{"id":"https://openalex.org/W2564591810","doi":"https://doi.org/10.1109/iccv.2017.629","title":"StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks","display_name":"StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2564591810","doi":"https://doi.org/10.1109/iccv.2017.629","mag":"2564591810"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2017.629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.03242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100399257","display_name":"Han Zhang","orcid":"https://orcid.org/0000-0001-7072-2189"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Han Zhang","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621909","display_name":"Tao Xu","orcid":"https://orcid.org/0000-0003-3705-4152"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Xu","raw_affiliation_strings":["Lehigh University"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066553616","display_name":"Shaoting Zhang","orcid":"https://orcid.org/0000-0002-8719-448X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoting Zhang","raw_affiliation_strings":["Baidu Research"],"affiliations":[{"raw_affiliation_string":"Baidu Research","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444820","display_name":"Xiaogang Wang","orcid":"https://orcid.org/0000-0002-7929-5889"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaogang Wang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000467703","display_name":"Xiaolei Huang","orcid":"https://orcid.org/0000-0003-2338-6535"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolei Huang","raw_affiliation_strings":["Lehigh University"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109600054","display_name":"Dimitris Metaxas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dimitris Metaxas","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100399257"],"corresponding_institution_ids":["https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":45.1562,"has_fulltext":true,"cited_by_count":706,"citation_normalized_percentile":{"value":0.99853751,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5908","last_page":"5916"},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.9861999750137329,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9843999743461609,"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":0.7686679363250732},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7169795632362366},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7090252637863159},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6512701511383057},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6447466611862183},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5737618803977966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365047454833984},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5313571095466614},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4736539125442505},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.44864070415496826},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.43392547965049744},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.41364622116088867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33287373185157776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10932686924934387},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07948324084281921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686679363250732},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7169795632362366},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7090252637863159},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6512701511383057},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6447466611862183},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5737618803977966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365047454833984},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5313571095466614},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4736539125442505},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.44864070415496826},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.43392547965049744},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.41364622116088867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33287373185157776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10932686924934387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07948324084281921},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv.2017.629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1612.03242","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.03242","pdf_url":"https://arxiv.org/pdf/1612.03242","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"mag:2564591810","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1612.03242.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1612.03242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1612.03242","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1612.03242","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.03242","pdf_url":"https://arxiv.org/pdf/1612.03242","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2564591810.pdf","grobid_xml":"https://content.openalex.org/works/W2564591810.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1850742715","https://openalex.org/W1861492603","https://openalex.org/W1893585201","https://openalex.org/W1909320841","https://openalex.org/W2125389028","https://openalex.org/W2183341477","https://openalex.org/W2184218725","https://openalex.org/W2194775991","https://openalex.org/W2298992465","https://openalex.org/W2398118205","https://openalex.org/W2423557781","https://openalex.org/W2434741482","https://openalex.org/W2467604901","https://openalex.org/W2521028896","https://openalex.org/W2523714292","https://openalex.org/W2524985544","https://openalex.org/W2533598788","https://openalex.org/W2548275288","https://openalex.org/W2553897675","https://openalex.org/W2566832195","https://openalex.org/W2949650786","https://openalex.org/W2950560720","https://openalex.org/W2951004968","https://openalex.org/W2963143316","https://openalex.org/W2964201867","https://openalex.org/W6621378261","https://openalex.org/W6639102338","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6683074461","https://openalex.org/W6685352114","https://openalex.org/W6687500345","https://openalex.org/W6687506355","https://openalex.org/W6697565712","https://openalex.org/W6713645886","https://openalex.org/W6718140377","https://openalex.org/W6718379498","https://openalex.org/W6726794401","https://openalex.org/W6727340567","https://openalex.org/W6727420689","https://openalex.org/W6727501944","https://openalex.org/W6728889164","https://openalex.org/W6729116442","https://openalex.org/W6729482032","https://openalex.org/W6729767818","https://openalex.org/W6729966448","https://openalex.org/W6730095352","https://openalex.org/W6731602930","https://openalex.org/W6732249622","https://openalex.org/W6733322467","https://openalex.org/W6743907487","https://openalex.org/W6764108317"],"related_works":["https://openalex.org/W2963981733","https://openalex.org/W2963966654","https://openalex.org/W2963470893","https://openalex.org/W2963073614","https://openalex.org/W2962793481","https://openalex.org/W2962760235","https://openalex.org/W2951939904","https://openalex.org/W2949999304","https://openalex.org/W2893749619","https://openalex.org/W2739748921","https://openalex.org/W2548275288","https://openalex.org/W2432004435","https://openalex.org/W2331128040","https://openalex.org/W2194775991","https://openalex.org/W2173520492","https://openalex.org/W2125389028","https://openalex.org/W2099471712","https://openalex.org/W1901129140","https://openalex.org/W1834627138","https://openalex.org/W1522301498"],"abstract_inverted_index":{"Synthesizing":[0],"high-quality":[1],"images":[2,59,113,141,184],"from":[3],"text":[4,62,93,106,187],"descriptions":[5,107],"is":[6,118],"a":[7,74,151],"challenging":[8],"problem":[9,68],"in":[10,123,159],"computer":[11],"vision":[12],"and":[13,41,84,105,110,126,142,166],"has":[14],"many":[15],"practical":[16],"applications.":[17],"Samples":[18],"generated":[19],"by":[20],"existing":[21],"textto-":[22],"image":[23],"approaches":[24],"can":[25],"roughly":[26],"reflect":[27],"the":[28,31,66,81,87,91,131,136,139,144,147,160,175],"meaning":[29],"of":[30,86,138,146],"given":[32,92],"descriptions,":[33],"but":[34],"they":[35],"fail":[36],"to":[37,55,120],"contain":[38],"necessary":[39],"details":[40,129],"vivid":[42],"object":[43,88],"parts.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,149],"propose":[49],"Stacked":[50],"Generative":[51],"Adversarial":[52],"Networks":[53],"(StackGAN)":[54],"generate":[56],"256.256":[57],"photo-realistic":[58,115,183],"conditioned":[60,185],"on":[61,90,170,181,186],"descriptions.":[63,188],"We":[64],"decompose":[65],"hard":[67],"into":[69],"more":[70],"manageable":[71],"sub-problems":[72],"through":[73],"sketch-refinement":[75],"process.":[76,133],"The":[77,99],"Stage-I":[78,96,103,124],"GAN":[79,101],"sketches":[80],"primitive":[82],"shape":[83],"colors":[85],"based":[89],"description,":[94],"yielding":[95],"low-resolution":[97],"images.":[98],"Stage-II":[100],"takes":[102],"results":[104,125],"as":[108],"inputs,":[109],"generates":[111],"high-resolution":[112],"with":[114,130,168],"details.":[116],"It":[117],"able":[119],"rectify":[121],"defects":[122],"add":[127],"compelling":[128],"refinement":[132],"To":[134],"improve":[135],"diversity":[137],"synthesized":[140],"stabilize":[143],"training":[145],"conditional-GAN,":[148],"introduce":[150],"novel":[152],"Conditioning":[153],"Augmentation":[154],"technique":[155],"that":[156,174],"encourages":[157],"smoothness":[158],"latent":[161],"conditioning":[162],"manifold.":[163],"Extensive":[164],"experiments":[165],"comparisons":[167],"state-of-the-arts":[169],"benchmark":[171],"datasets":[172],"demonstrate":[173],"proposed":[176],"method":[177],"achieves":[178],"significant":[179],"improvements":[180],"generating":[182]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":119},{"year":2020,"cited_by_count":127},{"year":2019,"cited_by_count":172},{"year":2018,"cited_by_count":134},{"year":2017,"cited_by_count":56},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}