StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
Published in IEEE Journal of Selected Topics in Signal Processing (J-STSP), 2026
This paper presents StyleAvatar3D, a method for generating high-quality, stylized 3D avatars that utilizes pre-trained image-text diffusion models for data generation and a GAN-based 3D generation network for training.
Recommended citation: C Zhang, Y Chen, Y Fu, W Cheng, Z Zhou, W Jiang, Z Wang, B Fu, T Chen, G Yu, G Lin, C Song. (2026). "StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation." IEEE J-STSP.
Download Paper