{"id":"https://openalex.org/W4392904162","doi":"https://doi.org/10.1109/icassp48485.2024.10445885","title":"Progressive Image Synthesis from Semantics to Details with Denoising Diffusion GAN","display_name":"Progressive Image Synthesis from Semantics to Details with Denoising Diffusion GAN","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904162","doi":"https://doi.org/10.1109/icassp48485.2024.10445885"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5101633476","display_name":"Guoxing Yang","orcid":"https://orcid.org/0000-0002-1019-2021"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guoxing Yang","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030033393","display_name":"Haoyu Lu","orcid":"https://orcid.org/0000-0003-2620-6296"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Lu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072905534","display_name":"Chongxuan Li","orcid":"https://orcid.org/0000-0002-0912-9076"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongxuan Li","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111540139","display_name":"Guang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Zhou","raw_affiliation_strings":["China Unicom Research Institute,Beijing,China","China Unicom Research Institute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom Research Institute,Beijing,China","institution_ids":["https://openalex.org/I6507939"]},{"raw_affiliation_string":"China Unicom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100769821","display_name":"Haoran Wu","orcid":"https://orcid.org/0000-0001-5822-8698"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wu","raw_affiliation_strings":["China Unicom Research Institute,Beijing,China","China Unicom Research Institute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom Research Institute,Beijing,China","institution_ids":["https://openalex.org/I6507939"]},{"raw_affiliation_string":"China Unicom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085349794","display_name":"Zhiwu Lu","orcid":"https://orcid.org/0000-0003-0280-7724"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Lu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101633476"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.5108,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61179802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7495","last_page":"7499"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9811000227928162,"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":0.9803000092506409,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246518731117249},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5545967221260071},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5435450077056885},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5358767509460449},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4954265356063843},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.480826735496521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48043394088745117},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4784936308860779},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.46970507502555847},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4566442668437958},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4262322783470154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35228925943374634},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2856902778148651},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06499096751213074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246518731117249},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5545967221260071},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5435450077056885},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5358767509460449},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4954265356063843},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.480826735496521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48043394088745117},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4784936308860779},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.46970507502555847},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4566442668437958},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4262322783470154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35228925943374634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2856902778148651},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06499096751213074},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5851092786","display_name":null,"funder_award_id":"62376274","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W967544008","https://openalex.org/W1686810756","https://openalex.org/W2129069237","https://openalex.org/W2959300817","https://openalex.org/W2962770929","https://openalex.org/W3034720584","https://openalex.org/W3036167779","https://openalex.org/W3041956526","https://openalex.org/W3110257065","https://openalex.org/W3118605064","https://openalex.org/W3121370741","https://openalex.org/W3162926177","https://openalex.org/W3168053944","https://openalex.org/W3171313410","https://openalex.org/W3175528029","https://openalex.org/W3176823897","https://openalex.org/W3180059462","https://openalex.org/W3180355996","https://openalex.org/W3191805365","https://openalex.org/W3210432528","https://openalex.org/W3217030260","https://openalex.org/W4226376398","https://openalex.org/W4287121833","https://openalex.org/W4287645637","https://openalex.org/W4289761690","https://openalex.org/W4294643831","https://openalex.org/W4301206121","https://openalex.org/W4312933868","https://openalex.org/W4313142698","https://openalex.org/W4320013936","https://openalex.org/W6625168331","https://openalex.org/W6637373629","https://openalex.org/W6679045638","https://openalex.org/W6745560452","https://openalex.org/W6752910514","https://openalex.org/W6765775151","https://openalex.org/W6765779288","https://openalex.org/W6779093361","https://openalex.org/W6779823529","https://openalex.org/W6780593937","https://openalex.org/W6783637136","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6788990321","https://openalex.org/W6795288823","https://openalex.org/W6796588791","https://openalex.org/W6797016743","https://openalex.org/W6797359156","https://openalex.org/W6803216872","https://openalex.org/W6803299508","https://openalex.org/W6811291704"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Although":[0],"denoising":[1],"diffusion":[2,100,121],"probabilistic":[3],"models":[4],"(DDPMs)":[5],"have":[6],"shown":[7,129],"remarkable":[8],"progress":[9],"in":[10,34,110],"image":[11,112,126],"generation,":[12],"they":[13],"typically":[14],"face":[15],"two":[16,54,66,107],"main":[17],"challenges:":[18],"the":[19,24,39,47,57,60,65,76,116],"time-expensive":[20],"sampling":[21,48,108],"process":[22],"and":[23],"semantically":[25,84,132],"meaningless":[26],"latent":[27,61,77,117],"space,":[28],"which":[29,134],"are":[30],"often":[31],"addressed":[32],"separately":[33],"previous":[35],"works.":[36],"In":[37],"particular,":[38],"latest":[40],"representative":[41],"work":[42],"Denoising":[43,80],"Diffusion":[44,81],"GAN":[45,82],"reduces":[46],"steps":[49,109],"to":[50,74,130],"as":[51,53],"few":[52],"but":[55],"ignores":[56],"semantics":[58],"of":[59,79,119],"space.":[62],"To":[63],"address":[64],"challenges":[67],"simultaneously,":[68],"we":[69],"propose":[70],"a":[71],"two-stage":[72],"framework":[73],"make":[75],"space":[78,118],"more":[83],"meaningful":[85],"while":[86],"enjoying":[87],"its":[88],"efficiency.":[89],"Extensive":[90],"results":[91,104],"on":[92,138],"three":[93],"benchmark":[94],"datasets":[95],"demonstrate":[96],"that":[97],"our":[98,120],"proposed":[99],"model":[101,122],"achieves":[102],"competitive":[103],"with":[105],"only":[106],"unconditional":[111,125],"generation.":[113],"More":[114],"importantly,":[115],"trained":[123],"for":[124],"generation":[127],"is":[128],"be":[131,136],"meaningful,":[133],"can":[135],"exploited":[137],"various":[139],"downstream":[140],"tasks":[141],"(e.g.,":[142],"attribute":[143],"editing)":[144],"without":[145],"further":[146],"training.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}