{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:48:50Z","timestamp":1774021730806,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"name":"Key R&D Program of Zhejiang","award":["2024C01069"],"award-info":[{"award-number":["2024C01069"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472373"],"award-info":[{"award-number":["62472373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SNSF project","award":["200021 204840"],"award-info":[{"award-number":["200021 204840"]}]},{"DOI":"10.13039\/501100022491","name":"Max Planck ETH Center for Learning Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100022491","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730680","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-based Animatable 3D Avatars with Morphable Model Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2432-809X","authenticated-orcid":false,"given":"Yiqian","family":"Wu","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland and State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4268-9133","authenticated-orcid":false,"given":"Malte","family":"Prinzler","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-2920","authenticated-orcid":false,"given":"Xiaogang","family":"Jin","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1015-4770","authenticated-orcid":false,"given":"Siyu","family":"Tang","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00541"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01972"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00283"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1838"},{"key":"e_1_3_3_2_6_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Chu Xuangeng","year":"2024","unstructured":"Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu, and Tatsuya Harada. 2024. GPAvatar: Generalizable and Precise Head Avatar from Image(s). In The Twelfth International Conference on Learning Representations, ICLR 2024. OpenReview.net."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687601"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Xuan Gao Chenglai Zhong Jun Xiang Yang Hong Yudong Guo and Juyong Zhang. 2022. Reconstructing Personalized Semantic Facial NeRF Models from Monocular Video. ACM Trans. Graph. 41 6 (2022) 200:1\u2013200:12.","DOI":"10.1145\/3550454.3555501"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02012"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687689"},{"key":"e_1_3_3_2_14_1","unstructured":"Google. 2024. mediapipe. https:\/\/github.com\/google-ai-edge\/mediapipe."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01810"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00995"},{"key":"e_1_3_3_2_17_1","first-page":"6840","volume-title":"Advances in Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems , Vol.\u00a033. 6840\u20136851."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Diqiong Jiang Yiwei Jin Fang-Lue Zhang Zhe Zhu Yun Zhang Ruofeng Tong and Min Tang. 2023. Sphere Face Model: A 3D morphable model with hypersphere manifold latent space using joint 2D\/3D training. Comput. Vis. Media 9 2 (2023) 279\u2013296.","DOI":"10.1007\/s41095-022-0286-4"},{"key":"e_1_3_3_2_21_1","unstructured":"Alexander Kapitanov Karina Kvanchiani and Sofia Kirillova. 2023. EasyPortrait - Face Parsing and Portrait Segmentation Dataset. CoRR abs\/2304.13509 (2023)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine and Timo Aila. 2021. A Style-Based Generator Architecture for Generative Adversarial Networks. IEEE Trans. Pattern Anal. Mach. Intell. 43 12 (2021) 4217\u20134228.","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimkuehler and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Trans. Graph. 42 4 (2023) 139:1\u2013139:14.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_24_1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1007\/978-3-031-73235-5_12","volume-title":"Computer Vision - ECCV 2024 - 18th European Conference","volume":"15062","author":"Khirodkar Rawal","year":"2024","unstructured":"Rawal Khirodkar, Timur\u00a0M. Bagautdinov, Julieta Martinez, Su Zhaoen, Austin James, Peter Selednik, Stuart Anderson, and Shunsuke Saito. 2024. Sapiens: Foundation for Human Vision Models. In Computer Vision - ECCV 2024 - 18th European Conference(Lecture Notes in Computer Science, Vol.\u00a015062). Springer, 206\u2013228."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687686"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Tobias Kirschstein Shenhan Qian Simon Giebenhain Tim Walter and Matthias Nie\u00dfner. 2023. NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads. ACM Trans. Graph. 42 4 (2023) 161:1\u2013161:14.","DOI":"10.1145\/3592455"},{"key":"e_1_3_3_2_27_1","unstructured":"Nikos Kolotouros Thiemo Alldieck Andrei Zanfir Eduard\u00a0Gabriel Bazavan Mihai Fieraru and Cristian Sminchisescu. 2023. DreamHuman: Animatable 3D Avatars from Text. CoRR abs\/2306.09329 (2023)."},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687653"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Tianye Li Timo Bolkart Michael\u00a0J. Black Hao Li and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. 36 6 (2017) 194:1\u2013194:17.","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Armand\u00a0Comas Massague Di Qiu Menglei Chai Marcel\u00a0C. B\u00fchler Amit Raj Ruiqi Gao Qiangeng Xu Mark Matthews Paulo F.\u00a0U. Gotardo Octavia\u00a0I. Camps Sergio Orts-Escolano and Thabo Beeler. 2024. MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space. CoRR abs\/2404.01296 (2024).","DOI":"10.1007\/978-3-031-72848-8_11"},{"key":"e_1_3_3_2_35_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In The Tenth International Conference on Learning Representations, ICLR 2022. OpenReview.net."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_11"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"crossref","unstructured":"Thomas M\u00fcller Alex Evans Christoph Schied and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41 4 (2022) 102:1\u2013102:15.","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_3_2_41_1","volume-title":"The 11th International Conference on Learning Representations, ICLR","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The 11th International Conference on Learning Representations, ICLR."},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Malte Prinzler Egor Zakharov Vanessa Sklyarova Berna Kabadayi and Justus Thies. 2024. Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions.","DOI":"10.1109\/3DV66043.2025.00148"},{"key":"e_1_3_3_2_43_1","unstructured":"Shenhan Qian. 2024. VHAP. https:\/\/github.com\/ShenhanQian\/VHAP."},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"e_1_3_3_2_45_1","series-title":"Proceedings of Machine Learning Research","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021(Proceedings of Machine Learning Research, Vol.\u00a0139). PMLR, 8748\u20138763."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"e_1_3_3_2_49_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. In The Twelfth International Conference on Learning Representations, ICLR 2024. OpenReview.net."},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_3_2_51_1","volume-title":"Advances in Neural Information Processing Systems","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Advances in Neural Information Processing Systems , Vol.\u00a034."},{"key":"e_1_3_3_2_52_1","unstructured":"Kailu Wu Fangfu Liu Zhihan Cai Runjie Yan Hanyang Wang Yating Hu Yueqi Duan and Kaisheng Ma. 2024a. Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image. CoRR abs\/2405.20343 (2024)."},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"crossref","unstructured":"Yiqian Wu Hao Xu Xiangjun Tang Xien Chen Siyu Tang Zhebin Zhang Chen Li and Xiaogang Jin. 2024b. Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior. ACM Trans. Graph. 43 4 Article 45 (jul 2024) 12\u00a0pages. https:\/\/doi.org\/10.1145\/3658162","DOI":"10.1145\/3658162"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00189"},{"key":"e_1_3_3_2_56_1","unstructured":"Yuanyou Xu Zongxin Yang and Yi Yang. 2023. SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance. arxiv:https:\/\/arXiv.org\/abs\/2312.08889\u00a0[cs.CV]"},{"key":"e_1_3_3_2_57_1","unstructured":"YBIGTA. 2018. pytorch-hair-segmentation. https:\/\/github.com\/YBIGTA\/pytorch-hair-segmentation."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28540"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00151"},{"key":"e_1_3_3_2_60_1","unstructured":"Jianfeng Zhang Xuanmeng Zhang Huichao Zhang Jun\u00a0Hao Liew Chenxu Zhang Yi Yang and Jiashi Feng. 2023b. AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text. CoRR abs\/2311.17917 (2023)."},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_62_1","unstructured":"Xiaozheng Zheng Chao Wen Zhaohu Li Weiyi Zhang Zhuo Su Xu Chang Yang Zhao Zheng Lv Xiaoyuan Zhang Yongjie Zhang Guidong Wang and Lan Xu. 2024. HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors. CoRR abs\/2408.06019 (2024)."},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"crossref","unstructured":"Ziming Zhong Yanxu Xu Jing Li Jiale Xu Zhengxin Li Chaohui Yu and Shenghua Gao. 2024. MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis. CoRR abs\/2407.13675 (2024).","DOI":"10.1007\/978-3-031-72980-5_11"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01485"},{"key":"e_1_3_3_2_65_1","series-title":"(Lecture Notes in Computer Science)","volume-title":"Computer Vision - ECCV 2024 - 18th European Conference","author":"Zhou Zhenglin","year":"2024","unstructured":"Zhenglin Zhou, Fan Ma, Hehe Fan, and Yi Yang. 2024. HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting. In Computer Vision - ECCV 2024 - 18th European Conference(Lecture Notes in Computer Science). Springer."}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:55:41Z","timestamp":1774018541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":64,"alternative-id":["10.1145\/3721238.3730680","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730680","relation":{},"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"}}]}}