{"id":"https://openalex.org/W7118266272","doi":"https://doi.org/10.48550/arxiv.2601.00703","title":"Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks","display_name":"Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks","publication_year":2026,"publication_date":"2026-01-02","ids":{"openalex":"https://openalex.org/W7118266272","doi":"https://doi.org/10.48550/arxiv.2601.00703"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.00703","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122228213","display_name":"Cory Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fan, Cory","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122092853","display_name":"Wenchao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenchao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122228213"],"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.7337999939918518,"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":0.7337999939918518,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.022700000554323196,"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/demosaicing","display_name":"Demosaicing","score":0.847000002861023},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.8313000202178955},{"id":"https://openalex.org/keywords/color-filter-array","display_name":"Color filter array","score":0.5916000008583069},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4666000008583069},{"id":"https://openalex.org/keywords/isotropy","display_name":"Isotropy","score":0.439300000667572},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4133000075817108},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.398499995470047}],"concepts":[{"id":"https://openalex.org/C27624317","wikidata":"https://www.wikidata.org/wiki/Q263499","display_name":"Demosaicing","level":5,"score":0.847000002861023},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8313000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7024000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6453999876976013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6244000196456909},{"id":"https://openalex.org/C177299597","wikidata":"https://www.wikidata.org/wiki/Q2468214","display_name":"Color filter array","level":5,"score":0.5916000008583069},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C5622133","wikidata":"https://www.wikidata.org/wiki/Q812133","display_name":"Bayer filter","level":5,"score":0.39719998836517334},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C142771000","wikidata":"https://www.wikidata.org/wiki/Q1435398","display_name":"Color gel","level":4,"score":0.337799996137619},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.3021000027656555},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C173642442","wikidata":"https://www.wikidata.org/wiki/Q1253346","display_name":"Decimation","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26579999923706055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.00703","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.00703","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.00703","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":"pmh:doi:10.48550/arxiv.2601.00703","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.4733392894268036,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"digital":[1,34],"imaging,":[2],"image":[3,28,63,162],"demosaicing":[4,45,64,69,163],"is":[5,24],"a":[6,16,99,126,159],"crucial":[7],"first":[8],"step":[9],"which":[10],"recovers":[11],"the":[12,104,145],"RGB":[13],"information":[14],"from":[15,132],"color":[17],"filter":[18],"array":[19],"(CFA).":[20],"Oftentimes,":[21],"deep":[22,42],"learning":[23,43],"utilized":[25],"to":[26,44,87,98],"perform":[27],"demosaicing.":[29],"Given":[30],"that":[31,95,136],"most":[32],"modern":[33],"imaging":[35],"applications":[36],"occur":[37],"on":[38,158],"mobile":[39,84],"platforms,":[40],"applying":[41],"requires":[46],"lightweight":[47],"and":[48,65,76,106,122,134,164],"efficient":[49],"networks.":[50,110],"Isotropic":[51],"networks,":[52,57],"also":[53],"known":[54],"as":[55],"residual-in-residual":[56],"have":[58],"been":[59],"often":[60,79],"employed":[61],"for":[62,83],"joint-demosaicing-and-denoising":[66],"(JDD).":[67],"Most":[68],"isotropic":[70,89,109],"networks":[71,120,153],"avoid":[72],"spatial":[73,96],"downsampling":[74,97,124,137],"entirely,":[75],"thus":[77],"are":[78],"prohibitively":[80],"expensive":[81],"computationally":[82],"applications.":[85],"Contrary":[86],"previous":[88],"network":[90],"designs,":[91],"this":[92,113],"paper":[93],"claims":[94],"signficant":[100],"degree":[101],"can":[102],"improve":[103],"efficiency":[105],"performance":[107,157],"of":[108,144,149,161],"To":[111],"validate":[112],"claim,":[114],"we":[115],"design":[116,129],"simple":[117],"fully":[118,151],"convolutional":[119,152],"with":[121],"without":[123],"using":[125],"mathematical":[127],"architecture":[128],"technique":[130],"adapted":[131],"DeepMAD,":[133],"find":[135],"improves":[138],"empirical":[139,142,156],"performance.":[140],"Additionally,":[141],"testing":[143],"downsampled":[146],"variant,":[147],"JD3Net,":[148],"our":[150],"reveals":[154],"strong":[155],"variety":[160],"JDD":[165],"tasks.":[166]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-01-08T00:00:00"}