{"id":"https://openalex.org/W7141464322","doi":"https://doi.org/10.48550/arxiv.2603.25316","title":"Adaptive Learned Image Compression with Graph Neural Networks","display_name":"Adaptive Learned Image Compression with Graph Neural Networks","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141464322","doi":"https://doi.org/10.48550/arxiv.2603.25316"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25316","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.25316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072947255","display_name":"Yunuo Chen","orcid":"https://orcid.org/0000-0003-4791-6393"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Yunuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130734668","display_name":"Bing He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Bing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130793538","display_name":"Zezheng Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Zezheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130774159","display_name":"Hongwei Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Hongwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130768063","display_name":"Qunshan Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Qunshan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130752827","display_name":"Yuan Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130779554","display_name":"Guo Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Guo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072947255"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.5144000053405762,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.5144000053405762,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.0917000025510788,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.03759999945759773,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7038000226020813},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5256999731063843},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.49219998717308044},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.486299991607666},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46639999747276306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3993000090122223},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3968000113964081},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.3756999969482422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064999938011169},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7038000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5256999731063843},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.2639999985694885},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25316","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.25316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25316","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"image":[1,15,85],"compression":[2,16,86],"relies":[3],"on":[4,21,89,122,169],"modeling":[5],"both":[6],"local":[7,123],"and":[8,32,40,148,164,172],"global":[9,75],"redundancy.":[10],"Most":[11],"state-of-the-art":[12,156],"(SOTA)":[13],"learned":[14],"(LIC)":[17],"methods":[18],"are":[19,26],"based":[20,88,121],"CNNs":[22],"or":[23],"Transformers,":[24],"which":[25,44],"inherently":[27],"rigid.":[28],"Standard":[29],"CNN":[30],"kernels":[31],"window-based":[33],"attention":[34],"mechanisms":[35],"impose":[36],"fixed":[37],"receptive":[38,104],"fields":[39],"static":[41],"connectivity":[42,110],"patterns,":[43],"potentially":[45],"couple":[46],"non-redundant":[47],"pixels":[48],"simply":[49],"due":[50],"to":[51,63,136,145,167],"their":[52],"proximity":[53],"in":[54],"Euclidean":[55],"space.":[56],"This":[57],"rigidity":[58],"limits":[59],"the":[60,70,74,114],"model's":[61],"ability":[62],"adaptively":[64],"capture":[65],"spatially":[66],"varying":[67],"redundancy":[68,140],"across":[69,142],"image,":[71],"particularly":[72],"at":[73,179],"level.":[76],"To":[77],"overcome":[78],"these":[79],"limitations,":[80],"we":[81,107],"propose":[82],"a":[83],"content-adaptive":[84],"framework":[87],"Graph":[90],"Neural":[91],"Networks":[92],"(GNNs).":[93],"Specifically,":[94],"our":[95,129],"approach":[96],"constructs":[97],"dual-scale":[98],"graphs":[99],"that":[100,153],"enable":[101],"flexible,":[102],"data-driven":[103],"fields.":[105],"Furthermore,":[106],"introduce":[108],"adaptive":[109,149],"by":[111],"dynamically":[112],"adjusting":[113],"number":[115],"of":[116,161],"neighbors":[117],"for":[118],"each":[119],"node":[120],"content":[124],"complexity.":[125],"These":[126],"innovations":[127],"empower":[128],"Graph-based":[130],"Learned":[131],"Image":[132],"Compression":[133],"(GLIC)":[134],"model":[135,138],"effectively":[137],"diverse":[139],"patterns":[141],"images,":[143],"leading":[144],"more":[146],"efficient":[147],"compression.":[150],"Experiments":[151],"demonstrate":[152],"GLIC":[154],"achieves":[155],"performance,":[157],"achieving":[158],"BD-rate":[159],"reductions":[160],"19.29%,":[162],"21.69%,":[163],"18.71%":[165],"relative":[166],"VTM-9.1":[168],"Kodak,":[170],"Tecnick,":[171],"CLIC,":[173],"respectively.":[174],"Code":[175],"will":[176],"be":[177],"released":[178],"https://github.com/UnoC-727/GLIC.":[180]},"counts_by_year":[],"updated_date":"2026-03-28T06:16:51.555046","created_date":"2026-03-28T00:00:00"}