Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars

Eric Ming Chen, Di Liu, Sizhuo Ma, Michael Vasilkovsky, Bing Zhou, Qiang Gao, Wenzhou Wang, Jiahao Luo, Dimitris N. Metaxas, Vincent Sitzmann, Jian Wang; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026, pp. 1948-1958

Abstract

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Eric Ming and Liu, Di and Ma, Sizhuo and Vasilkovsky, Michael and Zhou, Bing and Gao, Qiang and Wang, Wenzhou and Luo, Jiahao and Metaxas, Dimitris N. and Sitzmann, Vincent and Wang, Jian}, title = {Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1948-1958} }