{"id":"https://openalex.org/W4415536745","doi":"https://doi.org/10.1145/3746027.3755774","title":"SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction","display_name":"SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536745","doi":"https://doi.org/10.1145/3746027.3755774"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755774","doi":"https://doi.org/10.1145/3746027.3755774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755774","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021098663","display_name":"Gangjian Zhang","orcid":"https://orcid.org/0000-0003-1503-4513","observed_orcids":["https://orcid.org/0000-0003-1503-4513"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangjian Zhang","raw_affiliation_strings":["HKUST(GZ), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1503-4513","affiliations":[{"raw_affiliation_string":"HKUST(GZ), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Shu","orcid":"https://orcid.org/0009-0007-4734-2058","observed_orcids":["https://orcid.org/0009-0007-4734-2058"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Shu","raw_affiliation_strings":["HKUST(GZ), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4734-2058","affiliations":[{"raw_affiliation_string":"HKUST(GZ), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102674783","display_name":"Nanjie Yao","orcid":"https://orcid.org/0009-0007-4930-7758","observed_orcids":["https://orcid.org/0009-0007-4930-7758"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanjie Yao","raw_affiliation_strings":["HKUST(GZ), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4930-7758","affiliations":[{"raw_affiliation_string":"HKUST(GZ), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100446112","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3086-3128","observed_orcids":["https://orcid.org/0000-0002-3086-3128","https://orcid.org/0000-0003-1662-2480"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["HKUST(GZ), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3086-3128","affiliations":[{"raw_affiliation_string":"HKUST(GZ), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405261251"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35630368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10563","last_page":"10572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/3d-avatar-generation","display_name":"3D avatar generation","score":0.7289999723434448},{"id":"https://openalex.org/keywords/geometric-ambiguity","display_name":"geometric ambiguity","score":0.48500001430511475},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.5609999895095825},{"id":"https://openalex.org/keywords/smpl","display_name":"SMPL","score":0.3880000114440918},{"id":"https://openalex.org/keywords/normal-maps","display_name":"normal maps","score":0.7829999923706055},{"id":"https://openalex.org/keywords/facial-distortion","display_name":"facial distortion","score":0.5609999895095825}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.73580002784729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006000280380249},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6840999722480774},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.3091999888420105},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.2921000123023987},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755774","doi":"https://doi.org/10.1145/3746027.3755774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755774","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2939665722","https://openalex.org/W2962785568","https://openalex.org/W3104898586","https://openalex.org/W3107271392","https://openalex.org/W3174025609","https://openalex.org/W4200150166","https://openalex.org/W4367622621","https://openalex.org/W4385318467","https://openalex.org/W4385489997","https://openalex.org/W4386075660","https://openalex.org/W4386075747","https://openalex.org/W4402727576","https://openalex.org/W4402727627","https://openalex.org/W4402753800","https://openalex.org/W4408564952"],"related_works":["https://openalex.org/W7134094127","https://openalex.org/W4416380234","https://openalex.org/W4413298894","https://openalex.org/W4413156118","https://openalex.org/W3016099659","https://openalex.org/W3127639500","https://openalex.org/W4415707665","https://openalex.org/W4417082030","https://openalex.org/W7162304655","https://openalex.org/W7160401076"],"abstract_inverted_index":{"Monocular":[0],"texture":[1],"3D":[2,10,35,96,115,190],"human":[3,18,36,62,97,191],"reconstruction":[4,98,164],"aims":[5],"to":[6,59,76,82,142,209],"create":[7],"a":[8,15,27,94,108,128,135,176,182],"complete":[9],"digital":[11],"avatar":[12],"from":[13,187],"just":[14],"single":[16,28],"front-view":[17],"RGB":[19],"image.":[20],"However,":[21,73],"the":[22,32,40,67,118,139,188,203],"geometric":[23,56,63,151],"ambiguity":[24],"inherent":[25],"in":[26,45,107],"2D":[29],"image":[30],"and":[31,70,111,161],"scarcity":[33,160],"of":[34,185,205],"training":[37,147],"data":[38,159,192],"are":[39],"main":[41],"obstacles":[42],"limiting":[43],"progress":[44],"this":[46,90],"field.":[47],"To":[48,89,121,157],"address":[49],"these":[50,78,149],"issues,":[51],"current":[52],"methods":[53],"employ":[54],"prior":[55,105],"estimation":[57],"networks":[58],"derive":[60],"various":[61,104],"forms,":[64],"such":[65,85],"as":[66,86,117,146],"SMPL":[68],"model":[69,195],"normal":[71],"maps.":[72],"they":[74],"struggle":[75],"integrate":[77],"modalities":[79],"effectively,":[80],"leading":[81],"view":[83],"inconsistencies,":[84],"facial":[87],"distortions.":[88],"end,":[91],"we":[92,126,166,180],"propose":[93,168],"two-process":[95],"framework,":[99],"SAT,":[100],"which":[101],"seamlessly":[102],"learns":[103],"geometries":[106],"unified":[109],"manner":[110],"reconstructs":[112],"high-quality":[113],"textured":[114],"avatars":[116],"final":[119],"output.":[120],"further":[122,162],"facilitate":[123],"geometry":[124],"learning,":[125],"introduce":[127],"Supervisor":[129],"Feature":[130],"Regularization":[131],"module.":[132,173],"By":[133,174],"employing":[134],"multi-view":[136],"network":[137],"with":[138],"same":[140],"structure":[141],"provide":[143],"intermediate":[144],"features":[145],"supervision,":[148],"varied":[150],"priors":[152],"can":[153],"be":[154],"better":[155],"fused.":[156],"tackle":[158],"improve":[163],"quality,":[165],"also":[167],"an":[169],"Online":[170],"Animation":[171],"Augmentation":[172],"building":[175],"one-feed-forward":[177],"animation":[178],"network,":[179],"augment":[181],"massive":[183],"number":[184],"samples":[186],"original":[189],"online":[193],"for":[194],"training.":[196],"Extensive":[197],"experiments":[198],"on":[199],"two":[200],"benchmarks":[201],"show":[202],"superiority":[204],"our":[206],"approach":[207],"compared":[208],"state-of-the-art":[210],"methods.":[211]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-10-25T00:00:00"}