{"id":"https://openalex.org/W3135058862","doi":"https://doi.org/10.48550/arxiv.2103.03841","title":"Generating Images with Sparse Representations","display_name":"Generating Images with Sparse Representations","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3135058862","doi":"https://doi.org/10.48550/arxiv.2103.03841","mag":"3135058862"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2103.03841","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03841","pdf_url":"https://arxiv.org/pdf/2103.03841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.03841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031250211","display_name":"Charlie Nash","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nash, Charlie","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088720016","display_name":"Jacob Menick","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Menick, Jacob","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034960578","display_name":"Sander Dieleman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dieleman, Sander","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059792149","display_name":"Peter Battaglia","orcid":"https://orcid.org/0000-0003-3622-7111","observed_orcids":["https://orcid.org/0000-0003-3622-7111"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Battaglia, Peter W.","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"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":true,"cited_by_count":226,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7958","last_page":"7968"},"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":0.9984999895095825,"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":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00039999998989515007,"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":9.999999747378752e-05,"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/image-generation","display_name":"image generation","score":0.9179999828338623},{"id":"https://openalex.org/keywords/sparse-representation","display_name":"sparse representation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"discrete cosine transform","score":0.843999981880188},{"id":"https://openalex.org/keywords/autoregressive-models","display_name":"autoregressive models","score":0.6980000138282776},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.4959999918937683},{"id":"https://openalex.org/keywords/image-compression","display_name":"image compression","score":0.5899999737739563},{"id":"https://openalex.org/keywords/image-colorization","display_name":"image colorization","score":0.8700000047683716},{"id":"https://openalex.org/keywords/super-resolution","display_name":"super-resolution","score":0.7049999833106995},{"id":"https://openalex.org/keywords/high-resolution-image-synthesis","display_name":"high-resolution image generation","score":0.6729999780654907}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7812701463699341},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6700149774551392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568558216094971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.622748613357544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6018565893173218},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4533398449420929},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.4529688060283661},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39076778292655945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33720481395721436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32382306456565857},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2103.03841","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03841","pdf_url":"https://arxiv.org/pdf/2103.03841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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:3135058862","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.03841.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2103.03841","doi":"https://doi.org/10.48550/arxiv.2103.03841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.03841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3169734832","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v139/nash21a/nash21a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.03841","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03841","pdf_url":"https://arxiv.org/pdf/2103.03841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135058862.pdf","grobid_xml":"https://content.openalex.org/works/W3135058862.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W967544008","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2031614119","https://openalex.org/W2079145130","https://openalex.org/W2099471712","https://openalex.org/W2117539524","https://openalex.org/W2133665775","https://openalex.org/W2140196014","https://openalex.org/W2156886646","https://openalex.org/W2183341477","https://openalex.org/W2267126114","https://openalex.org/W2561715562","https://openalex.org/W2626778328","https://openalex.org/W2893749619","https://openalex.org/W2902630600","https://openalex.org/W2904367110","https://openalex.org/W2940744433","https://openalex.org/W2947590261","https://openalex.org/W2962760235","https://openalex.org/W2963090522","https://openalex.org/W2963139417","https://openalex.org/W2963799213","https://openalex.org/W2963981733","https://openalex.org/W2964121744","https://openalex.org/W2970607325","https://openalex.org/W2971128425","https://openalex.org/W2994673210","https://openalex.org/W2995327724","https://openalex.org/W2997517014","https://openalex.org/W3001279689","https://openalex.org/W3010768098","https://openalex.org/W3021164770","https://openalex.org/W3034445277","https://openalex.org/W3100971012","https://openalex.org/W3125056032","https://openalex.org/W6906509723"],"related_works":["https://openalex.org/W4312974539","https://openalex.org/W7124905231","https://openalex.org/W4403853941","https://openalex.org/W4312254454","https://openalex.org/W2952583441","https://openalex.org/W4386076713","https://openalex.org/W2947590261","https://openalex.org/W4288044063","https://openalex.org/W7133194075","https://openalex.org/W4405644891"],"abstract_inverted_index":{"The":[0],"high":[1,101,117],"dimensionality":[2],"of":[3,65,89,107,128],"images":[4,50],"presents":[5],"architecture":[6],"and":[7,48,70,96,145],"sampling-efficiency":[8],"challenges":[9],"for":[10,32],"likelihood-based":[11,33],"generative":[12],"models.":[13,34,147],"Previous":[14],"approaches":[15],"such":[16,94],"as":[17,30,62],"VQ-VAE":[18],"use":[19],"deep":[20],"autoencoders":[21],"to":[22,51,83,100,138],"obtain":[23],"compact":[24],"representations,":[25],"which":[26,58,80,97],"are":[27,59],"more":[28],"practical":[29],"inputs":[31],"We":[35,74,132],"present":[36],"an":[37],"alternative":[38],"approach,":[39],"inspired":[40],"by":[41],"common":[42],"image":[43,108,143],"compression":[44],"methods":[45],"like":[46],"JPEG,":[47],"convert":[49],"quantized":[52],"discrete":[53],"cosine":[54],"transform":[55],"(DCT)":[56],"blocks,":[57],"represented":[60],"sparsely":[61],"a":[63,76,105],"sequence":[64],"DCT":[66,71],"channel,":[67],"spatial":[68],"location,":[69],"coefficient":[72],"triples.":[73],"propose":[75],"Transformer-based":[77],"autoregressive":[78],"architecture,":[79],"is":[81],"trained":[82],"sequentially":[84],"predict":[85],"the":[86,90,129],"conditional":[87],"distribution":[88],"next":[91],"element":[92],"in":[93],"sequences,":[95],"scales":[98],"effectively":[99],"resolution":[102],"images.":[103],"On":[104],"range":[106],"datasets,":[109],"we":[110],"demonstrate":[111],"that":[112,135],"our":[113,139],"approach":[114],"can":[115],"generate":[116],"quality,":[118],"diverse":[119],"images,":[120],"with":[121,126],"sample":[122],"metric":[123],"scores":[124],"competitive":[125],"state":[127],"art":[130],"methods.":[131],"additionally":[133],"show":[134],"simple":[136],"modifications":[137],"method":[140],"yield":[141],"effective":[142],"colorization":[144],"super-resolution":[146]},"counts_by_year":[{"year":2026,"cited_by_count":48},{"year":2025,"cited_by_count":65},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-03-15T00:00:00"}