{"id":"https://openalex.org/W4408354997","doi":"https://doi.org/10.1109/icassp49660.2025.10888619","title":"LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation","display_name":"LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354997","doi":"https://doi.org/10.1109/icassp49660.2025.10888619"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888619","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":"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":"https://openalex.org/A5051747971","display_name":"F. S. Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fan Deng","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638142","display_name":"Yidong Wu","orcid":"https://orcid.org/0000-0003-3456-3373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaguang Wu","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056584211","display_name":"Xiongdong Yu","orcid":"https://orcid.org/0000-0002-1179-1667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyang Yu","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110615560","display_name":"X.Y. Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangjun Huang","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579299","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-2590-2388"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014393508","display_name":"Guorong Yan","orcid":"https://orcid.org/0000-0001-9200-2959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangyu Yan","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100552857","display_name":"Qiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Xu","raw_affiliation_strings":["MetaX,China"],"affiliations":[{"raw_affiliation_string":"MetaX,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5051747971"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04318516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11448","display_name":"Face recognition and analysis","score":0.9573000073432922,"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":0.9573000073432922,"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":0.6143151521682739},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5852513909339905},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08681726455688477},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.057239681482315063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6143151521682739},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5852513909339905},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08681726455688477},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.057239681482315063}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888619","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386076027","https://openalex.org/W4390873054","https://openalex.org/W4393154259","https://openalex.org/W4400573550","https://openalex.org/W4402623742","https://openalex.org/W4402704533","https://openalex.org/W4402727823","https://openalex.org/W4402782221","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6791353385","https://openalex.org/W6801666068","https://openalex.org/W6802987763","https://openalex.org/W6803216872","https://openalex.org/W6809885388","https://openalex.org/W6851461864","https://openalex.org/W6851736801","https://openalex.org/W6853706214","https://openalex.org/W6855771293","https://openalex.org/W6863032331","https://openalex.org/W6863631979","https://openalex.org/W6869845562"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"text-to-image":[1],"models":[2],"based":[3],"on":[4,117],"diffusion":[5,108],"have":[6],"achieved":[7],"remarkable":[8],"success":[9],"in":[10,29,134],"generating":[11],"high-quality":[12],"images.":[13],"However,":[14],"the":[15,59,88,107,118,124],"challenge":[16],"of":[17,21,31,45,48,61],"personalized,":[18],"controllable":[19],"generation":[20,71],"instances":[22],"within":[23,54],"these":[24],"images":[25],"remains":[26],"an":[27,55,81,96],"area":[28],"need":[30],"further":[32],"development.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,64,94],"present":[38],"LocRef-Diffusion,":[39],"a":[40,66],"novel,":[41],"tuning-free":[42],"model":[43,109],"capable":[44],"personalized":[46],"customization":[47],"multiple":[49],"instances\u2019":[50],"appearance":[51,89,101,137],"and":[52,80,103,120,123,136],"position":[53],"image.":[56],"To":[57,86],"enhance":[58],"precision":[60],"instance":[62,70,77,82,100],"placement,":[63],"introduce":[65],"Layout-net,":[67],"which":[68],"controls":[69],"locations":[72],"by":[73],"leveraging":[74],"both":[75],"explicit":[76],"layout":[78,135],"information":[79],"region":[83],"cross-attention":[84,111],"module.":[85],"improve":[87],"fidelity":[90],"to":[91],"reference":[92],"images,":[93],"employ":[95],"appearance-net":[97],"that":[98,127],"extracts":[99],"features":[102],"integrates":[104],"them":[105],"into":[106],"through":[110],"mechanisms.":[112],"We":[113],"conducted":[114],"extensive":[115],"experiments":[116],"COCO":[119],"OpenImages":[121],"datasets,":[122],"results":[125],"demonstrate":[126],"our":[128],"proposed":[129],"method":[130],"achieves":[131],"state-of-the-art":[132],"performance":[133],"guided":[138],"generation.":[139]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}