MienCap: Realtime Performance-Based Facial Animation with Live Mood Dynamics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pan, Ye, Zhang, Ruisi, Wang, Jingying, Chen, Nengfu, Qiu, Yilin, Ding, Yu, Mitchell, Kenny
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909725366419456
author Pan, Ye
Zhang, Ruisi
Wang, Jingying
Chen, Nengfu
Qiu, Yilin
Ding, Yu
Mitchell, Kenny
author_facet Pan, Ye
Zhang, Ruisi
Wang, Jingying
Chen, Nengfu
Qiu, Yilin
Ding, Yu
Mitchell, Kenny
contents Our purpose is to improve performance-based animation which can drive believable 3D stylized characters that are truly perceptual. By combining traditional blendshape animation techniques with multiple machine learning models, we present both non-real time and real time solutions which drive character expressions in a geometrically consistent and perceptually valid way. For the non-real time system, we propose a 3D emotion transfer network makes use of a 2D human image to generate a stylized 3D rig parameters. For the real time system, we propose a blendshape adaption network which generates the character rig parameter motions with geometric consistency and temporally stability. We demonstrate the effectiveness of our system by comparing to a commercial product Faceware. Results reveal that ratings of the recognition, intensity, and attractiveness of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the animation pipeline, and provide animators with a system for creating the expressions they wish to use more quickly and accurately.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MienCap: Realtime Performance-Based Facial Animation with Live Mood Dynamics
Pan, Ye
Zhang, Ruisi
Wang, Jingying
Chen, Nengfu
Qiu, Yilin
Ding, Yu
Mitchell, Kenny
Graphics
Computer Vision and Pattern Recognition
I.3.2; I.4.10
Our purpose is to improve performance-based animation which can drive believable 3D stylized characters that are truly perceptual. By combining traditional blendshape animation techniques with multiple machine learning models, we present both non-real time and real time solutions which drive character expressions in a geometrically consistent and perceptually valid way. For the non-real time system, we propose a 3D emotion transfer network makes use of a 2D human image to generate a stylized 3D rig parameters. For the real time system, we propose a blendshape adaption network which generates the character rig parameter motions with geometric consistency and temporally stability. We demonstrate the effectiveness of our system by comparing to a commercial product Faceware. Results reveal that ratings of the recognition, intensity, and attractiveness of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the animation pipeline, and provide animators with a system for creating the expressions they wish to use more quickly and accurately.
title MienCap: Realtime Performance-Based Facial Animation with Live Mood Dynamics
topic Graphics
Computer Vision and Pattern Recognition
I.3.2; I.4.10
url https://arxiv.org/abs/2508.04687