{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:52Z","timestamp":1784268652708,"version":"3.55.0"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2018,12,4]],"date-time":"2018-12-04T00:00:00Z","timestamp":1543881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100004344","name":"Adobe Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004344","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004359","name":"Sony Electronics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"crossref","award":["W911NF- 14-D-0005"],"award-info":[{"award-number":["W911NF- 14-D-0005"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ONR YIP","award":["N00014-17-S- FO14"],"award-info":[{"award-number":["N00014-17-S- FO14"]}]},{"name":"CONIX Research Center"},{"name":"the Andrew and Erna Viterbi Early Career Chair"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2018,12,31]]},"abstract":"<jats:p>Recent advances in single-view 3D hair digitization have made the creation of high-quality CG characters scalable and accessible to end-users, enabling new forms of personalized VR and gaming experiences. To handle the complexity and variety of hair structures, most cutting-edge techniques rely on the successful retrieval of a particular hair model from a comprehensive hair database. Not only are the aforementioned data-driven methods storage intensive, but they are also prone to failure for highly unconstrained input images, complicated hairstyles, and failed face detection. Instead of using a large collection of 3D hair models directly, we propose to represent the manifold of 3D hairstyles implicitly through a compact latent space of a volumetric variational autoencoder (VAE). This deep neural network is trained with volumetric orientation field representations of 3D hair models and can synthesize new hairstyles from a compressed code. To enable end-to-end 3D hair inference, we train an additional embedding network to predict the code in the VAE latent space from any input image. Strand-level hairstyles can then be generated from the predicted volumetric representation. Our fully automatic framework does not require any ad-hoc face fitting, intermediate classification and segmentation, or hairstyle database retrieval. Our hair synthesis approach is significantly more robust and can handle a much wider variation of hairstyles than state-of-the-art data-driven hair modeling techniques with challenging inputs, including photos that are low-resolution, overexposured, or contain extreme head poses. The storage requirements are minimal and a 3D hair model can be produced from an image in a second. Our evaluations also show that successful reconstructions are possible from highly stylized cartoon images, non-human subjects, and pictures taken from behind a person. Our approach is particularly well suited for continuous and plausible hair interpolation between very different hairstyles.<\/jats:p>","DOI":"10.1145\/3272127.3275019","type":"journal-article","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T19:16:10Z","timestamp":1543432570000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":70,"title":["3D hair synthesis using volumetric variational autoencoders"],"prefix":"10.1145","volume":"37","author":[{"given":"Shunsuke","family":"Saito","sequence":"first","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liwen","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hikaru","family":"Ibayashi","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Luo","sequence":"additional","affiliation":[{"name":"Snap Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,12,4]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073207"},{"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":"10.1561\/2200000006"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_2_2_5_1","unstructured":"Andrew Brock Theodore Lim James M Ritchie and Nick Weston. 2016. Generative and Discriminative Voxel Modeling with Convolutional Neural Networks. In 3D Deep Learning Workshop Advances in neural information processing systems (NIPS). 1--9.  Andrew Brock Theodore Lim James M Ritchie and Nick Weston. 2016. Generative and Discriminative Voxel Modeling with Convolutional Neural Networks. In 3D Deep Learning Workshop Advances in neural information processing systems (NIPS). 1--9."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601212"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.512"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818112"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925961"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461990"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185612"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2005.20"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601133"},{"key":"e_1_2_2_15_1","unstructured":"FaceUnity. 2017. http:\/\/www.faceunity.com\/p2a-demo.mp4.  FaceUnity. 2017. http:\/\/www.faceunity.com\/p2a-demo.mp4."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1384429.1384439"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366165"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601194"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766931"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661254"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.31310887"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_2_24_1","volume-title":"Avatar SDK","year":"2017","unstructured":"itSeez3D : Avatar SDK . 2017 . https:\/\/avatarsdk.com. itSeez3D: Avatar SDK. 2017. https:\/\/avatarsdk.com."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.117"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618510"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566627"},{"key":"e_1_2_2_29_1","volume-title":"Proceedings of International Conference on Learning Representations (ICLR).","author":"Kingma Diederik","year":"2015","unstructured":"Diederik Kingma and Jimmy Ba . 2015 . Adam: A method for stochastic optimization . In Proceedings of International Conference on Learning Representations (ICLR). Diederik Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_30_1","volume-title":"Proceedings of International Conference on Learning Representations (ICLR).","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Max Welling . 2014 . Auto-encoding variational bayes . In Proceedings of International Conference on Learning Representations (ICLR). Diederik P Kingma and Max Welling. 2014. Auto-encoding variational bayes. In Proceedings of International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766939"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462026"},{"key":"e_1_2_2_34_1","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 922--928","author":"Maturana D.","unstructured":"D. Maturana and S. Scherer . 2015. VoxNet: A 3D Convolutional Neural Network for real-time object recognition . In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 922--928 . D. Maturana and S. Scherer. 2015. VoxNet: A 3D Convolutional Neural Network for real-time object recognition. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 922--928."},{"key":"e_1_2_2_35_1","unstructured":"Myidol. 2017. http:\/\/en.faceii.com\/.  Myidol. 2017. http:\/\/en.faceii.com\/."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980252"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015784"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360629"},{"key":"e_1_2_2_39_1","unstructured":"Pinscreen. 2017. http:\/\/www.pinscreen.com.  Pinscreen. 2017. http:\/\/www.pinscreen.com."},{"key":"e_1_2_2_40_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 77--85","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi , Hao Su , Kaichun Mo , and Leonidas J Guibas . 2017 a. PointNet: Deep learning on point sets for 3d classification and segmentation . In IEEE Conference on Computer Vision and Pattern Recognition. 77--85 . Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017a. PointNet: Deep learning on point sets for 3d classification and segmentation. In IEEE Conference on Computer Vision and Pattern Recognition. 77--85."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"e_1_2_2_42_1","unstructured":"Charles R Qi Li Yi Hao Su and Leonidas J Guibas. 2017b. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Advances in Neural Information Processing Systems. 5099--5108.   Charles R Qi Li Yi Hao Su and Leonidas J Guibas. 2017b. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Advances in Neural Information Processing Systems. 5099--5108."},{"key":"e_1_2_2_43_1","volume-title":"Proceedings of International Conference on International Conference on Machine Learning (ICML). 1278--1286","author":"Rezende Danilo Jimenez","year":"2014","unstructured":"Danilo Jimenez Rezende , Shakir Mohamed , and Daan Wierstra . 2014 . Stochastic back-propagation and approximate inference in deep generative models . In Proceedings of International Conference on International Conference on Machine Learning (ICML). 1278--1286 . Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic back-propagation and approximate inference in deep generative models. In Proceedings of International Conference on International Conference on Machine Learning (ICML). 1278--1286."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_15"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00612"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3182644"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.163"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3145749.3145758"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531362"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.30"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073267"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12214"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2007.31"},{"key":"e_1_2_2_56_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu , Shuran Song , Aditya Khosla , Fisher Yu , Linguang Zhang , Xiaoou Tang , and Jianxiong Xiao . 2015 . 3D ShapeNets: A deep representation for volumetric shapes . In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920 . Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920."},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661284"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556700.2556715"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618512"},{"key":"e_1_2_2_60_1","volume-title":"Proceedings of the European Conference on Computer Vision. 294--311","author":"Ersin Yumer M","year":"2016","unstructured":"M Ersin Yumer and Niloy J Mitra . 2016 . Learning Semantic Deformation Flows with 3D Convolutional Networks . In Proceedings of the European Conference on Computer Vision. 294--311 . M Ersin Yumer and Niloy J Mitra. 2016. Learning Semantic Deformation Flows with 3D Convolutional Networks. In Proceedings of the European Conference on Computer Vision. 294--311."},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073627"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"e_1_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_15"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275019","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3272127.3275019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:03Z","timestamp":1750207443000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,4]]},"references-count":62,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,12,31]]}},"alternative-id":["10.1145\/3272127.3275019"],"URL":"https:\/\/doi.org\/10.1145\/3272127.3275019","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,4]]},"assertion":[{"value":"2018-12-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}