{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:56Z","timestamp":1781538896318,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["2024YFC3308300"],"award-info":[{"award-number":["2024YFC3308300"]}]},{"name":"the National Natural Science Foundation of China","award":["62077026"],"award-info":[{"award-number":["62077026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810572","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1203-1212","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GD-Head: Reconstructing High-quality 3D Avatar Head from a Single Image Using Geometry-guided Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8050-8677","authenticated-orcid":false,"given":"Leyuan","family":"Liu","sequence":"first","affiliation":[{"name":"Central China Normal University, WuHan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5836-4765","authenticated-orcid":false,"given":"Xiaoqing","family":"Chen","sequence":"additional","affiliation":[{"name":"Central China Normal University, WuHan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5546-5440","authenticated-orcid":false,"given":"Yufei","family":"Qian","sequence":"additional","affiliation":[{"name":"Central China Normal University, WuHan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1523-3478","authenticated-orcid":false,"given":"Jingying","family":"Chen","sequence":"additional","affiliation":[{"name":"Central China Normal University, WuHan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Oleg Alexander Mike Rogers William Lambeth Jen-Yuan Chiang Wan-Chun Ma Chuan-Chang Wang and Paul Debevec. 2010. The digital emily project: Achieving a photorealistic digital actor. IEEE Compt. Graph. & App. (CG&A) 30 4 (2010) 20\u201331.","DOI":"10.1109\/MCG.2010.65"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00043"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Linchao Bao Xiangkai Lin Yajing Chen Haoxian Zhang Sheng Wang Xuefei Zhe Di Kang Haozhi Huang Xinwei Jiang Jue Wang Dong Yu and Zhengyou Zhang. 2021. High-fidelity 3D digital human head creation from RGB-D selfies. ACM Trans. Graph. (TOG) 41 1 (2021) 1\u201321.","DOI":"10.1145\/3472954"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Anil Bas and William\u00a0AP Smith. 2019. What does 2D geometric information really tell us about 3D face shape?Int. J. Comput. Vis. (IJCV) 127 (2019) 1455\u20131473.","DOI":"10.1007\/s11263-019-01197-x"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"e_1_3_3_1_8_2","unstructured":"Blender. 2024. https:\/\/www.blender.org\/ (2024)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.598"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1198555.1198593"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Chen Cao Tomas Simon Jin\u00a0Kyu Kim Gabriel Schwartz Michael Zollhoefer Shun-Suke Saito Stephen Lombardi Shih-En Wei Danielle Belko Shoou-I Yu Yaser Sheikh and Jason Saragih. 2022. Authentic volumetric avatars from a phone scan. ACM Trans. Graph. (TOG) 41 4 (2022) 1\u20139.","DOI":"10.1145\/3528223.3530143"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Chen Cao Yanlin Weng Shun Zhou Yiying Tong and Kun Zhou. 2013. FaceWarehouse: A 3D facial expression database for visual computing. IEEE Trans. Vis. Comput. Graph. (TVCG) 20 3 (2013) 413\u2013425.","DOI":"10.1109\/TVCG.2013.249"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1862"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.335"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Yao Feng Haiwen Feng Michael\u00a0J Black and Timo Bolkart. 2021. Learning an animatable detailed 3D face model from in-the-wild images. ACM Trans. Graph. (TOG) 40 4 (2021) 1\u201313.","DOI":"10.1145\/3450626.3459936"},{"key":"e_1_3_3_1_20_2","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. (TOG) 41 6 (2022) 1\u201312.","DOI":"10.1145\/3550454.3555501"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02012"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01810"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Kaiwen Guo Peter Lincoln Philip Davidson Jay Busch Xueming Yu Matt Whalen Geoff Harvey Sergio Orts-Escolano Rohit Pandey Jason Dourgarian Danhang Tang Anastasia Tkach Adarsh Kowdle Emily Cooper Mingsong Dou Sean Fanello Graham Fyffe Christoph Rhemann Jonathan Taylor Paul Debevec and Shahram Izadi. 2019. The Relightables: Volumetric performance capture of humans with realistic relighting. ACM Trans. Graph. (TOG) 38 6 (2019) 1\u201319.","DOI":"10.1145\/3355089.3356571"},{"key":"e_1_3_3_1_24_2","first-page":"20374","volume-title":"Conf. Comput. Vis. Pattern Recog. (CVPR)","author":"Hong Yang","year":"2022","unstructured":"Yang Hong, Bo Peng, Haiyao Xiao, Ligang Liu, and Juyong Zhang. 2022. HeadNeRF: A real-time nerf-based parametric head model. In Conf. Comput. Vis. Pattern Recog. (CVPR). 20374\u201320384."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_1_26_2","first-page":"23593","volume-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Kawar Bahjat","year":"2022","unstructured":"Bahjat Kawar, Michael Elad, Stefano Ermon, and Jiaming Song. 2022. Denoising diffusion restoration models. In Adv. Neural Inform. Process. Syst. (NeurIPS). 23593\u201323606."},{"key":"e_1_3_3_1_27_2","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. (TOG) 36 6 (2017) 194\u20131.","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Leyuan Liu Xu Liu Jianchi Sun Changxin Gao and Jingying Chen. 2024. SeIF: Semantic-Constrained Deep Implicit Function for Single-Image 3D Head Reconstruction. IEEE Trans. Multimedia (TMM) 26 (2024) 10106\u201310120.","DOI":"10.1109\/TMM.2024.3405721"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803452"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Stephen Lombardi Jason Saragih Tomas Simon and Yaser Sheikh. 2018. Deep appearance models for face rendering. ACM Trans. Graph. (TOG) 37 4 (2018) 1\u201313.","DOI":"10.1145\/3197517.3201401"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01179"},{"key":"e_1_3_3_1_33_2","volume-title":"Int. Conf. Learn. Represent. (ICLR)","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 Int. Conf. Learn. Represent. (ICLR)."},{"key":"e_1_3_3_1_34_2","first-page":"13503","volume-title":"Conf. Comput. Vis. Pattern Recog. (CVPR)","author":"Or-El Roy","year":"2022","unstructured":"Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong\u00a0Joon Park, and Ira Kemelmacher-Shlizerman. 2022. StyleSDF: High-resolution 3D-consistent image and geometry generation. In Conf. Comput. Vis. Pattern Recog. (CVPR). 13503\u201313513."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00809"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Stylianos Ploumpis Evangelos Ververas Eimear O\u2019Sullivan Stylianos Moschoglou Haoyang Wang Nick Pears William\u00a0AP Smith Baris Gecer and Stefanos Zafeiriou. 2020. Towards a complete 3D morphable model of the human head. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 43 11 (2020) 4142\u20134160.","DOI":"10.1109\/TPAMI.2020.2991150"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00557"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00984"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02437"},{"key":"e_1_3_3_1_44_2","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Wang Zhengyi","year":"2024","unstructured":"Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, and Jun Zhu. 2024. CRM: Single image to 3D textured mesh with convolutional reconstruction model. In Eur. Conf. Comput. Vis. (ECCV)."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"e_1_3_3_1_46_2","volume-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Wu Kailu","year":"2024","unstructured":"Kailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan, Hanyang Wang, Yating Hu, Yueqi Duan, and Kaisheng Ma. 2024. Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image. In Adv. Neural Inform. Process. Syst. (NeurIPS)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01261"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00825"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618180"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Longwen Zhang Qiwei Qiu Hongyang Lin Qixuan Zhang Cheng Shi Wei Yang Ye Shi Sibei Yang Lan Xu and Jingyi Yu. 2023. DreamFace: Progressive generation of animatable 3d faces under text guidance. ACM Trans. Graph. (TOG) (2023) 42(4).","DOI":"10.1145\/3592094"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00129"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_15"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Michael Zollh\u00f6fer Justus Thies Pablo Garrido Derek Bradley Thabo Beeler Patrick P\u00e9rez Marc Stamminger Matthias Nie\u00dfner and Christian Theobalt. 2018. State of the art on monocular 3D face reconstruction tracking and applications. Comput. Graph. Forum (CGF) 37 2 (2018) 523\u2013550.","DOI":"10.1111\/cgf.13382"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:09:12Z","timestamp":1781536152000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":53,"alternative-id":["10.1145\/3805622.3810572","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810572","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}