{"id":"https://openalex.org/W4415708205","doi":"https://doi.org/10.1109/icme59968.2025.11210103","title":"OmniStyle: Attention-Optimized Global and Local Image Stylization with Diffusion Model Inversion","display_name":"OmniStyle: Attention-Optimized Global and Local Image Stylization with Diffusion Model Inversion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708205","doi":"https://doi.org/10.1109/icme59968.2025.11210103"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5110967002","display_name":"Jiarong Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiarong Cheng","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108978360","display_name":"Xihang Qiu","orcid":"https://orcid.org/0009-0001-9103-8025"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihang Qiu","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036029284","display_name":"Qing Zhou","orcid":"https://orcid.org/0000-0002-5352-5842"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Zhou","raw_affiliation_strings":["Shenzhen MSU-BIT University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351468","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-7852-0159"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031811109","display_name":"Chun Li","orcid":"https://orcid.org/0000-0002-8819-2443"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Li","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640766","display_name":"Yao Lu","orcid":"https://orcid.org/0000-0001-6747-9210"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Lu","raw_affiliation_strings":["Shenzhen MSU-BIT University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Richard Yu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5110967002"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33770119,"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":"6"},"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":0.98089998960495,"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":0.98089998960495,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.001500000013038516,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.001500000013038516,"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/scalability","display_name":"Scalability","score":0.6037999987602234},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5178999900817871},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5170000195503235},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4025999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794999837875366},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5462999939918518},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.531000018119812},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46000000834465027},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.39629998803138733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2475287302","https://openalex.org/W2603777577","https://openalex.org/W3202767484","https://openalex.org/W3216156094","https://openalex.org/W4281253515","https://openalex.org/W4312502087","https://openalex.org/W4312933868","https://openalex.org/W4385271281","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4393156458","https://openalex.org/W4402979949"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"interest":[1],"in":[2],"large-scale":[3],"text-driven":[4,57],"diffusion":[5,65],"models":[6],"has":[7],"highlighted":[8],"their":[9],"ability":[10],"to":[11,88,116],"generate":[12,90],"diverse":[13],"images":[14,73],"from":[15],"textual":[16],"prompts,":[17],"with":[18,105],"style":[19,62,113],"transfer":[20,114],"being":[21],"a":[22,50],"significant":[23],"application.":[24],"However,":[25],"existing":[26],"text-guided":[27],"stylization":[28],"methods":[29],"are":[30,74,86,102],"constrained":[31],"by":[32],"the":[33,95,121,129],"reliance":[34],"on":[35],"manually":[36],"created":[37],"masks":[38],"for":[39,56,97],"localized":[40,60],"transformations,":[41],"which":[42],"limits":[43],"scalability":[44,130],"and":[45,59,68,108,131],"automation.":[46],"In":[47],"this":[48],"work,":[49],"novel":[51],"framework,":[52],"OmniStyle,":[53],"is":[54],"introduced":[55],"global":[58,124],"image":[61],"transfer,":[63],"leveraging":[64],"model":[66],"inversion":[67],"attention-based":[69],"mask":[70],"generation.":[71],"Input":[72],"mapped":[75],"into":[76],"latent":[77],"noise":[78],"representations":[79],"using":[80],"DDIM":[81],"inversion,":[82],"while":[83,119],"cross-attention":[84],"maps":[85],"utilized":[87],"automatically":[89],"precise":[91],"semantic":[92],"masks,":[93],"eliminating":[94],"need":[96],"manual":[98],"annotations.":[99],"Latent":[100],"features":[101],"dynamically":[103],"optimized":[104],"mask-guided":[106],"constraints":[107],"attention":[109],"manipulations,":[110],"enabling":[111],"fine-grained":[112],"confined":[115],"target":[117],"regions":[118],"maintaining":[120],"integrity":[122],"of":[123,133],"content.":[125],"Extensive":[126],"experiments":[127],"demonstrate":[128],"effectiveness":[132],"OmniStyle.":[134]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}