Emotion-controllable 3D talking face generation with hierarchical decoupling-guided VQ-VAE

Journal article

Peer reviewed

Sheng Chen, Qiang Sun and Xiatian Zhu

Zhongguo tu xiang tu xing xue bao, Vol.31(8), pp.3015-3029

2026

Abstract

3D face generation

emotionally controllable

feature quantization

Transformer

vector quantized variational autoencoders (VQ-VAE)

url

https://doi.org/10.11834/jig.250451View

Published (Version of record) Open

1 Record Views

Title: Emotion-controllable 3D talking face generation with hierarchical decoupling-guided VQ-VAE
Creators: Sheng Chen - Xi'an University of Technology
Qiang Sun - Xi'an University of Technology
Xiatian Zhu - The Surrey Institute for People-Centred Artificial Intelligence and the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom
Publication Details: Zhongguo tu xiang tu xing xue bao, Vol.31(8), pp.3015-3029
Publication Date: 2026
Identifiers: 991158418802346
Academic Unit: School of Computer Science & Electronic Engineering
Language: English
Resource Type: Journal article