{"id":"https://openalex.org/W4408345972","doi":"https://doi.org/10.1109/icassp49660.2025.10889379","title":"DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images","display_name":"DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345972","doi":"https://doi.org/10.1109/icassp49660.2025.10889379"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"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/A5046240298","display_name":"Enbo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enbo Huang","raw_affiliation_strings":["Nanning Normal University,Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision,Nanning,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanning Normal University,Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision,Nanning,China","institution_ids":["https://openalex.org/I4210151929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768439","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0003-2367-8132"},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Nanning Normal University,School of Computer and Information Engineering,Nanning,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanning Normal University,School of Computer and Information Engineering,Nanning,China","institution_ids":["https://openalex.org/I4210151929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021971414","display_name":"Faliang Huang","orcid":"https://orcid.org/0000-0002-0656-7361"},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Faliang Huang","raw_affiliation_strings":["Nanning Normal University,Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision,Nanning,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanning Normal University,Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision,Nanning,China","institution_ids":["https://openalex.org/I4210151929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446013","display_name":"Guangyu Zhang","orcid":"https://orcid.org/0000-0002-8604-3786"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Zhang","raw_affiliation_strings":["South China Agricultural University,College of Mathematics and Informatics,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,College of Mathematics and Informatics,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063685742","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-3768-6654"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9786999821662903,"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":0.9786999821662903,"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":0.9153000116348267,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9125000238418579,"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":0.7147009372711182},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6121722459793091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48085981607437134},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3923443555831909},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38248106837272644},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07969686388969421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147009372711182},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6121722459793091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48085981607437134},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3923443555831909},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38248106837272644},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07969686388969421},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2559085405","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963800363","https://openalex.org/W3024104158","https://openalex.org/W3034950620","https://openalex.org/W3035515747","https://openalex.org/W3035574324","https://openalex.org/W3173561947","https://openalex.org/W3176412779","https://openalex.org/W4213304546","https://openalex.org/W4301373693","https://openalex.org/W4312896571","https://openalex.org/W4313030876","https://openalex.org/W4386076520","https://openalex.org/W4390871780","https://openalex.org/W4402727583","https://openalex.org/W4403757521","https://openalex.org/W6745560452","https://openalex.org/W6779823529","https://openalex.org/W6785870135","https://openalex.org/W6840815571","https://openalex.org/W6870077751"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Person":[0],"image":[1,24],"synthesis":[2],"with":[3,35,125],"controllable":[4],"body":[5,103],"poses":[6,67],"and":[7,26,40,68,109,155,174],"appearances":[8],"is":[9,74],"an":[10],"essential":[11],"task":[12],"owing":[13],"to":[14,57,84,112],"the":[15,19,41,86,101,113,117,123,150,161,165],"practical":[16],"needs":[17],"in":[18,64,170],"context":[20],"of":[21,88,105,116,153,167],"virtual":[22],"try-on,":[23],"editing":[25],"video":[27],"production.":[28],"However,":[29],"existing":[30],"methods":[31],"face":[32],"significant":[33],"challenges":[34],"details":[36],"missing,":[37],"limbs":[38],"distortion":[39],"garment":[42],"style":[43],"deviation.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"we":[49,138],"propose":[50],"a":[51,71,81,92,106,131,140],"Disentangled":[52],"Representations":[53],"Diffusion":[54],"Model":[55],"(DRDM)":[56],"generate":[58],"photorealistic":[59],"images":[60],"from":[61,100],"source":[62,107],"portraits":[63],"specific":[65],"desired":[66],"appearances.":[69],"First,":[70],"pose":[72,78,172],"encoder":[73],"responsible":[75],"for":[76,129],"encoding":[77],"features":[79,99,128],"into":[80],"high-dimensional":[82],"space":[83],"guide":[85],"generation":[87],"person":[89],"images.":[90],"Second,":[91],"body-part":[93],"subspace":[94],"decoupling":[95],"block":[96],"(BSDB)":[97],"disentangles":[98],"different":[102],"parts":[104],"figure":[108],"feeds":[110],"them":[111],"various":[114],"layers":[115],"noise":[118],"prediction":[119],"block,":[120],"thereby":[121],"supplying":[122],"network":[124],"rich":[126],"disentangled":[127,143],"generating":[130],"realistic":[132],"target":[133],"image.":[134],"Moreover,":[135],"during":[136],"inference,":[137],"develop":[139],"parsing":[141],"map-based":[142],"classifier-free":[144],"guided":[145],"sampling":[146],"method,":[147],"which":[148],"amplifies":[149],"conditional":[151],"signals":[152],"texture":[154],"pose.":[156],"Extensive":[157],"experimental":[158],"results":[159],"on":[160],"Deepfashion":[162],"dataset":[163],"demonstrate":[164],"effectiveness":[166],"our":[168],"approach":[169],"achieving":[171],"transfer":[173],"appearance":[175],"control.":[176],"The":[177],"associated":[178],"project":[179],"can":[180],"be":[181],"found":[182],"at":[183],"https://github.com/lovemusiceb/DRDM":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}