AvatarArtist：开放域4D化身生成系统

AvatarArtist: Open-Domain 4D Avatarization

March 25, 2025

作者: Hongyu Liu, Xuan Wang, Ziyu Wan, Yue Ma, Jingye Chen, Yanbo Fan, Yujun Shen, Yibing Song, Qifeng Chen

cs.AI

摘要

本研究聚焦于开放领域的4D虚拟化身生成，旨在从任意风格的肖像图像中创建4D虚拟化身。我们选择参数化三平面作为中间4D表示，并提出了一种结合生成对抗网络（GANs）与扩散模型的实用训练范式。这一设计源于我们观察到4D GANs在无监督条件下能有效连接图像与三平面，但在处理多样化数据分布时往往面临挑战。一个强大的2D扩散先验模型应运而生，协助GAN将其专业知识跨领域迁移。这两者的协同作用促成了多领域图像-三平面数据集的构建，进而推动了一个通用4D虚拟化身生成器的发展。大量实验表明，我们的模型AvatarArtist能够生成高质量的4D虚拟化身，并对多种源图像域展现出极强的鲁棒性。代码、数据及模型将公开，以促进未来研究。

English

This work focuses on open-domain 4D avatarization, with the purpose of creating a 4D avatar from a portrait image in an arbitrary style. We select parametric triplanes as the intermediate 4D representation and propose a practical training paradigm that takes advantage of both generative adversarial networks (GANs) and diffusion models. Our design stems from the observation that 4D GANs excel at bridging images and triplanes without supervision yet usually face challenges in handling diverse data distributions. A robust 2D diffusion prior emerges as the solution, assisting the GAN in transferring its expertise across various domains. The synergy between these experts permits the construction of a multi-domain image-triplane dataset, which drives the development of a general 4D avatar creator. Extensive experiments suggest that our model, AvatarArtist, is capable of producing high-quality 4D avatars with strong robustness to various source image domains. The code, the data, and the models will be made publicly available to facilitate future studies..