StyleMe3D: 通过多编码器在3D高斯上实现解耦先验的风格化
StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians
AI总结：
StyleMe3D通过多编码器在3D高斯上实现解耦先验的风格化，利用动态风格分数蒸馏和多模态对齐策略提升风格迁移效果。
摘要：
当前基于3D高斯点的风格化方法在表示多样艺术风格方面受限，常常默认低层次纹理替换或产生语义不一致的输出。在本文中，我们引入了StyleMe3D，一种新颖的分层框架，通过解耦多级风格表示并在保持几何保真度的同时实现全面、高保真的风格化。StyleMe3D的核心是动态风格分数蒸馏（DSSD），它利用具有风格意识的扩散模型的潜在先验来提供高层语义指导，确保稳健且富有表现力的风格迁移。为进一步完善这一蒸馏过程，我们提出了一种多模态对齐策略，利用CLIP潜在空间：一种基于CLIP的风格流评估器（对比风格描述符）强制中等层次的风格相似性，以及一种基于CLIP的内容流评估器（3D高斯质量评估）作为全局正则化器以缓解典型GS质量退化。最后，集成了一个基于VGG的同时优化尺度模块，用于在低层次上细化细粒度纹理细节。广泛的实验表明，我们的方法一致地保持了复杂的几何细节，并在整个场景中实现了连贯的风格效果，显著超越了最先进的基线在定性和定量评估中。
英文摘要：
Current 3D Gaussian Splatting stylization approaches are limited in their ability to represent diverse artistic styles, frequently defaulting to low-level texture replacement or yielding semantically inconsistent outputs. In this paper, we introduce StyleMe3D, a novel hierarchical framework that achieves comprehensive, high-fidelity stylization by disentangling multi-level style representations while preserving geometric fidelity. The cornerstone of StyleMe3D is Dynamic Style Score Distillation (DSSD), which harnesses latent priors from a style-aware diffusion model to provide high-level semantic guidance, ensuring robust and expressive style transfer. To further refine this distillation process, we propose a multi-modal alignment strategy using the CLIP latent space: a CLIP-based style stream evaluator (Contrastive Style Descriptor) that enforces middle-level stylistic similarity, and a CLIP-based content stream evaluator (3D Gaussian Quality Assessment) that acts as a global regularizer to mitigate typical GS quality degradation. Finally, a VGG-based Simultaneously Optimized Scale module is integrated to refine fine-grained texture details at the low-level. Extensive experiments demonstrate that our method consistently preserves intricate geometric details and achieves coherent stylistic effects across entire scenes, significantly surpassing state-of-the-art baselines in both qualitative and quantitative evaluations.
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。
