arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03763cs.CVcs.GRcs.LG

Gaussian3Diff:用于三维全头合成与编辑的三维高斯扩散

Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing

Google(谷歌);S-Lab, Nanyang Technological University(南洋理工大学S-Lab实验室)

Yushi Lan, Feitong Tan, Di Qiu, Qiangeng Xu, Kyle Genova, Zeng Huang, Sean Fanello, Rohit Pandey, Thomas Funkhouser, Chen Change Loy, Yinda Zhang

AI总结:

提出一种基于三维高斯扩散的框架,利用参数化人脸模型和三维高斯表示,结合轻量级三平面编码与二维UV空间参数化,实现逼真三维头部的生成、操控和细粒度编辑。

摘要:

我们提出了一种新颖的框架,用于生成逼真的三维人类头部,并随后以显著的灵活性对其进行操控和重新摆姿。所提出的方法利用三维人类头部的隐式函数表示,采用锚定在参数化人脸模型上的三维高斯。为了增强表示能力并编码空间信息,我们在每个高斯内嵌入一个轻量级的三平面有效载荷,而不是直接存储颜色和不透明度。此外,我们通过三维形变模型(3DMM)在二维UV空间中对高斯进行参数化,从而能够有效利用扩散模型进行三维头部头像生成。我们的方法有助于创建多样且逼真的三维人类头部,并支持对面部特征和表情进行细粒度编辑。大量实验证明了我们方法的有效性。

英文摘要:

We present a novel framework for generating photorealistic 3D human head and subsequently manipulating and reposing them with remarkable flexibility. The proposed approach leverages an implicit function representation of 3D human heads, employing 3D Gaussians anchored on a parametric face model. To enhance representational capabilities and encode spatial information, we embed a lightweight tri-plane payload within each Gaussian rather than directly storing color and opacity. Additionally, we parameterize the Gaussians in a 2D UV space via a 3DMM, enabling effective utilization of the diffusion model for 3D head avatar generation. Our method facilitates the creation of diverse and realistic 3D human heads with fine-grained editing over facial features and expressions. Extensive experiments demonstrate the effectiveness of our method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑