{"id":"https://openalex.org/W4226236785","doi":"https://doi.org/10.1109/tmm.2022.3143712","title":"SPG-VTON: Semantic Prediction Guidance for Multi-Pose Virtual Try-on","display_name":"SPG-VTON: Semantic Prediction Guidance for Multi-Pose Virtual Try-on","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226236785","doi":"https://doi.org/10.1109/tmm.2022.3143712"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3143712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3143712","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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/A5026892941","display_name":"Bingwen Hu","orcid":"https://orcid.org/0000-0003-4890-1775"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Bingwen Hu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","ReLER Laborataory, AAII, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4890-1775","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"ReLER Laborataory, AAII, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442358","display_name":"Ping Liu","orcid":"https://orcid.org/0000-0002-3170-3783"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["AU","SG"],"is_corresponding":false,"raw_author_name":"Ping Liu","raw_affiliation_strings":["ReLER Lab, AAII, University of Technology Sydney, Ultimo, NSW, Australia","Center for Frontier Artificial Intelligence Research (CFAR), Agency for Science, Technology, and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3170-3783","affiliations":[{"raw_affiliation_string":"ReLER Lab, AAII, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Center for Frontier Artificial Intelligence Research (CFAR), Agency for Science, Technology, and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034162160","display_name":"Zhedong Zheng","orcid":"https://orcid.org/0000-0002-2434-9050"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["AU","SG"],"is_corresponding":false,"raw_author_name":"Zhedong Zheng","raw_affiliation_strings":["ReLER Laboratory, AAII, University of Technology Sydney, Ultimo, NSW, Australia","NExT++, School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2434-9050","affiliations":[{"raw_affiliation_string":"ReLER Laboratory, AAII, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"NExT++, School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102968758","display_name":"Mingwu Ren","orcid":"https://orcid.org/0000-0001-5576-3281"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwu Ren","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.046,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92684127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"24","issue":null,"first_page":"1233","last_page":"1246"},"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":0.9983999729156494,"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":0.9983999729156494,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9922000169754028,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9894999861717224,"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/computer-science","display_name":"Computer science","score":0.8119986653327942},{"id":"https://openalex.org/keywords/clothing","display_name":"Clothing","score":0.7814496755599976},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7604420781135559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6017544269561768},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5661717653274536},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5438022017478943},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5237172245979309},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5202746987342834},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4550735056400299},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.45194390416145325},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.43839138746261597},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4257444441318512},{"id":"https://openalex.org/keywords/texture-mapping","display_name":"Texture mapping","score":0.4209884703159332},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.413156658411026},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36083561182022095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119986653327942},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.7814496755599976},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7604420781135559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6017544269561768},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5661717653274536},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5438022017478943},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5237172245979309},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5202746987342834},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4550735056400299},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.45194390416145325},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.43839138746261597},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4257444441318512},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.4209884703159332},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.413156658411026},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36083561182022095},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2022.3143712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3143712","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/245847","is_oa":false,"landing_page_url":"https://scholarbank.nus.edu.sg/handle/10635/245847","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Elements","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6588797881","display_name":null,"funder_award_id":"61703209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8812960752","display_name":null,"funder_award_id":"61773117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W2017735937","https://openalex.org/W2057175746","https://openalex.org/W2125389028","https://openalex.org/W2128409098","https://openalex.org/W2133665775","https://openalex.org/W2331128040","https://openalex.org/W2471768434","https://openalex.org/W2502312327","https://openalex.org/W2559085405","https://openalex.org/W2585635281","https://openalex.org/W2593414223","https://openalex.org/W2598915960","https://openalex.org/W2604233003","https://openalex.org/W2725422033","https://openalex.org/W2771558241","https://openalex.org/W2786383677","https://openalex.org/W2792263949","https://openalex.org/W2883309205","https://openalex.org/W2883311563","https://openalex.org/W2939645724","https://openalex.org/W2947387440","https://openalex.org/W2948542554","https://openalex.org/W2954626788","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2962963674","https://openalex.org/W2963049565","https://openalex.org/W2963073614","https://openalex.org/W2963373786","https://openalex.org/W2963466847","https://openalex.org/W2963800363","https://openalex.org/W2964002510","https://openalex.org/W2964050021","https://openalex.org/W2964097473","https://openalex.org/W2981464166","https://openalex.org/W2981959899","https://openalex.org/W2982413914","https://openalex.org/W2984983779","https://openalex.org/W2990737297","https://openalex.org/W2991079364","https://openalex.org/W3013135579","https://openalex.org/W3033682561","https://openalex.org/W3035194714","https://openalex.org/W3035661604","https://openalex.org/W3115879670","https://openalex.org/W3128990302","https://openalex.org/W3132906222","https://openalex.org/W3175714707","https://openalex.org/W3184322134","https://openalex.org/W3206838119","https://openalex.org/W4205474609","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6718379498","https://openalex.org/W6724804524","https://openalex.org/W6738824914","https://openalex.org/W6749927861","https://openalex.org/W6754560582","https://openalex.org/W6762645922","https://openalex.org/W6763562632"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2735770592","https://openalex.org/W1971024059","https://openalex.org/W1502062143","https://openalex.org/W2738456166","https://openalex.org/W4224236531","https://openalex.org/W4291993329","https://openalex.org/W2104495739","https://openalex.org/W2353890843"],"abstract_inverted_index":{"Image-based":[0],"virtual":[1,59,185,219],"try-on":[2,125,186,220],"is":[3,91,250,257],"challenging":[4],"in":[5,162],"fitting":[6],"a":[7,12,38,42,83,97,123,128,153,168,203],"target":[8,39],"in-shop":[9,134],"clothes":[10,36,135,180,193],"onto":[11,37],"reference":[13,84],"person":[14,40,85],"under":[15,41,86,195],"diverse":[16],"human":[17],"poses.":[18,88],"Previous":[19],"works":[20],"focus":[21],"on":[22,231],"preserving":[23,188],"clothing":[24,81,119,164],"details":[25,189],"(":[26],"<italic":[27,267],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,268],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g.,</i>":[29],"texture,":[30],"logos,":[31],"patterns)":[32],"when":[33,53],"transferring":[34],"desired":[35,80,104,118,138,148,192,197],"fixed":[43],"pose.":[44,149,198],"However,":[45],"the":[46,79,103,117,137,142,147,160,163,174,178,183,191,196,209,214,217,223,228,232,239,253,278],"performances":[47],"of":[48,93,190,216],"existing":[49,55],"methods":[50,56,255],"significantly":[51],"dropped":[52],"extending":[54],"to":[57,115,136,141,158,181,207,252,259,277],"multi-pose":[58,71,235],"try-on.":[60],"In":[61,199],"this":[62],"paper,":[63],"we":[64,151,201],"propose":[65],"an":[66],"end-to-end":[67],"Semantic":[68,98],"Prediction":[69,99],"Guidance":[70],"Virtual":[72],"Try-On":[73],"Network":[74],"(SPG-VTON),":[75],"which":[76],"can":[77],"fit":[78],"into":[82],"arbitrary":[87],"Specifically,":[89,150],"SPG-VTON":[90,249],"composed":[92],"three":[94],"sub-modules.":[95],"First,":[96],"Module":[100,131,171],"(SPM)":[101],"generates":[102],"semantic":[105,109,144],"map.":[106],"The":[107,242],"predicted":[108,143],"map":[110,145],"provides":[111],"more":[112],"abundant":[113],"guidance":[114],"locate":[116],"region":[120],"and":[121,146,177,194,212,238,244,256,264,272],"produce":[122],"coarse":[124,175],"image.":[126],"Second,":[127],"Clothes":[129],"Warping":[130],"(CWM)":[132],"warps":[133],"shape":[139],"according":[140],"introduce":[152,202],"conductible":[154],"cycle":[155],"consistency":[156],"loss":[157,206],"alleviate":[159],"misalignment":[161],"warping":[165],"process.":[166],"Third,":[167],"Try-on":[169],"Synthesis":[170],"(TSM)":[172],"combines":[173],"result":[176,221],"warped":[179],"generate":[182],"final":[184,218],"image,":[187],"addition,":[200],"face":[204],"identity":[205,215],"refine":[208],"facial":[210],"appearance":[211],"maintain":[213],"at":[222],"same":[224],"time.":[225],"We":[226],"evaluate":[227],"proposed":[229],"method":[230],"most":[233],"massive":[234],"dataset":[236],"(MPV)":[237],"DeepFashion":[240],"dataset.":[241],"qualitative":[243],"quantitative":[245],"experiments":[246],"show":[247],"that":[248],"superior":[251],"state-of-the-art":[254],"robust":[258],"data":[260],"noise,":[261],"including":[262],"background":[263],"accessory":[265],"changes,":[266],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e.</i>":[269],",":[270],"hats":[271],"handbags,":[273],"showing":[274],"good":[275],"scalability":[276],"real-world":[279],"scenario.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}