{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/styleavatar3d-leveraging-image-text-diffusion","title":"StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation","arxiv_id":"2305.19012","date":"2023-05-30","proceeding":null,"authors":["Chi Zhang","YiWen Chen","Yijun Fu","Zhenglin Zhou","Gang Yu","Billzb Wang","Bin Fu","Tao Chen","Guosheng Lin","Chunhua Shen"],"abstract":"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 address the misalignment between poses and images in data, we investigate view-specific prompts and develop a coarse-to-fine discriminator for GAN training. We also delve into attribute-related prompts to increase the diversity of the generated avatars. Additionally, we develop a latent diffusion model within the style space of StyleGAN to enable the generation of avatars based on image inputs. Our approach demonstrates superior performance over current state-of-the-art methods in terms of visual quality and diversity of the produced avatars.","url_abs":"https://arxiv.org/abs/2305.19012v2","url_pdf":"https://arxiv.org/pdf/2305.19012v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"styleavatar3d-leveraging-image-text-diffusion","repo_url":"https://github.com/icoz69/styleavatar3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"styleavatar3d-leveraging-image-text-diffusion","repo_url":"https://github.com/icoz69/stablellava","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"},{"method_slug":"stylegan","method_name":"StyleGAN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.19012","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}