Lune

SIGGRAPH2025Top-tier venue

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

Chengan He, Junxuan Li, Tobias Kirschstein, Artem Sevastopolsky, Shunsuke Saito, Qingyang Tan, Javier Romero, Chen Cao, Holly E. Rushmeier, Giljoo Nam

Abstract

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/.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PhysHead: Simulation-Ready Gaussian Head Avatars cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Condition Matters in Full-head 3D GANs cites GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
  • Condition Matters in Full-head 3D GANs cites Efficient Geometry-aware 3D Generative Adversarial Networks
  • FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Efficient Geometry-aware 3D Generative Adversarial Networks cites StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis
  • Efficient Geometry-aware 3D Generative Adversarial Networks cites GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Condition Matters in Full-head 3D GANsHeyuan Li, Huimin Zhang, Yuda Qiu, Zhengwentai Sun et al.ICLR 2026 · 3 citations
  2. PhysHead: Simulation-Ready Gaussian Head AvatarsBerna Kabadayi, Vanessa Sklyarova, Wojciech Zielonka, Justus Thies et al.CVPR 2026 · 1 citation
  3. FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual CapturesYujie Sun, Zhuoqiang CAI, Chaoyue Niu, Jianchuan Chen et al.CVPR 2026

Builds on28

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. GRAF: Generative Radiance Fields for 3D-Aware Image SynthesisKatja Schwarz, Yiyi Liao, Michael Niemeyer, Andreas GeigerNeurIPS 2020 · 1,001 citations
  3. Efficient Geometry-aware 3D Generative Adversarial NetworksEric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano et al.CVPR 2022 · 984 citations
  4. StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image SynthesisJiatao Gu, Lingjie Liu, Peng Wang, Christian TheobaltICLR 2022 · 622 citations
  5. AdaFace: Quality Adaptive Margin for Face RecognitionMinchul Kim, Anil K. Jain, Xiaoming LiuCVPR 2022 · 509 citations

Related papers

  1. HairCUP: Hair Compositional Universal Prior for 3D Gaussian AvatarsByungjun Kim, Shunsuke Saito, Giljoo Nam, Tomas Simon et al.ICCV 2025 · 2 citations
  2. i3DMM: Deep Implicit 3D Morphable Model of Human HeadsTarun Yenamandra, Ayush Tewari, Florian Bernard, Hans-Peter Seidel et al.CVPR 2021
  3. AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and IndexingFan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai et al.CVPR 2024 · 6 citations
  4. HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle SynthesisHaimin Luo, Min Ouyang, Lan Xu, Jingyi YuSIGGRAPH 2026
  5. DGH: Dynamic Gaussian HairJunying Wang, Yuanlu Xu, Edith Tretschk, Ziyan Wang et al.NeurIPS 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines