用专家混合模型实现多层级图像风格化，保留材质与语义细节
Mixture of Style Experts for Diverse Image Stylization
- 基于门控机制动态分配风格到专用专家，支持多级语义风格
- 在内容-风格-生成三元组数据集上训练，提升未见风格泛化能力
- 适合需要高质量、多样化风格迁移的图像生成任务
基于扩散模型的风格化技术虽有进展，但现有方法多局限于色彩变换，忽视复杂语义与材质细节。本文提出StyleExpert，一种基于专家混合（MoE）的语义感知框架。该框架采用统一风格编码器，在自建的大规模内容-风格-生成三元组数据集上训练，将多样风格嵌入一致的潜在空间。该嵌入用于条件化相似性感知的门控机制，动态将风格路由至MoE架构中的专用专家。借助此架构，方法能有效处理从浅层纹理到深层语义的多层级风格。大量实验表明，StyleExpert在保持语义和材质细节方面优于现有方法，且可泛化至未见风格。代码与数据集已公开于项目主页：https://hh-lg.github.io/StyleExpert-Page/。
原文摘要 · Abstract (English)
Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。