{"id":"https://openalex.org/W4415707709","doi":"https://doi.org/10.1109/icme59968.2025.11209379","title":"EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models","display_name":"EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707709","doi":"https://doi.org/10.1109/icme59968.2025.11209379"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209379","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.05152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100366623","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0001-9460-0979"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031208819","display_name":"Donglin Di","orcid":"https://orcid.org/0000-0002-2270-3378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donglin Di","raw_affiliation_strings":["Li Auto,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033324841","display_name":"Tonghua Su","orcid":"https://orcid.org/0000-0002-8869-1664"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tonghua Su","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100640159","display_name":"Lei Fan","orcid":"https://orcid.org/0000-0002-9988-4517"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Fan","raw_affiliation_strings":["University of New South Wales,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.33855268,"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":0.7996000051498413,"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":0.7996000051498413,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.05869999900460243,"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/T11019","display_name":"Image Enhancement Techniques","score":0.03819999843835831,"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/focus","display_name":"Focus (optics)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4738999903202057},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4072999954223633},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.40549999475479126},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3465999960899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43639999628067017},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11209379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209379","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"},{"id":"pmh:oai:arXiv.org:2512.05152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.05152","pdf_url":"https://arxiv.org/pdf/2512.05152","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.05152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.05152","pdf_url":"https://arxiv.org/pdf/2512.05152","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3035574324","https://openalex.org/W3176828726","https://openalex.org/W4226418836","https://openalex.org/W4295935120","https://openalex.org/W4382457527","https://openalex.org/W4387185314","https://openalex.org/W4390872006","https://openalex.org/W4390872297","https://openalex.org/W4393148638","https://openalex.org/W4393159139","https://openalex.org/W4402754267","https://openalex.org/W4402774574","https://openalex.org/W4403791271","https://openalex.org/W4403843325","https://openalex.org/W4406970700"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,22],"are":[2],"highly":[3],"regarded":[4],"for":[5],"their":[6],"controllability":[7],"and":[8,39,70,82,120],"the":[9,43,74,84,91,101,106,112,136],"diversity":[10],"of":[11,35,55,86,93,103,115,160],"images":[12,45,117],"they":[13],"generate.":[14],"However,":[15],"class-conditional":[16],"generation":[17,109],"methods":[18,157],"based":[19],"on":[20,25,146],"diffusion":[21,75,137],"often":[23],"focus":[24],"more":[26],"common":[27],"categories.":[28],"In":[29],"large-scale":[30],"fine-grained":[31,60,97,116],"image":[32,61],"generation,":[33,62],"issues":[34],"semantic":[36,65,80,87],"information":[37,66,81,108],"entanglement":[38],"insufficient":[40,94],"detail":[41,95],"in":[42,59,96,135,158],"generated":[44],"still":[46],"persist.":[47],"This":[48],"paper":[49],"attempts":[50],"to":[51,77],"introduce":[52,100],"a":[53,56],"concept":[54,102],"\"tiered":[57],"embedder\"":[58],"which":[63],"integrates":[64],"from":[67],"both":[68],"super":[69],"child":[71],"classes,":[72],"allowing":[73],"model":[76],"better":[78],"incorporate":[79],"address":[83,90],"issue":[85,92],"entanglement.":[88],"To":[89],"images,":[98],"we":[99,124],"super-resolution":[104],"during":[105],"perceptual":[107],"stage,":[110],"enhancing":[111],"detailed":[113],"features":[114],"through":[118,143],"enhancement":[119],"degradation":[121],"models.":[122],"Furthermore,":[123],"propose":[125],"an":[126],"efficient":[127],"ProAttention":[128],"mechanism":[129],"that":[130,150],"can":[131],"be":[132],"effectively":[133],"implemented":[134],"model.":[138],"We":[139],"evaluate":[140],"our":[141,151],"method":[142],"extensive":[144],"experiments":[145],"public":[147],"benchmarks,":[148],"demonstrating":[149],"approach":[152],"outperforms":[153],"other":[154],"state-of-the-art":[155],"fine-tuning":[156],"terms":[159],"performance.":[161]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-30T00:00:00"}