first time. CDST significantly improves the style similarity by multi-feature image embeddings compression and preserves strong editing capability via our new CDST style definition inspired by Diffusion UNet disentanglement law. By conducting thorough qualitative and quantitative experiments and human evaluations, we demonstrate that CDST achieves state-of-the-art results on various style transfer tasks.

Shiwen Zhang, Zhuowei Chen, Lang Chen +1

ByteDance

Disentangled Representation LearningImage Style Transfer
AskPDF