{"id":"https://openalex.org/W7108212307","doi":"https://doi.org/10.1109/tcsvt.2025.3639218","title":"Diffusion-Based Text-Guided Image Generation With Fine-Grained Spatial Object-Attribute Relationships","display_name":"Diffusion-Based Text-Guided Image Generation With Fine-Grained Spatial Object-Attribute Relationships","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7108212307","doi":"https://doi.org/10.1109/tcsvt.2025.3639218"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3639218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3639218","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":null,"display_name":"Fuxiang Wu","orcid":"https://orcid.org/0000-0002-4542-4486"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuxiang Wu","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4542-4486","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-8128-2788"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8128-2788","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fusheng Hao","orcid":"https://orcid.org/0000-0003-1490-2235"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fusheng Hao","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1490-2235","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziliang Ren","orcid":"https://orcid.org/0000-0001-7940-294X"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziliang Ren","raw_affiliation_strings":["Dongguan University of Technology, Dongguan, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-7940-294X","affiliations":[{"raw_affiliation_string":"Dongguan University of Technology, Dongguan, Guangdong, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyu Wu","orcid":"https://orcid.org/0000-0001-6130-7821"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Wu","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6130-7821","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3131-3275","affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78810985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"4","first_page":"4609","last_page":"4621"},"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":0.2870999872684479,"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":0.2870999872684479,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.19750000536441803,"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":0.19210000336170197,"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/leverage","display_name":"Leverage (statistics)","score":0.7099999785423279},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6014999747276306},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5295000076293945},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.490200012922287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.474700003862381},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4187999963760376},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3928999900817871},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3790000081062317},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929999828338623},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7099999785423279},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6014999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570900022983551},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2906000018119812},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3639218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3639218","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G253655306","display_name":null,"funder_award_id":"62376261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4459270519","display_name":null,"funder_award_id":"2024A1515011754","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G587205070","display_name":null,"funder_award_id":"62372440","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6149225315","display_name":null,"funder_award_id":"U25A20477","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6718967287","display_name":null,"funder_award_id":"2025A1515012957","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8926547000","display_name":null,"funder_award_id":"62206268","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Expressing":[0],"and":[1,24,79,92,188],"controlling":[2],"fine-grained":[3,41,94,159,181],"spatial":[4,16,37,63,105,119,148,182],"attributes":[5,17],"of":[6,104,132],"objects":[7],"in":[8,40],"large-scale":[9],"models":[10,145,153],"presents":[11],"significant":[12],"challenges,":[13],"as":[14,97],"these":[15,118,128],"are":[18,123],"often":[19],"difficult":[20],"to":[21,61,99,115,125,146,158],"describe":[22],"textually":[23],"exhaustive":[25],"enumeration":[26],"is":[27],"impractical.":[28],"This":[29],"hinders":[30],"effective":[31],"alignment":[32],"with":[33,127,141],"user":[34],"preferences":[35],"regarding":[36],"attribute-object":[38,106],"relationships":[39],"synthesis":[42,162,186],"tasks.":[43],"To":[44],"tackle":[45],"this":[46],"problem,":[47],"we":[48],"propose":[49],"AttrObjDiff,":[50],"a":[51,89],"novel":[52],"framework":[53],"built":[54],"on":[55],"the":[56,69,113,138],"pre-trained":[57],"Stable":[58],"Diffusion":[59],"model":[60],"integrate":[62],"attribute":[64,95],"maps.":[65],"Firstly,":[66],"AttrObjDiff":[67,136],"constrains":[68],"denoising":[70],"step":[71],"using":[72],"trainable":[73],"cross-attention":[74,78,111],"fusion":[75,82],"modules,":[76],"attribute-enhancing":[77,110],"LoRAs.":[80],"The":[81,151],"modules":[83],"take":[84],"layout":[85],"features":[86,103,131],"extracted":[87],"by":[88,180],"frozen":[90],"ControlNet":[91],"corresponding":[93],"maps":[96],"inputs":[98],"generate":[100,176],"joint":[101,129],"constraint":[102,130],"relationships.":[107,134],"We":[108],"leverage":[109],"within":[112],"U-Net":[114],"further":[116],"refine":[117],"attributes.":[120],"Finally,":[121],"LoRAs":[122],"employed":[124],"align":[126],"finegrained":[133],"Secondly,":[135],"enhances":[137],"reverse":[139],"process":[140],"lightweight":[142],"noise":[143],"reranking":[144,152],"improve":[147],"object-attribute":[149,183],"alignment.":[150],"select":[154],"semantic":[155,189],"noises":[156],"related":[157],"relationships,":[160,184],"improving":[161,185],"quality":[163],"without":[164],"significantly":[165],"increasing":[166],"computational":[167],"costs.":[168],"Experimental":[169],"results":[170],"demonstrate":[171],"that":[172],"our":[173],"method":[174],"can":[175],"high-quality":[177],"images":[178],"guided":[179],"controllability":[187],"consistency.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-12-03T00:00:00"}