.png){kind=icon}
.png){kind=icon}
Return
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
.png){kind=icon}
PRE
AI
C
Y
Y
W
Z
W
Z
B
G
G
C
DOI：10.1109/JSTSP.2026.3662496.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models. Nevertheless, the limited availability of diverse 3D resources presents significant challenges to learning. In this paper, we present a novel method for generating high-quality, stylized 3D avatars that utilizes pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training. Our method leverages the comprehensive priors of appearance and geometry offered by image-text diffusion models to generate multi-view images of avatars in various styles. During data generation, we employ poses extracted from existing 3D models to guide the generation of multi-view images. To handle inaccurate pose annotations of stylized images, we investigate view-specific prompts and develop a coarse-to-fine discriminator for GAN training. Additionally, we develop a latent diffusion model within the style space of StyleGAN to enable the generation of avatars based on image or text inputs. Our approach demonstrates superior performance over current state-of-the-art methods in terms of visual quality and diversity of the produced avatars.
Keywords:
3D avatar generation
diffusion models
stylized multi-view synthesis
Journal
IF:
13.7
Papers:
1.9K
Citations:
1.1W
Organization
Cited Papers