{"id":"https://openalex.org/W4417125622","doi":"https://doi.org/10.1145/3757377.3763839","title":"Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement","display_name":"Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125622","doi":"https://doi.org/10.1145/3757377.3763839"},"language":"en","primary_location":{"id":"doi:10.1145/3757377.3763839","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763839","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757377.3763839","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101892130","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0002-6503-8312"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6503-8312","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086762510","display_name":"B. Zhang","orcid":"https://orcid.org/0009-0005-9489-7385"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo-Tao Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9489-7385","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632779","display_name":"Fenglin Liu","orcid":"https://orcid.org/0009-0007-4736-8100"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng-Lin Liu","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4736-8100","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616579","display_name":"Hongbo Fu","orcid":"https://orcid.org/0000-0002-0284-726X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongbo Fu","raw_affiliation_strings":["Division of Arts and Machine Creativity, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0284-726X","affiliations":[{"raw_affiliation_string":"Division of Arts and Machine Creativity, Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067850699","display_name":"Yu\u2010Kun Lai","orcid":"https://orcid.org/0000-0002-2094-5680"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu-Kun Lai","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2094-5680","affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100629376","display_name":"Lin Gao","orcid":"https://orcid.org/0000-0002-1021-8148"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gao","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1021-8148","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5475999712944031,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5475999712944031,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.17589999735355377,"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/T11448","display_name":"Face recognition and analysis","score":0.08089999854564667,"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/prior-probability","display_name":"Prior probability","score":0.6287000179290771},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5063999891281128},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4690999984741211},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4505000114440918},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4327000081539154},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3767000138759613},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3628000020980835},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.805899977684021},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7430999875068665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697700023651123},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6287000179290771},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.3208000063896179},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C104317376","wikidata":"https://www.wikidata.org/wiki/Q1894545","display_name":"Gaussian blur","level":5,"score":0.2703000009059906},{"id":"https://openalex.org/C68516990","wikidata":"https://www.wikidata.org/wiki/Q452912","display_name":"Subpixel rendering","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3757377.3763839","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763839","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:183216","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169935","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169935","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3757377.3763839","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763839","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2133665775","https://openalex.org/W2134484928","https://openalex.org/W2486034530","https://openalex.org/W2769666294","https://openalex.org/W2793768642","https://openalex.org/W2887358179","https://openalex.org/W2962785568","https://openalex.org/W2963669509","https://openalex.org/W2963995996","https://openalex.org/W2969985801","https://openalex.org/W2971467054","https://openalex.org/W2978956737","https://openalex.org/W2979283733","https://openalex.org/W2981637078","https://openalex.org/W2981978060","https://openalex.org/W2997691263","https://openalex.org/W3035291735","https://openalex.org/W3035551320","https://openalex.org/W3035678981","https://openalex.org/W3107197814","https://openalex.org/W3166229844","https://openalex.org/W3176327543","https://openalex.org/W3202804820","https://openalex.org/W4200150166","https://openalex.org/W4214625585","https://openalex.org/W4224640185","https://openalex.org/W4226160668","https://openalex.org/W4285799444","https://openalex.org/W4292261862","https://openalex.org/W4312311094","https://openalex.org/W4312453532","https://openalex.org/W4312607553","https://openalex.org/W4312809617","https://openalex.org/W4312891300","https://openalex.org/W4312933868","https://openalex.org/W4313175219","https://openalex.org/W4321021445","https://openalex.org/W4385318467","https://openalex.org/W4385527580","https://openalex.org/W4386065887","https://openalex.org/W4386071566","https://openalex.org/W4386075534","https://openalex.org/W4386075660","https://openalex.org/W4386075804","https://openalex.org/W4386076247","https://openalex.org/W4390190334","https://openalex.org/W4390872905","https://openalex.org/W4390873331","https://openalex.org/W4390873430","https://openalex.org/W4390874168","https://openalex.org/W4393148031","https://openalex.org/W4399563558","https://openalex.org/W4399574593","https://openalex.org/W4400573547","https://openalex.org/W4400822286","https://openalex.org/W4402667904","https://openalex.org/W4402703090","https://openalex.org/W4402704510","https://openalex.org/W4402716022","https://openalex.org/W4402733585","https://openalex.org/W4402753521","https://openalex.org/W4402754215","https://openalex.org/W4402951568","https://openalex.org/W4403792297","https://openalex.org/W4403842396","https://openalex.org/W4403942132","https://openalex.org/W4404525697","https://openalex.org/W4404719810","https://openalex.org/W4413156432","https://openalex.org/W4413157673"],"related_works":[],"abstract_inverted_index":{"Creating":[0],"high-quality,":[1],"photorealistic":[2,214],"3D":[3,34,134,152,164,180],"digital":[4],"humans":[5],"from":[6,24,218],"a":[7,51,64,68,79,219],"single":[8,220],"image":[9,70,129,171],"remains":[10],"challenging.":[11],"While":[12],"existing":[13,229],"methods":[14],"can":[15],"generate":[16],"visually":[17],"appealing":[18],"multi-view":[19,124,169,210],"outputs,":[20],"they":[21],"often":[22],"suffer":[23],"inconsistencies":[25],"in":[26,32,67],"viewpoints":[27],"and":[28,87,101,126,141,163,194,205,215,234],"camera":[29],"poses,":[30],"resulting":[31],"suboptimal":[33],"reconstructions":[35],"with":[36,132],"reduced":[37],"realism.":[38],"Furthermore,":[39],"most":[40],"approaches":[41],"focus":[42],"on":[43,150,167],"body":[44],"generation":[45],"while":[46],"overlooking":[47],"facial":[48,92,99,103,175,185,199],"consistency":[49,140,166],"\u2013":[50],"perceptually":[52],"critical":[53],"issue":[54],"caused":[55],"by":[56],"the":[57,60,91,114,133,146,156,206],"fact":[58],"that":[59,225],"face":[61],"occupies":[62],"only":[63],"small":[65],"area":[66],"full-body":[69],"(e.g.,":[71],"\u223c":[72],"80":[73,75],"\u00d7":[74,81],"pixels":[76],"out":[77],"of":[78,117,208],"512":[80,82],"image).":[83],"This":[84],"limited":[85],"resolution":[86],"low":[88],"weight":[89],"for":[90,122],"regions":[93],"during":[94],"optimization":[95,182],"leads":[96],"to":[97,137,183,197],"insufficient":[98],"details":[100],"inconsistent":[102],"identity":[104],"features":[105],"across":[106],"multiple":[107],"views.To":[108],"address":[109],"these":[110],"challenges,":[111],"we":[112,191],"leverage":[113],"powerful":[115],"capabilities":[116],"2D":[118],"video":[119],"diffusion":[120],"models":[121,148],"consistent":[123,216],"RGB":[125],"Normal":[127],"human":[128,153,170,236],"generation,":[130],"combined":[131],"SMPL-X":[135,202],"representation":[136],"enable":[138],"spatial":[139],"geometrical":[142],"details.":[143,186],"By":[144],"fine-tuning":[145],"DiT":[147],"(HumanWan-DiTs)":[149],"realistic":[151,168],"datasets":[154],"using":[155],"LoRA":[157],"technique,":[158],"our":[159,226],"method":[160],"ensuresboth":[161],"generalizability":[162],"visual":[165],"generation.":[172],"The":[173],"proposed":[174],"enhancement":[176],"is":[177],"integrated":[178],"into":[179],"Gaussian":[181],"enhance":[184],"To":[187],"further":[188],"refine":[189],"results,":[190],"apply":[192],"super-resolution":[193],"generative":[195],"priors":[196],"reduce":[198],"blurring":[200],"alongside":[201],"parameter":[203],"tuning":[204],"assistance":[207],"generated":[209],"normal":[211],"images,":[212],"achieving":[213],"rendering":[217],"image.":[221],"Extensive":[222],"experiments":[223],"demonstrate":[224],"approach":[227],"outperforms":[228],"methods,":[230],"producing":[231],"photorealistic,":[232],"consistent,":[233],"fine-detailed":[235],"renderings.":[237]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-08T00:00:00"}