Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Eric M., Liu, Di, Ma, Sizhuo, Vasilkovsky, Michael, Zhou, Bing, Gao, Qiang, Wang, Wenzhou, Luo, Jiahao, Metaxas, Dimitris N., Sitzmann, Vincent, Wang, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914376849555456
author Chen, Eric M.
Liu, Di
Ma, Sizhuo
Vasilkovsky, Michael
Zhou, Bing
Gao, Qiang
Wang, Wenzhou
Luo, Jiahao
Metaxas, Dimitris N.
Sitzmann, Vincent
Wang, Jian
author_facet Chen, Eric M.
Liu, Di
Ma, Sizhuo
Vasilkovsky, Michael
Zhou, Bing
Gao, Qiang
Wang, Wenzhou
Luo, Jiahao
Metaxas, Dimitris N.
Sitzmann, Vincent
Wang, Jian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11978
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
Chen, Eric M.
Liu, Di
Ma, Sizhuo
Vasilkovsky, Michael
Zhou, Bing
Gao, Qiang
Wang, Wenzhou
Luo, Jiahao
Metaxas, Dimitris N.
Sitzmann, Vincent
Wang, Jian
Graphics
Computer Vision and Pattern Recognition
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.
title Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.11978