{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T18:53:38Z","timestamp":1774637618371,"version":"3.50.1"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,8,1]]},"abstract":"<jats:p>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\/.<\/jats:p>","DOI":"10.1145\/3731211","type":"journal-article","created":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T04:02:22Z","timestamp":1753588942000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["3DGH: 3D Head Generation with Composable Hair and Face"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2052-4835","authenticated-orcid":false,"given":"Chengan","family":"He","sequence":"first","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4375-3443","authenticated-orcid":false,"given":"Junxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Meta Codec Avatars Lab, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5308-591X","authenticated-orcid":false,"given":"Tobias","family":"Kirschstein","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2951-1448","authenticated-orcid":false,"given":"Artem","family":"Sevastopolsky","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2053-3472","authenticated-orcid":false,"given":"Shunsuke","family":"Saito","sequence":"additional","affiliation":[{"name":"Meta Codec Avatars Lab, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9269-5289","authenticated-orcid":false,"given":"Qingyang","family":"Tan","sequence":"additional","affiliation":[{"name":"Meta Codec Avatars Lab, Burlingame, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7921-2679","authenticated-orcid":false,"given":"Javier","family":"Romero","sequence":"additional","affiliation":[{"name":"Meta Codec Avatars Lab, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7992-2814","authenticated-orcid":false,"given":"Chen","family":"Cao","sequence":"additional","affiliation":[{"name":"Meta Codec Avatars Lab, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5241-0886","authenticated-orcid":false,"given":"Holly","family":"Rushmeier","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1822-1501","authenticated-orcid":false,"given":"Giljoo","family":"Nam","sequence":"additional","affiliation":[{"name":"Meta Codec Avatars Lab, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530141"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"e_1_2_2_4_1","volume-title":"Reference-Based 3D-Aware Image Editing with Triplane. arXiv preprint arXiv:2404.03632","author":"Bilecen Bahri Batuhan","year":"2024","unstructured":"Bahri Batuhan Bilecen, Yigit Yalin, Ning Yu, and Aysegul Dundar. 2024. Reference-Based 3D-Aware Image Editing with Triplane. arXiv preprint arXiv:2404.03632 (2024)."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925961"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"e_1_2_2_9_1","volume-title":"Deep Generation of Face Images from Sketches. arXiv preprint arXiv:2006.01047","author":"Chen Shu-Yu","year":"2020","unstructured":"Shu-Yu Chen, Wanchao Su, Lin Gao, Shihong Xia, and Hongbo Fu. 2020. Deep Generation of Face Images from Sketches. arXiv preprint arXiv:2006.01047 (2020)."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00222"},{"key":"e_1_2_2_11_1","volume-title":"SketchFaceNeRF: Sketch-Based Facial Generation and Editing in Neural Radiance Fields. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2023)","author":"Gao Lin","year":"2023","unstructured":"Lin Gao, Feng-Lin Liu, Shu-Yu Chen, Kaiwen Jiang, Chun-Peng Li, Yu-Kun Lai, and Hongbo Fu. 2023. SketchFaceNeRF: Sketch-Based Facial Generation and Editing in Neural Radiance Fields. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2023) 42, 4 (2023), 159:1\u2013159:17."},{"key":"e_1_2_2_12_1","volume-title":"Generative Adversarial Nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_2_2_13_1","volume-title":"StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis. arXiv preprint arXiv:2110.08985","author":"Gu Jiatao","year":"2021","unstructured":"Jiatao Gu, Lingjie Liu, Peng Wang, and Christian Theobalt. 2021. StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis. arXiv preprint arXiv:2110.08985 (2021)."},{"key":"e_1_2_2_14_1","volume-title":"International Conference on Learning Representations.","author":"He Chengan","year":"2025","unstructured":"Chengan He, Xin Sun, Zhixin Shu, Fujun Luan, S\u00f6ren Pirk, Jorge Alejandro Amador Herrera, Dominik L. Michels, Tuanfeng Y. Wang, Meng Zhang, Holly Rushmeier, and Yi Zhou. 2025. Perm: A Parametric Representation for Multi-Style 3D Hair Modeling. In International Conference on Learning Representations."},{"key":"e_1_2_2_15_1","volume-title":"GANs Trained by a Two Time-scale Update Rule Converge to a Local Nash Equilibrium. Advances in neural information processing systems 30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-scale Update Rule Converge to a Local Nash Equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_2_16_1","volume-title":"Classifier-Free Diffusion Guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766931"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618510"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687686"},{"key":"e_1_2_2_24_1","volume-title":"SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation. arXiv preprint arXiv:2404.05680","author":"Li Heyuan","year":"2024","unstructured":"Heyuan Li, Ce Chen, Tianhao Shi, Yuda Qiu, Sizhe An, Guanying Chen, and Xiaoguang Han. 2024. SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation. arXiv preprint arXiv:2404.05680 (2024)."},{"key":"e_1_2_2_25_1","volume-title":"Learning a Model of Facial Shape and Expression from 4D Scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6","author":"Li Tianye","year":"2017","unstructured":"Tianye Li, Timo Bolkart, Michael. J. Black, Hao Li, and Javier Romero. 2017. Learning a Model of Facial Shape and Expression from 4D Scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6 (2017), 194:1\u2013194:17."},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00865"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_2_28_1","volume-title":"GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians. arXiv preprint arXiv:2402.10483","author":"Luo Haimin","year":"2024","unstructured":"Haimin Luo, Min Ouyang, Zijun Zhao, Suyi Jiang, Longwen Zhang, Qixuan Zhang, Wei Yang, Lan Xu, and Jingyi Yu. 2024. GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians. arXiv preprint arXiv:2402.10483 (2024)."},{"key":"e_1_2_2_29_1","volume-title":"International conference on machine learning. PMLR, 3481\u20133490","author":"Mescheder Lars","year":"2018","unstructured":"Lars Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which Training Methods for GANs Do Actually Converge?. In International conference on machine learning. PMLR, 3481\u20133490."},{"key":"e_1_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes As Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"e_1_2_2_32_1","volume-title":"HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach. arXiv preprint arXiv:2404.01094","author":"Nikolaev Maxim","year":"2024","unstructured":"Maxim Nikolaev, Mikhail Kuznetsov, Dmitry Vetrov, and Aibek Alanov. 2024. HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach. arXiv preprint arXiv:2404.01094 (2024)."},{"key":"e_1_2_2_33_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13503\u201313513","author":"Or-El Roy","year":"2022","unstructured":"Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong Joon Park, and Ira Kemelmacher-Shlizerman. 2022. StyleSDF: High-resolution 3D-Consistent Image and Geometry Generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13503\u201313513."},{"key":"e_1_2_2_34_1","first-page":"7993","article-title":"RenderMe-360: a Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","volume":"36","author":"Pan Dongwei","year":"2023","unstructured":"Dongwei Pan, Long Zhuo, Jingtan Piao, Huiwen Luo, Wei Cheng, Yuxin Wang, Siming Fan, Shengqi Liu, Lei Yang, Bo Dai, et al. 2023. RenderMe-360: a Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars. Advances in Neural Information Processing Systems 36 (2023), 7993\u20138005.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015784"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Stanislav Pidhorskyi Tomas Simon Gabriel Schwartz He Wen Yaser Sheikh and Jason Saragih. 2024. Rasterized Edge Gradients: Handling Discontinuities Differentiably. arXiv preprint. arXiv:2405.02508.","DOI":"10.1007\/978-3-031-73010-8_20"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275019"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00021"},{"key":"e_1_2_2_41_1","first-page":"20154","article-title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","volume":"33","author":"Schwarz Katja","year":"2020","unstructured":"Katja Schwarz, Yiyi Liao, Michael Niemeyer, and Andreas Geiger. 2020. GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis. Advances in Neural Information Processing Systems 33 (2020), 20154\u201320166.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592106"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00450"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555506"},{"key":"e_1_2_2_45_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00605"},{"key":"e_1_2_2_47_1","volume-title":"A Survey on Hair Modeling: Styling, Simulation, and Rendering","author":"Ward Kelly","year":"2007","unstructured":"Kelly Ward, Florence Bertails, Tae-Yong Kim, Stephen R Marschner, Marie-Paule Cani, and Ming C Lin. 2007. A Survey on Hair Modeling: Styling, Simulation, and Rendering. IEEE transactions on visualization and computer graphics 13, 2 (2007), 213\u2013234."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02156"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00158"},{"key":"e_1_2_2_51_1","volume-title":"Multiface: A Dataset for Neural Face Rendering. arXiv preprint arXiv:2207.11243","author":"Zheng Ningyuan","year":"2022","unstructured":"Cheng-hsin Wuu, Ningyuan Zheng, Scott Ardisson, Rohan Bali, Danielle Belko, Eric Brockmeyer, Lucas Evans, Timothy Godisart, Hyowon Ha, Xuhua Huang, et al. 2022. Multiface: A Dataset for Neural Face Rendering. arXiv preprint arXiv:2207.11243 (2022)."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661284"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01789"},{"key":"e_1_2_2_54_1","volume-title":"European Conference of Computer Vision (ECCV).","author":"Zakharov Egor","year":"2024","unstructured":"Egor Zakharov, Vanessa Sklyarova, Michael J Black, Giljoo Nam, Justus Thies, and Otmar Hilliges. 2024. Human Hair Reconstruction with Strand-Aligned 3D Gaussians. In European Conference of Computer Vision (ECCV)."},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073627"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01224"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618309"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_15"},{"key":"e_1_2_2_60_1","volume-title":"Barbershop: GAN-based Image Compositing Using Segmentation Masks. arXiv preprint arXiv:2106.01505","author":"Zhu Peihao","year":"2021","unstructured":"Peihao Zhu, Rameen Abdal, John Femiani, and Peter Wonka. 2021. Barbershop: GAN-based Image Compositing Using Segmentation Masks. arXiv preprint arXiv:2106.01505 (2021)."},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2001.964490"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:52:21Z","timestamp":1774633941000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":62,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8,1]]}},"alternative-id":["10.1145\/3731211"],"URL":"https:\/\/doi.org\/10.1145\/3731211","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}