{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T14:01:55Z","timestamp":1780063315487,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Grants Council (RGC) of Hong Kong","award":["STG1\/E-403\/24-N"],"award-info":[{"award-number":["STG1\/E-403\/24-N"]}]},{"name":"Research Grants Council (RGC) of Hong Kong","award":["CRF C4032-25E"],"award-info":[{"award-number":["CRF C4032-25E"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,21]]},"DOI":"10.1145\/3745756.3809219","type":"proceedings-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:52:21Z","timestamp":1780059141000},"page":"506-519","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HoloMobile: Photorealistic Avatar on Mobile via Compact Dynamic Gaussians from a Monocular Video"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1954-952X","authenticated-orcid":false,"given":"Yuting","family":"He","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-8280","authenticated-orcid":false,"given":"Yihua","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1455-7809","authenticated-orcid":false,"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4433-5211","authenticated-orcid":false,"given":"Zhenyu","family":"Yan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1772-7751","authenticated-orcid":false,"given":"Guoliang","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference. 10723\u201310734","author":"Chen Jianchuan","year":"2025","unstructured":"Jianchuan Chen, Jingchuan Hu, Gaige Wang, Zhonghua Jiang, Tiansong Zhou, Zhiwen Chen, and Chengfei Lv. 2025. TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting. In Proceedings of the Computer Vision and Pattern Recognition Conference. 10723\u201310734."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Yushuo Chen Zerong Zheng Zhe Li Chao Xu and Yebin Liu. 2024. MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos. arXiv:2407.08414 [cs.CV] https:\/\/arxiv.org\/abs\/2407.08414","DOI":"10.1007\/978-3-031-73113-6_15"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 365\u2013379","author":"Cheng Ruizhi","year":"2024","unstructured":"Ruizhi Cheng, Nan Wu, Vu Le, Eugene Chai, Matteo Varvello, and Bo Han. 2024. Magicstream: Bandwidth-conserving immersive telepresence via semantic communication. In Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 365\u2013379."},{"key":"e_1_3_2_1_4_1","unstructured":"MMPose Contributors. 2020. OpenMMLab Pose Estimation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmpose."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 1162\u20131176","author":"Fang Tiancheng","year":"2024","unstructured":"Tiancheng Fang, Chaoyue Niu, Yujie Sun, Chengfei Lv, Xiaotang Jiang, Ben Xue, Fan Wu, and Guihai Chen. 2024. An End-to-End, Low-Cost, and High-Fidelity 3D Video Pipeline for Mobile Devices. In Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 1162\u20131176."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Yao Feng Haiwen Feng Michael J. Black and Timo Bolkart. 2021. Learning an Animatable Detailed 3D Face Model from In-The-Wild Images. ACM Transactions on Graphics (Proc. SIGGRAPH) 40 8. 10.1145\/3450626.3459936","DOI":"10.1145\/3450626.3459936"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.12"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592530"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Guo Chen","year":"2025","unstructured":"Chen Guo, Junxuan Li, Yash Kant, Yaser Sheikh, Shunsuke Saito, and Chen Cao. 2025. Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3380888"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Forrest Iandola Stanislav Pidhorskyi Igor Santesteban Divam Gupta Anuj Pahuja Nemanja Bartolovic Frank Yu Emanuel Garbin Tomas Simon and Shunsuke Saito. 2025. SqueezeMe: Mobile-Ready Distillation of Gaussian Full-Body Avatars. In SIGGRAPH. ACM. https:\/\/arxiv.org\/abs\/2412.15171","DOI":"10.1145\/3721238.3730599"},{"key":"e_1_3_2_1_16_1","first-page":"20067","article-title":"Motiongpt: Human motion as a foreign language","volume":"36","author":"Jiang Biao","year":"2023","unstructured":"Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. 2023. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2023), 20067\u201320079.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the European conference on computer vision (ECCV).","author":"Jiang Wei","year":"2022","unstructured":"Wei Jiang, Kwang Moo Yi, Golnoosh Samei, Oncel Tuzel, and Anurag Ranjan. 2022. NeuMan: Neural Human Radiance Field from a Single Video. In Proceedings of the European conference on computer vision (ECCV)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680207.3765245"},{"key":"e_1_3_2_1_20_1","unstructured":"Mark Kellogg. 2024. GaussianSplats3D: Three.js-based implementation of 3D Gaussian splatting. https:\/\/github.com\/mkkellogg\/GaussianSplats3D"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680207.3765267"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_2_1_25_1","unstructured":"Kevin Kwok. 2023. splat: WebGL implementation of a real-time renderer for 3D Gaussian Splatting for Real-Time Radiance Field Rendering. https:\/\/github.com\/antimatter15\/splat"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711875.3729131"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592525"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419214"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596796"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517027"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649364"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_1_36_1","volume-title":"Computer Vision and Pattern Recognition Workshop (CVPRW).","author":"Moon Gyeongsik","year":"2022","unstructured":"Gyeongsik Moon, Hongsuk Choi, and Kyoung Mu Lee. 2022. Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation. In Computer Vision and Pattern Recognition Workshop (CVPRW)."},{"key":"e_1_3_2_1_37_1","volume-title":"European Conference on Computer Vision. Springer, 19\u201335","author":"Moon Gyeongsik","year":"2024","unstructured":"Gyeongsik Moon, Takaaki Shiratori, and Shunsuke Saito. 2024. Expressive whole-body 3D gaussian avatar. In European Conference on Computer Vision. Springer, 19\u201335."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 788\u2013798","author":"Moreau Arthur","year":"2024","unstructured":"Arthur Moreau, Jifei Song, Helisa Dhamo, Richard Shaw, Yiren Zhou, and Eduardo P\u00e9rez-Pellitero. 2024. Human gaussian splatting: Real-time rendering of animatable avatars. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 788\u2013798."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984517"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00117"},{"key":"e_1_3_2_1_41_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 10975\u201310985","author":"Pavlakos Georgios","unstructured":"Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, and Michael J. Black. 2019. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 10975\u201310985."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766993"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Kaiyue Shen Chen Guo Manuel Kaufmann Juan Zarate Julien Valentin Jie Song and Otmar Hilliges. 2023. X-Avatar: Expressive Human Avatars. Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR52729.2023.01622"},{"key":"e_1_3_2_1_47_1","volume-title":"HRM\u02c6 2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone Scans. arXiv preprint arXiv:2510.13587","author":"Shi Chao","year":"2025","unstructured":"Chao Shi, Shenghao Jia, Jinhui Liu, Yong Zhang, Liangchao Zhu, Zhonglei Yang, Jinze Ma, Chaoyue Niu, and Chengfei Lv. 2025. HRM\u02c6 2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone Scans. arXiv preprint arXiv:2510.13587 (2025)."},{"key":"e_1_3_2_1_48_1","volume-title":"2025 International Conference on 3D Vision (3DV). IEEE, 991\u20131000","author":"Shi Yuang","year":"2025","unstructured":"Yuang Shi, G\u00e9raldine Morin, Simone Gasparini, and Wei Tsang Ooi. 2025. Lapisgs: Layered progressive 3d gaussian splatting for adaptive streaming. In 2025 International Conference on 3D Vision (3DV). IEEE, 991\u20131000."},{"key":"e_1_3_2_1_49_1","volume-title":"Computer Graphics Forum","author":"Stam Jos","unstructured":"Jos Stam and Charles Loop. 2003. Quad\/triangle subdivision. In Computer Graphics Forum, Vol. 22. Wiley Online Library, 79\u201385."},{"key":"e_1_3_2_1_50_1","volume-title":"A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose. Advances in neural information processing systems 34","author":"Su Shih-Yang","year":"2021","unstructured":"Shih-Yang Su, Frank Yu, Michael Zollh\u00f6fer, and Helge Rhodin. 2021. A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose. Advances in neural information processing systems 34 (2021), 12278\u201312291."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712676.3714445"},{"key":"e_1_3_2_1_52_1","volume-title":"L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery. arXiv preprint arXiv:2504.05517","author":"Tsai Yi-Zhen","year":"2025","unstructured":"Yi-Zhen Tsai, Xuechen Zhang, Zheng Li, and Jiasi Chen. 2025. L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery. arXiv preprint arXiv:2504.05517 (2025)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687935"},{"key":"e_1_3_2_1_54_1","volume-title":"Motiongpt-2: A general-purpose motion-language model for motion generation and understanding. arXiv preprint arXiv:2410.21747","author":"Wang Yuan","year":"2024","unstructured":"Yuan Wang, Di Huang, Yaqi Zhang, Wanli Ouyang, Jile Jiao, Xuetao Feng, Yan Zhou, Pengfei Wan, Shixiang Tang, and Dan Xu. 2024. Motiongpt-2: A general-purpose motion-language model for motion generation and understanding. arXiv preprint arXiv:2410.21747 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600\u2013612."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00201"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"e_1_3_2_1_58_1","first-page":"14955","article-title":"H-nerf: Neural radiance fields for rendering and temporal reconstruction of humans in motion","volume":"34","author":"Xu Hongyi","year":"2021","unstructured":"Hongyi Xu, Thiemo Alldieck, and Cristian Sminchisescu. 2021. H-nerf: Neural radiance fields for rendering and temporal reconstruction of humans in motion. Advances in Neural Information Processing Systems 34 (2021), 14955\u201314966.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711875.3729140"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"e_1_3_2_1_61_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems.","author":"Yuan Yuheng","year":"2025","unstructured":"Yuheng Yuan, Qiuhong Shen, Xingyi Yang, and Xinchao Wang. 2025. 1000+ fps 4d gaussian splatting for dynamic scene rendering. In The Thirty-ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_62_1","volume-title":"YuZu: Neural-Enhanced Volumetric Video Streaming. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Zhang Anlan","year":"2022","unstructured":"Anlan Zhang, Chendong Wang, Bo Han, and Feng Qian. 2022. YuZu: Neural-Enhanced Volumetric Video Streaming. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 137\u2013154."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3742889.3768345"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 27828\u201327838","author":"Zhang Xinjie","year":"2025","unstructured":"Xinjie Zhang, Zhening Liu, Yifan Zhang, Xingtong Ge, Dailan He, Tongda Xu, Yan Wang, Zehong Lin, Shuicheng Yan, and Jun Zhang. 2025. Mega: Memory-efficient 4d gaussian splatting for dynamic scenes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 27828\u201327838."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592101","article-title":"Avatarrex: Real-time expressive full-body avatars","volume":"42","author":"Zheng Zerong","year":"2023","unstructured":"Zerong Zheng, Xiaochen Zhao, Hongwen Zhang, Boning Liu, and Yebin Liu. 2023. Avatarrex: Real-time expressive full-body avatars. ACM Transactions on Graphics (TOG) 42, 4 (2023), 1\u201319.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712676.3714437"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383300"}],"event":{"name":"MobiSys '26: 24th Annual International Conference on Mobile Systems, Applications and Services","location":"University of Cambridge Cambridge United Kingdom","acronym":"MobiSys '26","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 24th Annual International Conference on Mobile Systems, Applications and Services"],"original-title":[],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T13:02:43Z","timestamp":1780059763000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3745756.3809219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":68,"alternative-id":["10.1145\/3745756.3809219","10.1145\/3745756"],"URL":"https:\/\/doi.org\/10.1145\/3745756.3809219","relation":{},"subject":[],"published":{"date-parts":[[2026,6,20]]},"assertion":[{"value":"2026-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}