{"id":"https://openalex.org/W4407899908","doi":"https://doi.org/10.1109/tip.2025.3541877","title":"RTF: Recursive TransFusion for Multi-Modal Image Synthesis","display_name":"RTF: Recursive TransFusion for Multi-Modal Image Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407899908","doi":"https://doi.org/10.1109/tip.2025.3541877","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031796"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3541877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3541877","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":null,"license_id":null,"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/A5003688818","display_name":"Bing Cao","orcid":"https://orcid.org/0000-0002-0316-5404"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bing Cao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111319860","display_name":"Guoliang Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Qi","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008706834","display_name":"Jiaming Zhao","orcid":"https://orcid.org/0009-0004-5864-2900"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006952581","display_name":"Pengfei Zhu","orcid":"https://orcid.org/0000-0002-4310-9140"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Zhu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056686459","display_name":"Qinghua Hu","orcid":"https://orcid.org/0000-0001-7765-8095"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Hu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0003-1443-0776"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003688818"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":15.2349,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98591958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":null,"first_page":"1573","last_page":"1587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9891999959945679,"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":0.9728000164031982,"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/modal","display_name":"Modal","score":0.5443626642227173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5271517634391785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4686505198478699},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4250441789627075},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4176437258720398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070175588130951},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3789249062538147},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34808918833732605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32929253578186035}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5443626642227173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5271517634391785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4686505198478699},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4250441789627075},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4176437258720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070175588130951},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3789249062538147},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34808918833732605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32929253578186035},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3541877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3541877","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:40031796","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031796","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":[],"awards":[{"id":"https://openalex.org/G1585402135","display_name":null,"funder_award_id":"62222608","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2243041281","display_name":null,"funder_award_id":"62106171","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4013770026","display_name":null,"funder_award_id":"61925602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4297946667","display_name":null,"funder_award_id":"U22A2096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5070492027","display_name":null,"funder_award_id":"U23B2049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G549457566","display_name":null,"funder_award_id":"2022ZD0116500","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G566782536","display_name":null,"funder_award_id":"62476198","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7077580569","display_name":null,"funder_award_id":"62436002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G913836228","display_name":null,"funder_award_id":"62036007","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W66427752","https://openalex.org/W1641498739","https://openalex.org/W2015897296","https://openalex.org/W2064675550","https://openalex.org/W2102849263","https://openalex.org/W2133665775","https://openalex.org/W2141983208","https://openalex.org/W2183595887","https://openalex.org/W2208340121","https://openalex.org/W2484736472","https://openalex.org/W2521443754","https://openalex.org/W2522924304","https://openalex.org/W2523213734","https://openalex.org/W2523468284","https://openalex.org/W2565639579","https://openalex.org/W2594313306","https://openalex.org/W2626607737","https://openalex.org/W2751812122","https://openalex.org/W2765811365","https://openalex.org/W2767044624","https://openalex.org/W2773119425","https://openalex.org/W2773267467","https://openalex.org/W2795063884","https://openalex.org/W2902719825","https://openalex.org/W2914057844","https://openalex.org/W2914617358","https://openalex.org/W2952056941","https://openalex.org/W2962793481","https://openalex.org/W2962932373","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963768110","https://openalex.org/W2964185501","https://openalex.org/W3007486523","https://openalex.org/W3032240740","https://openalex.org/W3041018972","https://openalex.org/W3046194589","https://openalex.org/W3046815881","https://openalex.org/W3127751679","https://openalex.org/W3132541979","https://openalex.org/W3143351114","https://openalex.org/W3171125843","https://openalex.org/W3176466780","https://openalex.org/W3206815816","https://openalex.org/W3207918547","https://openalex.org/W3211246039","https://openalex.org/W3212516020","https://openalex.org/W4293868332","https://openalex.org/W4298326888","https://openalex.org/W4312950730","https://openalex.org/W4313449766","https://openalex.org/W4321232185","https://openalex.org/W4360899433","https://openalex.org/W4382372079","https://openalex.org/W4385245566","https://openalex.org/W4387211167","https://openalex.org/W4387211424","https://openalex.org/W6631190155","https://openalex.org/W6677645113","https://openalex.org/W6692550842","https://openalex.org/W6731370813","https://openalex.org/W6737778391","https://openalex.org/W6755207826","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6782529005","https://openalex.org/W6784910987","https://openalex.org/W6795288823"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386"],"abstract_inverted_index":{"Multi-modal":[0,61],"image":[1,100],"synthesis":[2,62],"is":[3],"crucial":[4],"for":[5,98],"obtaining":[6],"complete":[7],"modalities":[8],"due":[9],"to":[10,24,34,74,108],"the":[11,42,68,114,139,144,184],"imaging":[12],"restrictions":[13],"in":[14,49],"reality.":[15],"Current":[16],"methods,":[17],"primarily":[18],"CNN-based":[19,120],"models,":[20],"find":[21],"it":[22,72],"challenging":[23],"extract":[25,75],"global":[26,44,128],"representations":[27],"because":[28],"of":[29,47,67],"local":[30,110,121],"inductive":[31],"bias,":[32],"leading":[33],"synthetic":[35],"structure":[36],"deformation":[37],"or":[38],"color":[39],"distortion.":[40],"Despite":[41],"significant":[43],"representation":[45,122],"ability":[46],"transformer":[48],"capturing":[50],"long-range":[51],"dependencies,":[52],"its":[53],"huge":[54],"parameter":[55],"size":[56],"requires":[57],"considerable":[58],"training":[59],"data.":[60,83],"solely":[63],"based":[64],"on":[65,187],"one":[66],"two":[69],"structures":[70],"makes":[71],"hard":[73],"comprehensive":[76],"information":[77,164],"from":[78,113],"each":[79],"modality":[80,116],"with":[81,152],"limited":[82],"To":[84],"tackle":[85],"this":[86],"dilemma,":[87],"we":[88,103,146],"propose":[89],"a":[90,105,119,126,133,149],"simple":[91],"yet":[92],"effective":[93],"Recursive":[94],"TransFusion":[95,106,150,158],"(RTF)":[96],"framework":[97],"multi-modal":[99,163],"synthesis.":[101],"Specifically,":[102],"develop":[104],"unit":[107,151],"integrate":[109],"knowledge":[111],"extracted":[112],"individual":[115],"by":[117,143],"connecting":[118],"block":[123,130],"(LRB)":[124],"and":[125],"transformer-based":[127],"fusion":[129],"(GFB)":[131],"via":[132],"feature":[134],"translating":[135],"gate":[136],"(FTG).":[137],"Considering":[138],"numerous":[140],"parameters":[141,173],"introduced":[142],"transformer,":[145],"further":[147],"unfold":[148],"recursive":[153,157],"constraint":[154],"repeatedly,":[155],"forming":[156],"(RTF),":[159],"which":[160],"progressively":[161],"extracts":[162],"at":[165,196],"different":[166],"depths.":[167],"Our":[168],"RTF":[169],"remarkably":[170],"reduces":[171],"network":[172],"while":[174],"maintaining":[175],"superior":[176],"performance.":[177],"Extensive":[178],"experiments":[179],"validate":[180],"our":[181],"superiority":[182],"against":[183],"competing":[185],"methods":[186],"multiple":[188],"benchmarks.":[189],"The":[190],"source":[191],"code":[192],"will":[193],"be":[194],"available":[195],"https://github.com/guoliangq/RTF.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}