StyleDiffusion：通过扩散模型实现可控的解耦风格迁移
StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models
AI总结：
本文提出 StyleDiffusion 框架，结合 CLIP 风格解耦损失、风格重建先验与扩散模型，实现可解释、可控且效果优于现有方法的内容-风格解耦风格迁移。
摘要：
内容与风格（C-S）解耦是风格迁移的一个基础问题和关键挑战。现有基于显式定义（如 Gram matrix）或隐式学习（如 GAN）的方法既缺乏可解释性，也不易控制，导致表征相互纠缠，结果不够理想。本文提出一种新的用于风格迁移的 C-S 解耦框架，无需依赖以往假设。其核心思想是显式提取内容信息，并隐式学习互补的风格信息，从而实现可解释、可控的 C-S 解耦与风格迁移。我们引入了一种简单而有效的基于 CLIP 的风格解耦损失，并与风格重建先验协同，在 CLIP 图像空间中对 C-S 进行解耦。通过进一步利用扩散模型强大的风格去除和生成能力，我们的框架取得了优于当前最先进方法的结果，并实现灵活的 C-S 解耦和权衡控制。本工作为风格迁移中的 C-S 解耦提供了新的见解，并展示了扩散模型在学习良好解耦的内容与风格特征方面的潜力。
英文摘要：
Content and style (C-S) disentanglement is a fundamental problem and critical challenge of style transfer. Existing approaches based on explicit definitions (e.g., Gram matrix) or implicit learning (e.g., GANs) are neither interpretable nor easy to control, resulting in entangled representations and less satisfying results. In this paper, we propose a new C-S disentangled framework for style transfer without using previous assumptions. The key insight is to explicitly extract the content information and implicitly learn the complementary style information, yielding interpretable and controllable C-S disentanglement and style transfer. A simple yet effective CLIP-based style disentanglement loss coordinated with a style reconstruction prior is introduced to disentangle C-S in the CLIP image space. By further leveraging the powerful style removal and generative ability of diffusion models, our framework achieves superior results than state of the art and flexible C-S disentanglement and trade-off control. Our work provides new insights into the C-S disentanglement in style transfer and demonstrates the potential of diffusion models for learning well-disentangled C-S characteristics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
