CDST: Color Disentangled Style Transfer for Universal Style Reference Customization

• URL: http://arxiv.org/abs/2506.13770v1
• Date: Thu, 22 May 2025 18:44:48 GMT
• Title: CDST: Color Disentangled Style Transfer for Universal Style Reference Customization
• Authors: Shiwen Zhang, Zhuowei Chen, Lang Chen, Yanze Wu,
• Abstract summary: We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm.<n>With one same model, CDST unlocks universal style transfer capabilities in a tuning-free manner during inference.
• Score: 5.5422947587598035
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Inversion-Free Style Transfer with Dual Rectified Flows [57.02757226679549]
  We propose a novel textitinversion-free style transfer framework based on dual rectified flows.<n>Our approach predicts content and style trajectories in parallel, then fuses them through a dynamic midpoint.<n>Experiments demonstrate generalization across diverse styles and content, providing an effective and efficient pipeline for style transfer.
  arXiv  Detail & Related papers  (2025-11-26T02:28:51Z)
• AStF: Motion Style Transfer via Adaptive Statistics Fusor [58.660938790014455]
  We propose a novel Adaptive Statistics Fusor (AStF) which consists of Style Distemporalment Module (SDM) and High-Order Multi-Statistics Attention (HO-SAttn)<n> Experimental results show that, by providing a more comprehensive model, our proposed AStF shows proficiency in motion style over state-of-the-arts techniques.
  arXiv  Detail & Related papers  (2025-11-06T08:51:24Z)
• Pluggable Style Representation Learning for Multi-Style Transfer [41.09041735653436]
  We develop a style transfer framework by decoupling the style modeling and transferring.<n>For style modeling, we propose a style representation learning scheme to encode the style information into a compact representation.<n>For style transferring, we develop a style-aware multi-style transfer network (SaMST) to adapt to diverse styles using pluggable style representations.
  arXiv  Detail & Related papers  (2025-03-26T09:44:40Z)
• Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridging [5.501345898413532]
  We introduce Trajectory Reset Attention Control (TRAC), a novel method that allows for high-quality style transfer.<n>TRAC operates by resetting the denoising trajectory and enforcing attention control, thus enhancing content consistency.<n>We present a tuning-free framework that offers a stable, flexible, and efficient solution for both image and video style transfer.
  arXiv  Detail & Related papers  (2025-03-10T14:18:43Z)
• UniVST: A Unified Framework for Training-free Localized Video Style Transfer [102.52552893495475]
  This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models.<n>It operates without the need for training, offering a distinct advantage over existing diffusion methods that transfer style across entire videos.
  arXiv  Detail & Related papers  (2024-10-26T05:28:02Z)
• STEER: Unified Style Transfer with Expert Reinforcement [71.3995732115262]
  STEER: Unified Style Transfer with Expert Reinforcement, is a unified frame-work developed to overcome the challenge of limited parallel data for style transfer. We show STEER is robust, maintaining its style transfer capabilities on out-of-domain data, and surpassing nearly all baselines across various styles.
  arXiv  Detail & Related papers  (2023-11-13T09:02:30Z)
• Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer [83.1333306079676]
  In this paper, we devise a novel Transformer model termed as emphMaster specifically for style transfer. In the proposed model, different Transformer layers share a common group of parameters, which (1) reduces the total number of parameters, (2) leads to more robust training convergence, and (3) is readily to control the degree of stylization. Experiments demonstrate the superiority of Master under both zero-shot and few-shot style transfer settings.
  arXiv  Detail & Related papers  (2023-04-24T04:46:39Z)
• A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning [84.8813842101747]
  Unified Contrastive Arbitrary Style Transfer (UCAST) is a novel style representation learning and transfer framework. We present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components, i.e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer.
  arXiv  Detail & Related papers  (2023-03-09T04:35:00Z)
• StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning [89.86971464234533]
  Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. We propose a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method. Our method is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets.
  arXiv  Detail & Related papers  (2023-02-18T11:54:37Z)
• CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer [58.020470877242865]
  We devise a universally versatile style transfer method capable of performing artistic, photo-realistic, and video style transfer jointly. We make a mild and reasonable assumption that global inconsistency is dominated by local inconsistencies and devise a generic Contrastive Coherence Preserving Loss (CCPL) applied to local patches. CCPL can preserve the coherence of the content source during style transfer without degrading stylization.
  arXiv  Detail & Related papers  (2022-07-11T12:09:41Z)
• Multiple Style Transfer via Variational AutoEncoder [16.797476504327665]
  We propose ST-VAE, a Variational AutoEncoder for latent space-based style transfer. It performs multiple style transfer by projecting nonlinear styles to a linear latent space, enabling to merge styles via linear before transferring the new style to the content image.
  arXiv  Detail & Related papers  (2021-10-13T06:47:13Z)
• DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer [29.20616177457981]
  The paper proposes a Dynamic ResBlock Generative Adversarial Network (DRB-GAN) for artistic style transfer. Our proposed DRB-GAN outperforms state-of-the-art methods and exhibits its superior performance in terms of visual quality and efficiency.
  arXiv  Detail & Related papers  (2021-08-17T00:02:19Z)
• Arbitrary Style Transfer via Multi-Adaptation Network [109.6765099732799]
  A desired style transfer, given a content image and referenced style painting, would render the content image with the color tone and vivid stroke patterns of the style painting. A new disentanglement loss function enables our network to extract main style patterns and exact content structures to adapt to various input images.
  arXiv  Detail & Related papers  (2020-05-27T08:00:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.