{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:23:30Z","timestamp":1769631810351,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":82,"publisher":"ACM","funder":[{"name":"State Secretariat for Education, Research and Innovation SERI","award":["AI-PERCEIVE"],"award-info":[{"award-number":["AI-PERCEIVE"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763978","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PriorAvatar: Efficient and Robust Avatar Creation from Monocular Video Using Learned Priors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1702-5409","authenticated-orcid":false,"given":"Tianjian","family":"Jiang","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8683-7538","authenticated-orcid":false,"given":"Hsuan-I","family":"Ho","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5309-319X","authenticated-orcid":false,"given":"Manuel","family":"Kaufmann","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7484-1937","authenticated-orcid":false,"given":"Jie","family":"Song","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Guangzhou, China and Hong Kong University of Science and Technology, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Matthieu Armando Laurence Boissieux Edmond Boyer Jean-Sebastien Franco Martin Humenberger Christophe Legras Vincent Leroy Mathieu Marsot Julien Pansiot Sergi Pujades Rim Rekik Gregory Rogez Anilkumar Swamy and Stefanie Wuhrer. 2023. 4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements. Computer Vision and Image Understanding (2023).","DOI":"10.1016\/j.cviu.2023.103836"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Marcel\u00a0C Buehler Gengyan Li Erroll Wood Leonhard Helminger Xu Chen Tanmay Shah Daoye Wang Stephan Garbin Sergio Orts-Escolano Otmar Hilliges et\u00a0al. 2024. Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures. ACM SIGGRAPH Asia 2024 Conference Paper (2024).","DOI":"10.1145\/3680528.3687580"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00315"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Chen Cao Tomas Simon Jin\u00a0Kyu Kim Gabe 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 Transactions on Graphics (TOG) (2022).","DOI":"10.1145\/3528223.3530143"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_3_2_8_1","unstructured":"Jianchuan Chen Ying Zhang Di Kang Xuefei Zhe Linchao Bao Xu Jia and Huchuan Lu. 2021. Animatable Neural Radiance Fields from Monocular RGB Videos. arxiv:https:\/\/arXiv.org\/abs\/2106.13629"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Xu Chen Tianjian Jiang Jie Song Max Rietmann Andreas Geiger Michael\u00a0J Black and Otmar Hilliges. 2023. Fast-SNARF: A fast deformer for articulated neural fields. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2023).","DOI":"10.1109\/TPAMI.2023.3271569"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01978"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Alvaro Collet Ming Chuang Pat Sweeney Don Gillett Dennis Evseev David Calabrese Hugues Hoppe Adam Kirk and Steve Sullivan. 2015. High-quality streamable free-viewpoint video. ACM Transactions on Graphics (TOG) (2015).","DOI":"10.1145\/2766945"},{"key":"e_1_3_3_2_12_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Corona Enric","year":"2023","unstructured":"Enric Corona, Mihai Zanfir, Thiemo Alldieck, Eduard Gabriel\u00a0Bazavan, Andrei Zanfir, and Cristian Sminchisescu. 2023. Structured 3D Features for Reconstructing Relightable and Animatable Avatars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Edilson de Aguiar Carsten Stoll Christian Theobalt Naveed Ahmed Hans-Peter Seidel and Sebastian Thrun. 2008. Performance capture from sparse multi-view video. ACM Transactions on Graphics (TOG) (2008).","DOI":"10.1145\/1399504.1360697"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01982"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01617.x"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.199"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00522"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00510"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Marc Habermann Weipeng Xu Michael Zollh\u00f6fer Gerard Pons-Moll and Christian Theobalt. 2019. LiveCap: Real-Time Human Performance Capture From Monocular Video. ACM Transactions on Graphics (TOG) (2019).","DOI":"10.1145\/3311970"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01237"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01086"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02014"},{"key":"e_1_3_3_2_26_1","unstructured":"Hezhen Hu Zhiwen Fan Tianhao Wu Yihan Xi Seoyoung Lee Georgios Pavlakos Zhangyang Wang et\u00a0al. 2024a. Expressive gaussian human avatars from monocular rgb video. Advances in Neural Information Processing Systems (NeurIPS) (2024)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01930"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01488"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00552"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00019"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/1281957.1281965"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"crossref","unstructured":"Michael Kazhdan and Hugues Hoppe. 2013. Screened poisson surface reconstruction. ACM Transactions on Graphics (TOG) (2013).","DOI":"10.1145\/2487228.2487237"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics (TOG) (2023).","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383078"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_25"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00837"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657501"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Yebin Liu Qionghai Dai and Wenli Xu. 2009. A point-cloud-based multiview stereo algorithm for free-viewpoint video. IEEE Visualization and Computer Graphics (TVCG) (2009).","DOI":"10.1109\/TVCG.2009.88"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01079"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_49_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Moon Gyeongsik","year":"2024","unstructured":"Gyeongsik Moon, Takaaki Shiratori, and Shunsuke Saito. 2024. Expressive Whole-Body 3D Gaussian Avatar. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_50_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 Transactions on Graphics (TOG) (2022).","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01246"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01251"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00117"},{"key":"e_1_3_3_2_54_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Paudel Pramish","year":"2024","unstructured":"Pramish Paudel, Anubhav Khanal, Ajad Chhatkuli, Danda\u00a0Pani Paudel, and Jyoti Tandukar. 2024. iHuman: Instant Animatable Digital Humans From Monocular Videos. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Sida Peng Chen Geng Yuanqing Zhang Yinghao Xu Qianqian Wang Qing Shuai Xiaowei Zhou and Hujun Bao. 2023. Implicit Neural Representations with Structured Latent Codes for Human Body Modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2023).","DOI":"10.1109\/TPAMI.2023.3245815"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00161"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01622"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238446"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"crossref","unstructured":"Jonathan Starck and Adrian Hilton. 2007. Surface capture for performance-based animation. IEEE computer graphics and applications (2007).","DOI":"10.1109\/MCG.2007.68"},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14022"},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14507"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.195"},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00059"},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"e_1_3_3_2_73_1","unstructured":"Yuliang Xiu Yufei Ye Zhen Liu Dimitrios Tzionas and Michael\u00a0J Black. 2024. PuzzleAvatar: Assembling 3D Avatars from Personal Albums. ACM Transactions on Graphics (TOG) (2024)."},{"key":"e_1_3_3_2_74_1","unstructured":"Weipeng Xu Avishek Chatterjee Michael Zollh\u00f6fer Helge Rhodin Dushyant Mehta Hans-Peter Seidel and Christian Theobalt. 2018. MonoPerfCap: Human Performance Capture From Monocular Video. ACM Transactions on Graphics (TOG) (2018)."},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591545"},{"key":"e_1_3_3_2_76_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Xue Lixin","year":"2024","unstructured":"Lixin Xue, Chen Guo, Chengwei Zheng, Fangjinhua Wang, Tianjian Jiang, Hsuan-I Ho, Manuel Kaufmann, Jie Song, and Hilliges Otmar. 2024. HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00077"},{"key":"e_1_3_3_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00948"},{"key":"e_1_3_3_2_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00759"},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"e_1_3_3_2_82_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Zheng Yang","year":"2024","unstructured":"Yang Zheng, Qingqing Zhao, Guandao Yang, Wang Yifan, Donglai Xiang, Florian Dubost, Dmitry Lagun, Thabo Beeler, Federico Tombari, Leonidas Guibas, and Gordon Wetzstein. 2024. PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_83_1","unstructured":"Zerong Zheng Tao Yu Yebin Liu and Qionghai Dai. 2021. PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2021)."}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:28:45Z","timestamp":1765250925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":82,"alternative-id":["10.1145\/3757377.3763978","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763978","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}