{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T02:41:35Z","timestamp":1774924895077,"version":"3.50.1"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2023,12,5]]},"abstract":"<jats:p>\n            Despite recent successes in hair acquisition that fits a high-dimensional hair model to a specific input subject, generative hair models, which establish general embedding spaces for encoding, editing, and sampling diverse hairstyles, are way less explored. In this paper, we present\n            <jats:italic toggle=\"yes\">GroomGen<\/jats:italic>\n            , the first generative model designed for hair geometry composed of highly-detailed dense strands. Our approach is motivated by two key ideas. First, we construct\n            <jats:italic toggle=\"yes\">hair latent spaces<\/jats:italic>\n            covering both individual strands and hairstyles. The latent spaces are compact, expressive, and well-constrained for high-quality and diverse sampling. Second, we adopt a\n            <jats:italic toggle=\"yes\">hierarchical hair representation<\/jats:italic>\n            that parameterizes a complete hair model to three levels: single strands, sparse guide hairs, and complete dense hairs. This representation is critical to the compactness of latent spaces, the robustness of training, and the efficiency of inference. Based on this hierarchical latent representation, our proposed pipeline consists of a\n            <jats:italic toggle=\"yes\">strand-VAE<\/jats:italic>\n            and a\n            <jats:italic toggle=\"yes\">hairstyle-VAE<\/jats:italic>\n            that encode an individual strand and a set of guide hairs to their respective latent spaces, and a\n            <jats:italic toggle=\"yes\">hybrid densification step<\/jats:italic>\n            that populates sparse guide hairs to a dense hair model.\n            <jats:italic toggle=\"yes\">GroomGen<\/jats:italic>\n            not only enables novel hairstyle sampling and plausible hairstyle interpolation, but also supports interactive editing of complex hairstyles, or can serve as strong data-driven prior for hairstyle reconstruction from images. We demonstrate the superiority of our approach with qualitative examples of diverse sampled hairstyles and quantitative evaluation of generation quality regarding every single component and the entire pipeline.\n          <\/jats:p>","DOI":"10.1145\/3618309","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T10:20:48Z","timestamp":1701771648000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations"],"prefix":"10.1145","volume":"42","author":[{"given":"Yuxiao","family":"Zhou","sequence":"first","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Menglei","family":"Chai","sequence":"additional","affiliation":[{"name":"Google Inc., United States of America"}]},{"given":"Alessandro","family":"Pepe","sequence":"additional","affiliation":[{"name":"Google Inc., United States of America"}]},{"given":"Markus","family":"Gross","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Thabo","family":"Beeler","sequence":"additional","affiliation":[{"name":"Google Inc., Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Wasserstein Generative Adversarial Networks. In ICML","volume":"70","author":"Arjovsky Mart\u00edn","year":"2017","unstructured":"Mart\u00edn Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein Generative Adversarial Networks. In ICML 2017, Vol. 70. 214--223."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185613"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142012"},{"key":"e_1_2_2_4_1","volume-title":"Jean Luc L\u00e9v\u00eaque, and Marie-Paule Cani","author":"Bertails Florence","year":"2005","unstructured":"Florence Bertails, Basile Audoly, Bernard Querleux, Fr\u00e9d\u00e9ric Leroy, Jean Luc L\u00e9v\u00eaque, and Marie-Paule Cani. 2005. Predicting Natural Hair Shapes by Solving the Statics of Flexible Rods. In Eurographics 2005. 81--84."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818112"},{"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":"10.1145\/2461912.2461990"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185612"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601211"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2551242"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.05-07-01688.1985"},{"key":"e_1_2_2_12_1","volume-title":"Generative Adversarial Nets. In NIPS","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NIPS 2014. 2672--2680."},{"key":"e_1_2_2_13_1","volume-title":"Multi-linear Data-Driven Dynamic Hair Model with Efficient Hair-Body Collision Handling. In SCA","author":"Guan Peng","year":"2012","unstructured":"Peng Guan, Leonid Sigal, Valeria Reznitskaya, and Jessica K. Hodgins. 2012. Multi-linear Data-Driven Dynamic Hair Model with Efficient Hair-Body Collision Handling. In SCA 2012. 295--304."},{"key":"e_1_2_2_14_1","volume-title":"Deep Residual Learning for Image Recognition. In CVPR","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR 2016. 770--778."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366165"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3128975.3129002"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601194"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766931"},{"key":"e_1_2_2_19_1","volume-title":"ICML","volume":"37","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In ICML 2015, Vol. 37. 448--456."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618510"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_2_22_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015."},{"key":"e_1_2_2_23_1","volume-title":"Auto-Encoding Variational Bayes. In ICLR","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In ICLR 2014."},{"key":"e_1_2_2_24_1","volume-title":"SIGGRAPH Asia","author":"Kuang Zhiyi","year":"2022","unstructured":"Zhiyi Kuang, Yiyang Chen, Hongbo Fu, Kun Zhou, and Youyi Zheng. 2022. Deep-MVSHair: Deep Hair Modeling from Sparse Views. In SIGGRAPH Asia 2022. 10:1--10:8."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275020"},{"key":"e_1_2_2_26_1","volume-title":"CVPR","author":"Luo Linjie","year":"2012","unstructured":"Linjie Luo, Hao Li, Sylvain Paris, Thibaut Weise, Mark Pauly, and Szymon Rusinkiewicz. 2012. Multi-view hair capture using orientation fields. In CVPR 2012. 1490--1497."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462026"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3029823"},{"key":"e_1_2_2_29_1","volume-title":"Modulated Periodic Activations for Generalizable Local Functional Representations. In ICCV","author":"Mehta Ishit","year":"2021","unstructured":"Ishit Mehta, Micha\u00ebl Gharbi, Connelly Barnes, Eli Shechtman, Ravi Ramamoorthi, and Manmohan Chandraker. 2021. Modulated Periodic Activations for Generalizable Local Functional Representations. In ICCV 2021. 14194--14203."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_31_1","volume-title":"Strand-Accurate Multi-View Hair Capture. In CVPR","author":"Nam Giljoo","year":"2019","unstructured":"Giljoo Nam, Chenglei Wu, Min H. Kim, and Yaser Sheikh. 2019. Strand-Accurate Multi-View Hair Capture. In CVPR 2019. 155--164."},{"key":"e_1_2_2_32_1","first-page":"7444","article-title":"Intuitive","volume":"2020","author":"Olszewski Kyle","year":"2020","unstructured":"Kyle Olszewski, Duygu Ceylan, Jun Xing, Jose Echevarria, Zhili Chen, Weikai Chen, and Hao Li. 2020. Intuitive, Interactive Beard and Hair Synthesis With Generative Models. In CVPR 2020. 7444--7454.","journal-title":"Interactive Beard and Hair Synthesis With Generative Models. In CVPR"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015784"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360629"},{"key":"e_1_2_2_35_1","volume-title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In ICLR","author":"Radford Alec","year":"2016","unstructured":"Alec Radford, Luke Metz, and Soumith Chintala. 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In ICLR 2016."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87361-5_44"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_5"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275019"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2968433"},{"key":"e_1_2_2_40_1","volume-title":"EGSR","author":"Sun Tiancheng","year":"2021","unstructured":"Tiancheng Sun, Giljoo Nam, Carlos Aliaga, Christophe Hery, and Ravi Ramamoorthi. 2021. Human Hair Inverse Rendering using Multi-View Photometric data. In EGSR 2021. 179--190."},{"key":"e_1_2_2_41_1","volume-title":"Lempitsky","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. 2016. Instance Normalization: The Missing Ingredient for Fast Stylization. CoRR abs\/1607.08022 (2016)."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531362"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00605"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073267"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530116"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00158"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661284"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356511"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073627"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03192.x"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01224"},{"key":"e_1_2_2_52_1","volume-title":"HairNet: Single-View Hair Reconstruction Using Convolutional Neural Networks. In ECCV","volume":"11215","author":"Zhou Yi","year":"2018","unstructured":"Yi Zhou, Liwen Hu, Jun Xing, Weikai Chen, Han-Wei Kung, Xin Tong, and Hao Li. 2018. HairNet: Single-View Hair Reconstruction Using Convolutional Neural Networks. In ECCV 2018, Vol. 11215. 249--265."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618309","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3618309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T10:48:22Z","timestamp":1755773302000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12,5]]}},"alternative-id":["10.1145\/3618309"],"URL":"https:\/\/doi.org\/10.1145\/3618309","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"2023-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}