{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:57:24Z","timestamp":1776931044929,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003513","name":"University of Surrey","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003513","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1145\/3756863.3769705","type":"proceedings-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T07:15:50Z","timestamp":1763450150000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Realistic Clothed Human and Object Joint Reconstruction from a Single Image"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6958-5017","authenticated-orcid":false,"given":"Ayushi","family":"Dutta","sequence":"first","affiliation":[{"name":"University of Surrey, Guildford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2379-6593","authenticated-orcid":false,"given":"Marco","family":"Pesavento","sequence":"additional","affiliation":[{"name":"Meta, Redmond, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1869-9257","authenticated-orcid":false,"given":"Marco","family":"Volino","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4223-238X","authenticated-orcid":false,"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1779-2775","authenticated-orcid":false,"given":"Armin","family":"Mustafa","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00855"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Rongshan Chen Yuancheng Yang and Chao Tong. 2023. G2IFu: Graph-based implicit function for single-view 3D reconstruction. Engineering Applications of Artificial Intelligence 124 (2023) 106493.","DOI":"10.1016\/j.engappai.2023.106493"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00874"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"George Fahim Khalid Amin and Sameh Zarif. 2022. Enhancing single-view 3D mesh reconstruction with the aid of implicit surface learning. Image and Vision Computing 119 (2022) 104377.","DOI":"10.1016\/j.imavis.2022.104377"},{"key":"e_1_3_3_2_8_1","unstructured":"Tong He John Collomosse Hailin Jin and Stefano Soatto. 2020. Geo-pifu: Geometry and pixel aligned implicit functions for single-view human reconstruction. Advances in Neural Information Processing Systems 33 (2020) 9276\u20139287."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","unstructured":"Yinghao Huang Omid Taheri Michael\u00a0J. Black and Dimitrios Tzionas. 2024. InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction from Multi-view RGB-D Images. International Journal of Computer Vision (IJCV) (2024). 10.1007\/s11263-024-01984-1","DOI":"10.1007\/s11263-024-01984-1"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00606"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00065"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Nikos Kolotouros Thiemo Alldieck Enric Corona Eduard\u00a0Gabriel Bazavan and Cristian Sminchisescu. 2024. Instant 3D Human Avatar Generation using Image Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.07516 (2024).","DOI":"10.1007\/978-3-031-73021-4_11"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01011"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"e_1_3_3_2_18_1","unstructured":"Shichen Liu Shunsuke Saito Weikai Chen and Hao Li. 2019. Learning to infer implicit surfaces without 3d supervision. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"William\u00a0E Lorensen and Harvey\u00a0E Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm. ACM siggraph computer graphics 21 4 (1987) 163\u2013169.","DOI":"10.1145\/37402.37422"},{"key":"e_1_3_3_2_20_1","volume-title":"Third workshop on computer vision for AR\/VR at IEEE computer vision and pattern recognition (CVPR)","author":"Lugaresi Camillo","year":"2019","unstructured":"Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming Yong, Juhyun Lee, et\u00a0al. 2019. Mediapipe: A framework for perceiving and processing reality. In Third workshop on computer vision for AR\/VR at IEEE computer vision and pattern recognition (CVPR) , Vol.\u00a02019."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00973"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_26"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_12"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00521"},{"key":"e_1_3_3_2_27_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Javier Romero Dimitrios Tzionas and Michael\u00a0J. Black. 2017. Embodied Hands: Modeling and Capturing Hands and Bodies Together. ACM Transactions on Graphics (Proc. SIGGRAPH Asia) 36 6 (Nov. 2017).","DOI":"10.1145\/3130800.3130883"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00143"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475442"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Jianyuan Wang Huanqiang Xu Xinrui Hu and Biao Leng. 2023. IFKD: Implicit field knowledge distillation for single view reconstruction. Mathematical Biosciences and Engineering 20 8 (2023) 13864\u201313880.","DOI":"10.3934\/mbe.2023617"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00047"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00954"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00461"},{"key":"e_1_3_3_2_41_1","unstructured":"Xianghui Xie Jan\u00a0Eric Lenssen and Gerard Pons-Moll. 2024b. InterTrack: Tracking Human Object Interaction without Object Templates. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.13953 (2024)."},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"e_1_3_3_2_44_1","unstructured":"Qiangeng Xu Weiyue Wang Duygu Ceylan Radomir Mech and Ulrich Neumann. 2019. Disn: Deep implicit surface network for high-quality single-view 3d reconstruction. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_45_1","unstructured":"Xiang Xu Hanbyul Joo Greg Mori and Manolis Savva. 2021. D3d-hoi: Dynamic 3d human-object interactions from videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.08420 (2021)."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"e_1_3_3_2_47_1","unstructured":"Zehao Yu Songyou Peng Michael Niemeyer Torsten Sattler and Andreas Geiger. 2022. Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction. Advances in neural information processing systems 35 (2022) 25018\u201325032."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00853"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_3"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC53003.2021.9728714"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"crossref","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 44 6 (2021) 3170\u20133184.","DOI":"10.1109\/TPAMI.2021.3050505"}],"event":{"name":"CVMP '25: European Conference on Visual Media Production","location":"London United Kingdom","acronym":"CVMP '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 22nd ACM SIGGRAPH European Conference on Visual Media Production"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3756863.3769705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T20:50:01Z","timestamp":1767905401000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3756863.3769705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":51,"alternative-id":["10.1145\/3756863.3769705","10.1145\/3756863"],"URL":"https:\/\/doi.org\/10.1145\/3756863.3769705","relation":{},"subject":[],"published":{"date-parts":[[2025,12,2]]},"assertion":[{"value":"2025-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}