{"id":"https://openalex.org/W4408354982","doi":"https://doi.org/10.1109/icassp49660.2025.10889138","title":"Enhancing Image Generation Fidelity via Progressive Prompts","display_name":"Enhancing Image Generation Fidelity via Progressive Prompts","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354982","doi":"https://doi.org/10.1109/icassp49660.2025.10889138"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889138","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/A5035013898","display_name":"Zhen Xiong","orcid":"https://orcid.org/0000-0001-6685-9676"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xiong","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031930948","display_name":"Yuqi Li","orcid":"https://orcid.org/0000-0003-1501-1549"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046293929","display_name":"Chuanguang Yang","orcid":"https://orcid.org/0000-0001-5890-289X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanguang Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101351946","display_name":"Tiao Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiao Tan","raw_affiliation_strings":["Tsinghua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102856192","display_name":"Zhihong Zhu","orcid":"https://orcid.org/0009-0001-4530-5516"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Zhu","raw_affiliation_strings":["Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467828","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0002-2354-4233"},"institutions":[{"id":"https://openalex.org/I4210154234","display_name":"Exercise and Survivorship Education Cancer Foundation","ror":"https://ror.org/04csrvg63","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210154234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["EaseUS,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EaseUS,China","institution_ids":["https://openalex.org/I4210154234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100694246","display_name":"Yue Ma","orcid":"https://orcid.org/0009-0005-7477-5938"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yue Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology,HK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,HK","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8048,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89654355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9868000149726868,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9868000149726868,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9735000133514404,"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":0.967199981212616,"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":0.6787149310112},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4887261390686035},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.479358971118927},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4539083242416382},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4170714020729065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4057329297065735},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06498834490776062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787149310112},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4887261390686035},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.479358971118927},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4539083242416382},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4170714020729065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4057329297065735},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06498834490776062}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889138","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335768","display_name":"National Postdoctoral Program for Innovative Talents","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2009423060","https://openalex.org/W3153469116","https://openalex.org/W4304142382","https://openalex.org/W4312309807","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4386076027","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4393145119","https://openalex.org/W4393148505","https://openalex.org/W4402772638","https://openalex.org/W4403792125","https://openalex.org/W4404582704","https://openalex.org/W4404965490","https://openalex.org/W4405718500","https://openalex.org/W4409262178","https://openalex.org/W4409346646","https://openalex.org/W4409365603","https://openalex.org/W4409367025","https://openalex.org/W4409369698","https://openalex.org/W4411631879","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6809665764","https://openalex.org/W6838639034","https://openalex.org/W6849938875","https://openalex.org/W6854511533","https://openalex.org/W6855771293","https://openalex.org/W6856607740","https://openalex.org/W6866689913","https://openalex.org/W6869101536","https://openalex.org/W6874129404","https://openalex.org/W6874135059","https://openalex.org/W6874599112"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Diffusion":[0],"transformer":[1],"(DiT)":[2],"architecture":[3],"catches":[4],"much":[5],"attention":[6],"in":[7,88,122],"image":[8,21,63,74,137],"generation,":[9],"which":[10],"achieves":[11],"better":[12],"fidelity,":[13],"performance,":[14],"and":[15,27,68,70,78,141],"diversity.":[16],"However,":[17],"most":[18],"existing":[19],"DiT-based":[20,136],"generation":[22,41],"methods":[23],"are":[24,114,156],"global-aware":[25],"synthesis":[26],"regional":[28,44,119],"prompt":[29],"control":[30,121],"is":[31],"less":[32],"explored.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,48,81,131],"propose":[38],"a":[39],"coarse-to-fine":[40],"pipeline":[42,147],"for":[43,98,124],"prompt-following":[45],"generation.":[46,126,138],"Specifically,":[47],"first":[49],"leverage":[50],"the":[51,59,83,99,104,117,128,133,151],"powerful":[52],"large":[53],"language":[54],"model":[55],"(LLM)":[56],"to":[57,149],"generate":[58],"high-level":[60,100],"description":[61,72],"of":[62,73,85,135],"(such":[64,75],"as":[65,76],"content,":[66],"topic,":[67],"objects)":[69],"low-level":[71,108],"details":[77],"style).":[79],"Then":[80],"explore":[82],"influence":[84],"cross-attention":[86,120],"layers":[87,95,106],"different":[89],"depths.":[90],"We":[91],"discover":[92],"that":[93,145],"deeper":[94],"always":[96],"responsible":[97],"content":[101,109],"control,":[102],"while":[103],"shallow":[105],"handles":[107],"control.":[110],"The":[111],"various":[112],"prompts":[113],"injected":[115],"into":[116],"proposed":[118,129],"order":[123],"course-to-fine":[125],"Using":[127],"pipeline,":[130],"improve":[132,150],"controllability":[134],"Extensive":[139],"quantitative":[140],"qualitative":[142],"results":[143],"demonstrate":[144],"our":[146],"enables":[148],"generated":[152],"performance.":[153],"Our":[154],"codes":[155],"available":[157],"at":[158],"https://github.com/ZhenXiong-dl/ICASSP2025-RCAC.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}