{"id":"https://openalex.org/W7163135373","doi":"https://doi.org/10.1109/tip.2026.3697647","title":"MaPPA: Multimodal Controllable Person Image Generation With Pose and Appearance Guidance","display_name":"MaPPA: Multimodal Controllable Person Image Generation With Pose and Appearance Guidance","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163135373","doi":"https://doi.org/10.1109/tip.2026.3697647","pmid":"https://pubmed.ncbi.nlm.nih.gov/42228657"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3697647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697647","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5137649092","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3989-7655","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005283318","display_name":"Yuran Dong","orcid":"https://orcid.org/0009-0003-9037-9391"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuran Dong","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-9037-9391","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028876738","display_name":"T Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tongxin Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137634606","display_name":"Daiguo Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daiguo Zhou","raw_affiliation_strings":["Xiaomi Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846980","display_name":"Qingxiong Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxiong Tan","raw_affiliation_strings":["School of Computer Science and the Institute for Math and AI, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-1434-7021","affiliations":[{"raw_affiliation_string":"School of Computer Science and the Institute for Math and AI, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137681393","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69392799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7149","last_page":"7164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8510000109672546,"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/T11448","display_name":"Face recognition and analysis","score":0.8510000109672546,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0737999975681305,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007899999618530273,"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/image-segmentation","display_name":"Image segmentation","score":0.4733999967575073},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.45980000495910645},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3675999939441681},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.358599990606308},{"id":"https://openalex.org/keywords/image-registration","display_name":"Image registration","score":0.31839999556541443}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7694000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.733299970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717000007629395},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4733999967575073},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.45980000495910645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2816999852657318},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3697647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697647","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42228657","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42228657","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5960381627082825}],"awards":[{"id":"https://openalex.org/G1836220556","display_name":null,"funder_award_id":"62225113","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Person":[0,100],"image":[1,131],"generation":[2,132],"has":[3],"become":[4],"an":[5],"increasingly":[6],"important":[7],"problem":[8,256],"in":[9,15,28,65,88,260,289],"computer":[10],"vision":[11],"with":[12,103,168,195,276],"broad":[13],"applications":[14],"virtual":[16],"try-on,":[17],"digital":[18],"content":[19],"creation,":[20],"entertainment,":[21],"and":[22,63,105,161,222,294,312,333,343,348],"human-computer":[23],"interaction.":[24],"Despite":[25],"recent":[26],"advances":[27],"diffusion-based":[29],"generative":[30],"models":[31],"that":[32,112,154,182,211,301],"can":[33],"produce":[34],"photorealistic":[35],"results,":[36],"existing":[37],"pipelines":[38],"are":[39,165,175],"still":[40],"constrained":[41,320],"by":[42,321],"rigid":[43],"modality":[44,193],"requirements.":[45],"Most":[46],"prior":[47],"methods":[48],"rely":[49],"on":[50,134,177],"fixed":[51],"patterns":[52],"such":[53],"as":[54],"pose-plus-appearance":[55],"inputs":[56,185],"or":[57,73,142],"text-only":[58],"descriptions,":[59],"limiting":[60],"their":[61],"flexibility":[62,342],"controllability":[64,248],"practical":[66,344],"scenarios":[67],"where":[68],"users":[69,214,235],"may":[70],"prefer":[71],"different":[72,229],"mixed":[74],"types":[75],"of":[76,80,203,220,241,257,324,330],"guidance.":[77],"This":[78,232,280],"lack":[79],"adaptability":[81],"poses":[82],"a":[83,108,151,178,187,196,206,265,337],"clear":[84],"barrier":[85],"to":[86,122,215,236,252,357],"deployment":[87],"real-world":[89],"systems.":[90],"To":[91,146],"overcome":[92],"these":[93],"challenges,":[94],"we":[95,149,263],"propose":[96,264],"MaPPA":[97,204,302],"(Multimodal":[98],"Controllable":[99],"Image":[101],"Generation":[102],"Pose":[104],"Appearance":[106],"Guidance),":[107],"unified":[109,152,179,198,326],"multimodal":[110,180,327],"framework":[111,153],"leverages":[113],"transformer-based":[114],"latent":[115],"diffusion":[116],"models.":[117],"The":[118,346],"central":[119],"idea":[120],"is":[121,205],"provide":[123],"composable":[124],"control":[125,157,173,230],"over":[126],"multiple":[127],"modalities,":[128],"enabling":[129],"person":[130],"conditioned":[133,176],"text":[135],"prompts,":[136],"reference":[137],"appearance":[138,160,221,242,334],"images,":[139],"pose":[140,162,223,244],"keypoints,":[141],"any":[143],"combination":[144],"thereof.":[145],"achieve":[147],"this,":[148],"introduce":[150],"incorporates":[155],"dedicated":[156],"blocks":[158,174],"for":[159],"guidance,":[163,245],"which":[164,271],"strategically":[166],"interleaved":[167],"transformer":[169],"base":[170],"blocks.":[171],"These":[172],"embedding":[181],"integrates":[183],"heterogeneous":[184],"into":[186],"consistent":[188],"representation,":[189],"thereby":[190],"supporting":[191],"arbitrary":[192],"combinations":[194,329],"single":[197,338],"pipeline.":[199],"Another":[200],"key":[201],"contribution":[202],"cumulative":[207],"classifier-free":[208],"guidance":[209,224],"strategy":[210],"enables":[212],"allowing":[213],"independently":[216],"adjust":[217,237],"the":[218,238,254,273,322,325,349,358],"strength":[219,240],"via":[225],"scalar":[226],"weights":[227],"from":[228],"signals.":[231],"design":[233],"allows":[234],"relative":[239],"versus":[243],"providing":[246,308],"fine-grained":[247],"during":[249],"inference.":[250],"Furthermore,":[251],"address":[253],"common":[255],"detail":[258],"loss":[259],"latent-diffusion":[261],"decoders,":[262],"texture":[266,284],"enhancement":[267],"decoding":[268],"(TED)":[269],"strategy,":[270],"fine-tunes":[272],"VAE":[274],"decoder":[275],"edge-aware":[277],"reconstruction":[278],"objectives.":[279],"refinement":[281],"significantly":[282],"alleviates":[283],"distortion,":[285],"preserving":[286],"high-frequency":[287],"details":[288],"clothing":[290],"patterns,":[291],"facial":[292],"regions,":[293],"other":[295],"fine":[296],"structures.":[297],"Extensive":[298],"experiments":[299],"confirm":[300],"achieves":[303],"competitive":[304],"quantitative":[305],"scores":[306],"while":[307],"superior":[309],"perceptual":[310],"quality":[311],"user":[313],"preference.":[314],"Unlike":[315],"task-specific":[316],"methods,":[317],"our":[318],"framework-though":[319],"capacity":[323],"embedding-supports":[328],"text,":[331],"pose,":[332],"modalities":[335],"within":[336],"pipeline,":[339],"demonstrating":[340],"both":[341],"value.":[345],"code":[347],"corresponding":[350],"model":[351],"will":[352],"be":[353],"made":[354],"publicly":[355],"available":[356],"research":[359],"community.":[360]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-06-03T00:00:00"}
