{"id":"https://openalex.org/W4415428939","doi":"https://doi.org/10.3233/faia250820","title":"Object-Level Control for Refined Structure and Appearance in Conditional Image Synthesis","display_name":"Object-Level Control for Refined Structure and Appearance in Conditional Image Synthesis","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428939","doi":"https://doi.org/10.3233/faia250820"},"language":null,"primary_location":{"id":"doi:10.3233/faia250820","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250820","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250820","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069785955","display_name":"Ni Xu","orcid":"https://orcid.org/0000-0002-2507-1708"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni Xu","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739392","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4308-4385"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019983016","display_name":"Zening Fu","orcid":"https://orcid.org/0000-0002-1591-4900"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouchao Fu","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101150904","display_name":"Xiaoxu Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Lin","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622539","display_name":"Wanjun Chen","orcid":"https://orcid.org/0000-0002-4937-1692"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanjun Chen","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026942556","display_name":"Jianwei Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Zheng","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.63913331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.958899974822998,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.958899974822998,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9546999931335449,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9298999905586243,"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/representation","display_name":"Representation (politics)","score":0.595300018787384},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5203999876976013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5130000114440918},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4041999876499176},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37220001220703125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336000204086304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6894999742507935},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.595300018787384},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3840000033378601},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C2778744346","wikidata":"https://www.wikidata.org/wiki/Q1152224","display_name":"Distinctive feature","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2815999984741211},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250820","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250820","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250820","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250820","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,14,23,39,188],"pretrained":[3],"diffusion":[4],"models,":[5],"particularly":[6],"the":[7,40,45,49,60,74,77,86,93,102,114,119,128,132,142,148],"FreeControl,":[8],"have":[9],"enabled":[10],"fine-grained":[11],"spatial":[12],"control":[13],"text-to-image":[15],"generation.":[16],"However,":[17],"FreeControl":[18],"still":[19],"suffers":[20],"notable":[21],"limitations":[22],"detail":[24,196],"generation":[25,42,121],"and":[26,89,98,135,146,154,174,178,195],"appearance":[27,143],"synthesis.":[28],"With":[29],"deep":[30],"analysis":[31],"performed,":[32],"we":[33,57,100],"reveal":[34],"that":[35,160,182],"inadequate":[36],"feature":[37,116],"representation":[38,150],"early":[41],"phases":[43],"is":[44],"main":[46],"cause":[47],"of":[48,63,96,151,190],"insufficient":[50],"structure":[51,71,97],"elaboration.":[52],"To":[53],"address":[54],"this":[55],"issue,":[56],"dig":[58],"into":[59,108],"temporal":[61],"evolution":[62],"inverse":[64],"attention":[65],"features,":[66],"then":[67],"extract":[68],"more":[69],"expressive":[70],"information":[72],"as":[73],"input":[75],"to":[76,84],"guidance":[78,95],"function,":[79],"ensuring":[80],"formation":[81],"integrity.":[82],"Moreover,":[83],"tackle":[85],"surface":[87],"degradation":[88],"ambiguity":[90],"caused":[91],"by":[92],"dual":[94],"appearance,":[99],"engineer":[101],"Adaptive":[103],"Instance":[104],"Normalization":[105],"(AdaIN)":[106],"mechanism":[107],"a":[109],"latent":[110],"space,":[111,117],"rather":[112],"than":[113],"typical":[115],"during":[118],"intermediate":[120],"stage.":[122],"This":[123],"improvement":[124],"not":[125],"only":[126],"guarantees":[127],"close":[129],"alignment":[130],"between":[131],"generated":[133],"image":[134],"structural":[136],"reference":[137],"but":[138],"also":[139],"significantly":[140],"strengthens":[141],"modeling":[144],"capability":[145],"optimizes":[147],"texture":[149],"both":[152],"foreground":[153],"background":[155],"elements.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"our":[161,183],"proposal":[162],"consistently":[163],"outperforms":[164],"existing":[165],"baseline":[166],"models":[167],"across":[168],"multiple":[169],"metrics,":[170],"including":[171],"Self-sim,":[172],"CLIP,":[173],"LPIPS.":[175],"Both":[176],"quantitative":[177],"qualitative":[179],"results":[180],"confirm":[181],"approach":[184],"achieves":[185],"superior":[186],"performance":[187],"terms":[189],"content":[191],"consistency,":[192],"visual":[193],"quality,":[194],"preservation.":[197]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}
