3DGH: 3D Head Generation with Composable Hair and Face

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Chengan, Li, Junxuan, Kirschstein, Tobias, Sevastopolsky, Artem, Saito, Shunsuke, Tan, Qingyang, Romero, Javier, Cao, Chen, Rushmeier, Holly, Nam, Giljoo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913912942755840
author He, Chengan
Li, Junxuan
Kirschstein, Tobias
Sevastopolsky, Artem
Saito, Shunsuke
Tan, Qingyang
Romero, Javier
Cao, Chen
Rushmeier, Holly
Nam, Giljoo
author_facet He, Chengan
Li, Junxuan
Kirschstein, Tobias
Sevastopolsky, Artem
Saito, Shunsuke
Tan, Qingyang
Romero, Javier
Cao, Chen
Rushmeier, Holly
Nam, Giljoo
contents We present 3DGH, an unconditional generative model for 3D human heads with composable hair and face components. Unlike previous work that entangles the modeling of hair and face, we propose to separate them using a novel data representation with template-based 3D Gaussian Splatting, in which deformable hair geometry is introduced to capture the geometric variations across different hairstyles. Based on this data representation, we design a 3D GAN-based architecture with dual generators and employ a cross-attention mechanism to model the inherent correlation between hair and face. The model is trained on synthetic renderings using carefully designed objectives to stabilize training and facilitate hair-face separation. We conduct extensive experiments to validate the design choice of 3DGH, and evaluate it both qualitatively and quantitatively by comparing with several state-of-the-art 3D GAN methods, demonstrating its effectiveness in unconditional full-head image synthesis and composable 3D hairstyle editing. More details will be available on our project page: https://c-he.github.io/projects/3dgh/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20875
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3DGH: 3D Head Generation with Composable Hair and Face
He, Chengan
Li, Junxuan
Kirschstein, Tobias
Sevastopolsky, Artem
Saito, Shunsuke
Tan, Qingyang
Romero, Javier
Cao, Chen
Rushmeier, Holly
Nam, Giljoo
Graphics
Computer Vision and Pattern Recognition
We present 3DGH, an unconditional generative model for 3D human heads with composable hair and face components. Unlike previous work that entangles the modeling of hair and face, we propose to separate them using a novel data representation with template-based 3D Gaussian Splatting, in which deformable hair geometry is introduced to capture the geometric variations across different hairstyles. Based on this data representation, we design a 3D GAN-based architecture with dual generators and employ a cross-attention mechanism to model the inherent correlation between hair and face. The model is trained on synthetic renderings using carefully designed objectives to stabilize training and facilitate hair-face separation. We conduct extensive experiments to validate the design choice of 3DGH, and evaluate it both qualitatively and quantitatively by comparing with several state-of-the-art 3D GAN methods, demonstrating its effectiveness in unconditional full-head image synthesis and composable 3D hairstyle editing. More details will be available on our project page: https://c-he.github.io/projects/3dgh/.
title 3DGH: 3D Head Generation with Composable Hair and Face
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.20875