一键生成可动画的双风格3D虚拟形象，保留真人特征。
Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
- 用高斯域迁移技术将自拍转为默认风格形象
- 二次添加新风格（如毛线、玩具）仍保持身份一致
- 移动端动画帧率30-40FPS，适合即时使用
尽管Snapchat Bitmoji等虚拟形象系统日益流行，现有平台仍存在预设资产有限、定制过程繁琐、渲染效率低等问题。为此，我们提出Snapmoji，一个可即时生成3D虚拟形象的系统，并支持一种称为双风格化（dual-stylization）的定制流程。Snapmoji首先利用新型高斯域迁移（Gaussian Domain Adaptation, GDA）技术，将用户自拍映射为一种主风格形象（如Bitmoji风格），随后在该基础上叠加第二种风格（如骨架、毛线、玩具），同时保持用户身份特征不变。生成的3D形象可在移动端以30-40 FPS流畅动画渲染，适用于即时交互场景。
原文摘要 · Abstract (English)
Despite the increasing popularity of avatar systems such as Snapchat Bitmojis, existing production avatar platforms face several limitations, such as a limited number of predefined assets, tedious customization processes, and inefficient rendering requirements. Addressing these shortcomings, we introduce Snapmoji, an avatar generation system that instantly creates 3D avatars, and enables customization in a process we call dual-stylization. Snapmoji first maps a selfie of a user to a primary avatar (e.g., Bitmoji style) using a new technique we name Gaussian Domain Adaptation (GDA), then applies a secondary style (e.g., skeleton, yarn, toy) to the primary avatar, all while preserving the user's identity. The generated 3D avatars can then be rendered an animated on mobile devices at 30-40 FPS.
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。