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.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementStyle TransferMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Understanding Generalized Whitening and Coloring Transform for Universal Style Transfer
Style transfer is a task of rendering images in the styles of other images. In the past few years, neural style transfer has achieved a great success in this task, yet suffers from either the inability to generalize to u…
Style TransferUniversal Photorealistic Style Transfer: A Lightweight and Adaptive Approach
Photorealistic style transfer aims to apply stylization while preserving the realism and structure of input content. However, existing methods often encounter challenges such as color tone distortions, dependency on pair…
GPUStyle TransferSuper-ResolutionVideo Style TransferUniversal Style Transfer via Feature Transforms
Universal style transfer aims to transfer arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen…
Image ReconstructionStyle TransferAdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer
Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have …
4kGPUStyle TransferCLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
Gaussian Splatting (GS) has recently emerged as an efficient representation for rendering 3D scenes from 2D images and has been extended to images, videos, and dynamic 4D content. However, applying style transfer to GS-b…
Style Transfer