{"id":"https://openalex.org/W4394625730","doi":"https://doi.org/10.1109/wacv57701.2024.00288","title":"Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model","display_name":"Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394625730","doi":"https://doi.org/10.1109/wacv57701.2024.00288"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00288","pdf_url":null,"source":{"id":"https://openalex.org/S4363607979","display_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.16817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024041814","display_name":"Shoma Iwai","orcid":"https://orcid.org/0000-0002-6340-3902"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoma Iwai","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009192524","display_name":"Tomo Miyazaki","orcid":"https://orcid.org/0000-0001-5205-0542"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomo Miyazaki","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020830042","display_name":"Shinichiro Omachi","orcid":"https://orcid.org/0000-0001-7706-9995"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichiro Omachi","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.901,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":4,"citation_normalized_percentile":{"value":0.998968,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2888","last_page":"2897"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9999,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9999,"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":0.9996,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994,"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/distortion","display_name":"Distortion (music)","score":0.5447976}],"concepts":[{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.5751404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.56389654},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5447976},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4639629},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.45805845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4541731},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4420759},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.43994167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42089385},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3794772},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.23281264},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.16710472},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12070465},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.07758537},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07153407},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00288","pdf_url":null,"source":{"id":"https://openalex.org/S4363607979","display_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2405.16817","pdf_url":"https://arxiv.org/pdf/2405.16817","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2405.16817","pdf_url":"https://arxiv.org/pdf/2405.16817","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":40,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2949361041","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2982853315","https://openalex.org/W3003267478","https://openalex.org/W3016076140","https://openalex.org/W3034469748","https://openalex.org/W3036167779","https://openalex.org/W3036682213","https://openalex.org/W3091266734","https://openalex.org/W3098418424","https://openalex.org/W3109585842","https://openalex.org/W3131427579","https://openalex.org/W3138516171","https://openalex.org/W3173274771","https://openalex.org/W3175457126","https://openalex.org/W3176591339","https://openalex.org/W3179468628","https://openalex.org/W3202918664","https://openalex.org/W3207406391","https://openalex.org/W4223425316","https://openalex.org/W4230291482","https://openalex.org/W4283220513","https://openalex.org/W4288083516","https://openalex.org/W4292793989","https://openalex.org/W4295682783","https://openalex.org/W4296608491","https://openalex.org/W4297846915","https://openalex.org/W4301206121","https://openalex.org/W4311638103","https://openalex.org/W4312806968","https://openalex.org/W4312934587","https://openalex.org/W4316830033","https://openalex.org/W4372342907","https://openalex.org/W4378771614","https://openalex.org/W4386065641","https://openalex.org/W4386075611","https://openalex.org/W4390874546","https://openalex.org/W569478347"],"related_works":["https://openalex.org/W4378191574","https://openalex.org/W4313046148","https://openalex.org/W4243608781","https://openalex.org/W3165542721","https://openalex.org/W2751842002","https://openalex.org/W2521595930","https://openalex.org/W2161981399","https://openalex.org/W2129829718","https://openalex.org/W1939109514","https://openalex.org/W1843792225"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"neural":[3],"network-driven":[4],"image":[5],"compression":[6],"(NIC)":[7],"has":[8],"gained":[9],"significant":[10],"attention.":[11],"Some":[12],"works":[13],"adopt":[14],"deep":[15],"generative":[16,34,74,124,137],"models":[17,23,50,139],"such":[18],"as":[19],"GANs":[20],"and":[21,88,113],"diffusion":[22],"to":[24,53,56,107],"enhance":[25],"perceptual":[26],"quality":[27],"(realism).":[28],"A":[29],"critical":[30],"obstacle":[31],"of":[32,134,145],"these":[33],"NIC":[35,75,125,138],"methods":[36],"is":[37,41,61],"that":[38],"each":[39],"model":[40],"optimized":[42],"for":[43,63,84],"a":[44,72,90,116,142],"single":[45,117],"bit":[46,58,110,146],"rate.":[47],"Consequently,":[48],"multiple":[49],"are":[51],"required":[52],"compress":[54],"images":[55],"different":[57],"rates,":[59],"which":[60],"impractical":[62],"real-world":[64],"applications.":[65],"To":[66],"tackle":[67],"this":[68],"issue,":[69],"we":[70,78],"propose":[71],"variable-rate":[73,86,123],"model.":[76,151],"Specifically,":[77],"explore":[79],"several":[80],"discriminator":[81],"designs":[82],"tailored":[83],"the":[85,97,105,109,132],"approach":[87],"introduce":[89],"novel":[91],"adversarial":[92],"loss.":[93],"Moreover,":[94],"by":[95],"incorporating":[96],"newly":[98],"proposed":[99],"multi-realism":[100],"technique,":[101],"our":[102,127],"method":[103,128],"allows":[104],"users":[106],"adjust":[108],"rate,":[111],"distortion,":[112],"realism":[114],"with":[115],"model,":[118],"achieving":[119],"ultra-controllability.":[120],"Unlike":[121],"existing":[122],"models,":[126],"matches":[129],"or":[130],"surpasses":[131],"performance":[133],"state-of-the-art":[135],"single-rate":[136],"while":[140],"covering":[141],"wide":[143],"range":[144],"rates":[147],"using":[148],"just":[149],"one":[150]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4394625730","counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2025-01-04T13:29:11.953160","created_date":"2024-04-10"}