{"id":"https://openalex.org/W4402716316","doi":"https://doi.org/10.1109/cvpr52733.2024.00729","title":"Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis","display_name":"Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402716316","doi":"https://doi.org/10.1109/cvpr52733.2024.00729"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101283118","display_name":"Yuchao Gu","orcid":"https://orcid.org/0009-0007-7167-8766"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchao Gu","raw_affiliation_strings":["Show Lab, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Show Lab, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538534","display_name":"Xintao Wang","orcid":"https://orcid.org/0000-0001-6585-8604"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xintao Wang","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047802386","display_name":"Yixiao Ge","orcid":"https://orcid.org/0000-0002-5351-5329"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiao Ge","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["Show Lab, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Show Lab, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7631","last_page":"7640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9987000226974487,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9962000250816345,"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":0.4824858009815216},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.481682151556015},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4338175058364868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3969830572605133},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3746262490749359},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3209728002548218},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.24439644813537598}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4824858009815216},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.481682151556015},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4338175058364868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3969830572605133},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3746262490749359},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3209728002548218},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.24439644813537598}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":74,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W967544008","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2016589492","https://openalex.org/W2108598243","https://openalex.org/W2423557781","https://openalex.org/W2603777577","https://openalex.org/W2752796333","https://openalex.org/W2938704169","https://openalex.org/W2942415903","https://openalex.org/W2950689937","https://openalex.org/W2952716587","https://openalex.org/W2962770929","https://openalex.org/W2962784628","https://openalex.org/W2962785568","https://openalex.org/W2963250244","https://openalex.org/W2963799213","https://openalex.org/W2971074500","https://openalex.org/W3009561768","https://openalex.org/W3034445277","https://openalex.org/W3035524453","https://openalex.org/W3035574324","https://openalex.org/W3036167779","https://openalex.org/W3036224891","https://openalex.org/W3087124270","https://openalex.org/W3089425003","https://openalex.org/W3096831136","https://openalex.org/W3128876955","https://openalex.org/W3129576130","https://openalex.org/W3152733922","https://openalex.org/W3165647589","https://openalex.org/W3166396011","https://openalex.org/W3168053944","https://openalex.org/W3170863103","https://openalex.org/W3180355996","https://openalex.org/W3206395542","https://openalex.org/W3213665720","https://openalex.org/W3213836217","https://openalex.org/W3215434919","https://openalex.org/W4281632497","https://openalex.org/W4281771798","https://openalex.org/W4283373024","https://openalex.org/W4283388932","https://openalex.org/W4287083626","https://openalex.org/W4287282209","https://openalex.org/W4288099666","https://openalex.org/W4296564887","https://openalex.org/W4301914798","https://openalex.org/W4312326192","https://openalex.org/W4312400623","https://openalex.org/W4312535427","https://openalex.org/W4312633146","https://openalex.org/W4312804044","https://openalex.org/W4312974539","https://openalex.org/W4313021454","https://openalex.org/W4313156423","https://openalex.org/W6621543089","https://openalex.org/W6747491877","https://openalex.org/W6762931180","https://openalex.org/W6763509872","https://openalex.org/W6779823529","https://openalex.org/W6779879114","https://openalex.org/W6779997284","https://openalex.org/W6788990321","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6796242362","https://openalex.org/W6796698253","https://openalex.org/W6798447524","https://openalex.org/W6800989748","https://openalex.org/W6804432862","https://openalex.org/W6810595431"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Vector-Quantized":[0],"(VQ-based)":[1],"generative":[2,14,40,73,162],"models":[3,163],"usually":[4],"consist":[5],"of":[6,24,39,53,87,180,186],"two":[7,84,113,119],"basic":[8],"components,":[9],"i.e.,":[10],"VQ":[11,25,54,69,88],"tokenizers":[12,26,55,70],"and":[13,79,95,143,147,167,182,204],"transformers.":[15,41],"Prior":[16],"research":[17],"focuses":[18],"on":[19,188],"improving":[20,49],"the":[21,31,36,50,60,118,122,136,141,149],"reconstruction":[22,34,51],"fidelity":[23,52],"but":[27,145],"rarely":[28],"examines":[29],"how":[30],"improvement":[32,196],"in":[33],"affects":[35],"generation":[37],"ability":[38,75],"In":[42,121,135],"this":[43],"paper,":[44],"we":[45,107,125,139],"surprisingly":[46],"find":[47],"that":[48,102],"does":[56],"not":[57],"necessarily":[58],"improve":[59],"generation.":[61,170],"Instead,":[62],"learning":[63,114],"to":[64,76,116,151],"compress":[65],"semantic":[66,93,133],"features":[67],"within":[68],"significantly":[71,159],"improves":[72,160],"transformers'":[74],"capture":[77],"textures":[78],"structures.":[80],"We":[81],"thus":[82],"highlight":[83],"competing":[85],"objectives":[86],"tokeniz-ers":[89],"for":[90,131,164],"image":[91,169],"synthesis:":[92],"compression":[94],"details":[96,105,154],"preservation.":[97,155],"Different":[98],"from":[99],"previous":[100],"work":[101],"pri-oritizes":[103],"better":[104,132,153],"preservation,":[106],"propose":[108,126],"Semantic-Quantized":[109],"GAN":[110],"(SeQ-GAN)":[111],"with":[112],"phases":[115],"balance":[117],"objectives.":[120],"first":[123],"phase,":[124,138],"a":[127,174,194],"semantic-enhanced":[128],"perceptual":[129],"loss":[130],"compression.":[134],"second":[137],"fix":[140],"encoder":[142],"codebook,":[144],"enhance":[146],"finetune":[148],"decoder":[150],"achieve":[152],"Our":[156],"proposed":[157],"SeQ-GAN":[158,172],"VQ-based":[161],"both":[165],"un-conditional":[166],"conditional":[168],"Specifically,":[171],"achieves":[173],"Fr\u00e9":[175],"chet":[176],"Inception":[177,183],"Distance":[178],"(FID)":[179],"6.25":[181],"Score":[184],"(IS)":[185],"140.9":[187],"256\u00d7256":[189],"Ima-geNet":[190],"generation,":[191],"which":[192,200],"is":[193],"remarkable":[195],"over":[197],"VIT-VQGAN":[198],"(714M),":[199],"obtains":[201],"11.2":[202],"FID":[203],"97.2":[205],"IS.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}