{"id":"https://openalex.org/W4312388283","doi":"https://doi.org/10.1109/cvpr52688.2022.01043","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","display_name":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4312388283","doi":"https://doi.org/10.1109/cvpr52688.2022.01043"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52688.2022.01043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01043","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5034954588","display_name":"Shuyang Gu","orcid":"https://orcid.org/0000-0003-4535-2280"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuyang Gu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319452","display_name":"Dong Chen","orcid":"https://orcid.org/0000-0002-0526-9346"},"institutions":[{"id":"https://openalex.org/I4210087053","display_name":"Microsoft (Germany)","ror":"https://ror.org/001dd4s60","country_code":"DE","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210087053"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Dong Chen","raw_affiliation_strings":["Microsoft Cloud+AI","Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI","institution_ids":["https://openalex.org/I4210087053"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074566006","display_name":"Jianmin Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianmin Bao","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070617771","display_name":"Fang Wen","orcid":"https://orcid.org/0000-0002-3170-8971"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fang Wen","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770109","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-9795-4673"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364587","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-4642-4373"},"institutions":[{"id":"https://openalex.org/I4210087053","display_name":"Microsoft (Germany)","ror":"https://ror.org/001dd4s60","country_code":"DE","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210087053"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft Cloud+AI","Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI","institution_ids":["https://openalex.org/I4210087053"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390820","display_name":"Lu Yuan","orcid":"https://orcid.org/0000-0001-7879-0389"},"institutions":[{"id":"https://openalex.org/I4210087053","display_name":"Microsoft (Germany)","ror":"https://ror.org/001dd4s60","country_code":"DE","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210087053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lu Yuan","raw_affiliation_strings":["Microsoft Cloud+AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI","institution_ids":["https://openalex.org/I4210087053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101666011","display_name":"Baining Guo","orcid":"https://orcid.org/0000-0001-8349-8868"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Baining Guo","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5034954588"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":34.6589,"has_fulltext":false,"cited_by_count":614,"citation_normalized_percentile":{"value":0.99772856,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10686","last_page":"10696"},"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":0.991100013256073,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9850000143051147,"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/diffusion","display_name":"Diffusion","score":0.6218078136444092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6109057664871216},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5534512996673584},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5343619585037231},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5027608871459961},{"id":"https://openalex.org/keywords/anisotropic-diffusion","display_name":"Anisotropic diffusion","score":0.4986765384674072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49772027134895325},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4744188189506531},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4656800627708435},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4294959604740143},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4120885729789734},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33165985345840454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2590482234954834},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12117904424667358},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.11428627371788025},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10650691390037537}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6218078136444092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6109057664871216},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5534512996673584},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5343619585037231},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5027608871459961},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.4986765384674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49772027134895325},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4744188189506531},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4656800627708435},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4294959604740143},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4120885729789734},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33165985345840454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2590482234954834},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12117904424667358},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.11428627371788025},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10650691390037537},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52688.2022.01043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01043","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":107,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2129069237","https://openalex.org/W2405756170","https://openalex.org/W2533598788","https://openalex.org/W2557449848","https://openalex.org/W2598991778","https://openalex.org/W2752796333","https://openalex.org/W2788768663","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2903838325","https://openalex.org/W2905434858","https://openalex.org/W2908510526","https://openalex.org/W2912984712","https://openalex.org/W2933890497","https://openalex.org/W2952716587","https://openalex.org/W2953318193","https://openalex.org/W2962770929","https://openalex.org/W2962784628","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963413689","https://openalex.org/W2963612019","https://openalex.org/W2963799213","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964122153","https://openalex.org/W2964216930","https://openalex.org/W2964833232","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2970562079","https://openalex.org/W2971074500","https://openalex.org/W2972328244","https://openalex.org/W2993158499","https://openalex.org/W2995665739","https://openalex.org/W3009811209","https://openalex.org/W3030163527","https://openalex.org/W3034445277","https://openalex.org/W3035500781","https://openalex.org/W3035574324","https://openalex.org/W3036167779","https://openalex.org/W3039253141","https://openalex.org/W3048484056","https://openalex.org/W3090238363","https://openalex.org/W3091653824","https://openalex.org/W3096601784","https://openalex.org/W3108650314","https://openalex.org/W3128876955","https://openalex.org/W3129576130","https://openalex.org/W3134582802","https://openalex.org/W3155072588","https://openalex.org/W3162926177","https://openalex.org/W3165647589","https://openalex.org/W3166396011","https://openalex.org/W3168053944","https://openalex.org/W3174525637","https://openalex.org/W3175528029","https://openalex.org/W3176641147","https://openalex.org/W3180355996","https://openalex.org/W3181640983","https://openalex.org/W3196163807","https://openalex.org/W3206384369","https://openalex.org/W3209532394","https://openalex.org/W4214485011","https://openalex.org/W4287083626","https://openalex.org/W4292779060","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6638575559","https://openalex.org/W6639102338","https://openalex.org/W6713645886","https://openalex.org/W6730746255","https://openalex.org/W6732492507","https://openalex.org/W6735061257","https://openalex.org/W6748596569","https://openalex.org/W6748634568","https://openalex.org/W6755207826","https://openalex.org/W6755312952","https://openalex.org/W6757817989","https://openalex.org/W6762931180","https://openalex.org/W6763128402","https://openalex.org/W6763509872","https://openalex.org/W6765779288","https://openalex.org/W6766556111","https://openalex.org/W6767137312","https://openalex.org/W6767384525","https://openalex.org/W6775142816","https://openalex.org/W6779688448","https://openalex.org/W6779823529","https://openalex.org/W6779879114","https://openalex.org/W6780226713","https://openalex.org/W6781951827","https://openalex.org/W6785719018","https://openalex.org/W6788990321","https://openalex.org/W6790675931","https://openalex.org/W6790978476","https://openalex.org/W6791276965","https://openalex.org/W6791353385","https://openalex.org/W6794269193","https://openalex.org/W6795288823","https://openalex.org/W6796242362","https://openalex.org/W6800989748","https://openalex.org/W6802987763","https://openalex.org/W6803194594"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2005223122"],"abstract_inverted_index":{"We":[0,40],"present":[1],"the":[2,32,57,75,91,126,138,156,163,195,199],"vector":[3,17],"quantized":[4,18],"diffusion":[5,71],"(VQ-Diffusion)":[6],"model":[7,197],"for":[8,48,174],"text-to-image":[9,49,96,115,157],"generation.":[10],"This":[11],"method":[12,45,144],"is":[13,25,46,80,169,201],"based":[14],"on":[15],"a":[16,28,69,81,131,184,211],"variational":[19],"autoencoder":[20],"(VQ-VAE)":[21],"whose":[22],"latent":[23],"space":[24],"modeled":[26],"by":[27,130,150],"conditional":[29],"variant":[30],"of":[31,77,109],"recently":[33],"developed":[34],"Denoising":[35],"Diffusion":[36],"Probabilistic":[37],"Model":[38],"(DDPM).":[39],"find":[41],"that":[42,90,137,194],"this":[43],"latent-space":[44],"well-suited":[47],"generation":[50,97,140,158],"tasks":[51],"because":[52],"it":[53],"not":[54],"only":[55],"eliminates":[56],"unidirectional":[58],"bias":[59],"with":[60,84,101,106,112,162,198],"existing":[61,85],"methods":[62,208],"but":[63],"also":[64],"allows":[65,180],"us":[66,181],"to":[67,73,182],"incorporate":[68],"mask-and-replace":[70],"strategy":[72],"avoid":[74],"accumulation":[76],"errors,":[78],"which":[79],"serious":[82],"problem":[83],"methods.":[86],"Our":[87,191],"experiments":[88,192],"show":[89,136],"VQ-Diffusion":[92,118,179,196],"produces":[93],"significantly":[94],"better":[95,185,212],"results":[98],"when":[99],"compared":[100],"conventional":[102],"autoregressive":[103],"(AR)":[104],"models":[105,218],"similar":[107],"numbers":[108],"parameters.":[110],"Compared":[111],"previous":[113],"GAN-based":[114],"methods,":[116,155],"our":[117,143],"can":[119,145],"handle":[120],"more":[121],"complex":[122],"scenes":[123],"and":[124,167,189,217],"improve":[125],"synthesized":[127],"image":[128,139,165,213],"quality":[129,188],"large":[132],"margin.":[133],"Finally,":[134],"we":[135],"computation":[141],"in":[142],"be":[146],"made":[147],"highly":[148],"efficient":[149],"reparameterization.":[151],"With":[152],"traditional":[153,206],"AR":[154,207],"time":[159,171],"increases":[160],"linearly":[161],"output":[164],"resolution":[166],"hence":[168],"quite":[170],"consuming":[172],"even":[173],"normal":[175],"size":[176],"images.":[177],"The":[178,215],"achieve":[183],"trade-off":[186],"between":[187],"speed.":[190],"indicate":[193],"reparameterization":[200],"fifteen":[202],"times":[203],"faster":[204],"than":[205],"while":[209],"achieving":[210],"quality.":[214],"code":[216],"are":[219],"available":[220],"at":[221],"https://github.com/cientgu/VQ-Diffusion.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":191},{"year":2024,"cited_by_count":242},{"year":2023,"cited_by_count":140},{"year":2022,"cited_by_count":14}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}