{"id":"https://openalex.org/W3086960204","doi":null,"title":"Residual Learning for Effective joint Demosaicing-Denoising","display_name":"Residual Learning for Effective joint Demosaicing-Denoising","publication_year":2020,"publication_date":"2020-09-14","ids":{"openalex":"https://openalex.org/W3086960204","mag":"3086960204"},"language":"en","primary_location":{"id":"mag:3086960204","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2009.06205.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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.06205.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037365971","display_name":"Yu Guo","orcid":"https://orcid.org/0000-0002-0642-7684","observed_orcids":["https://orcid.org/0000-0002-0642-7684","https://orcid.org/0000-0003-2571-0247"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Guo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0642-7684","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056596552","display_name":"Qiyu Jin","orcid":"https://orcid.org/0000-0001-8639-233X","observed_orcids":["https://orcid.org/0000-0001-8639-233X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiyu Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073617460","display_name":"Gabriele Facciolo","orcid":"https://orcid.org/0000-0002-8855-8513","observed_orcids":["https://orcid.org/0000-0002-8855-8513"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriele Facciolo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8855-8513","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059443966","display_name":"Tieyong Zeng","orcid":"https://orcid.org/0000-0002-0688-202X","observed_orcids":["https://orcid.org/0000-0002-0688-202X","https://orcid.org/0009-0005-0626-8782"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tieyong Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057798674","display_name":"Jean\u2010Michel Morel","orcid":"https://orcid.org/0000-0002-6108-897X","observed_orcids":["https://orcid.org/0000-0002-6108-897X","https://orcid.org/0000-0002-7122-9924"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean\u2010Michel Morel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"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":0.7407000064849854,"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":0.7407000064849854,"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":0.23229999840259552,"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/T11019","display_name":"Image Enhancement Techniques","score":0.01759999990463257,"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-denoising","display_name":"image denoising","score":0.9909999966621399},{"id":"https://openalex.org/keywords/color-image-processing","display_name":"color image processing","score":0.6230000257492065},{"id":"https://openalex.org/keywords/color-filter-array","display_name":"color filter array","score":0.7269999980926514},{"id":"https://openalex.org/keywords/residual-learning","display_name":"residual learning","score":0.652999997138977},{"id":"https://openalex.org/keywords/over-smoothing","display_name":"over-smoothing","score":0.8700000047683716},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7099999785423279},{"id":"https://openalex.org/keywords/inception-architecture","display_name":"Inception architecture","score":0.890999972820282},{"id":"https://openalex.org/keywords/channel-fusion","display_name":"channel fusion","score":0.6179999709129333}],"concepts":[{"id":"https://openalex.org/C27624317","wikidata":"https://www.wikidata.org/wiki/Q263499","display_name":"Demosaicing","level":5,"score":0.9651297330856323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7503432631492615},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6140432953834534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021748781204224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5503432750701904},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5493344068527222},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5049901604652405},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.50338214635849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41617482900619507},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.3697036802768707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35730797052383423},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3529319167137146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3086960204","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2009.06205.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}],"best_oa_location":{"id":"mag:3086960204","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2009.06205.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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1912194039","https://openalex.org/W1930824406","https://openalex.org/W1969210895","https://openalex.org/W1991350218","https://openalex.org/W1999046526","https://openalex.org/W2022007237","https://openalex.org/W2028140315","https://openalex.org/W2047710600","https://openalex.org/W2053779250","https://openalex.org/W2097117768","https://openalex.org/W2117396329","https://openalex.org/W2129381747","https://openalex.org/W2133665775","https://openalex.org/W2153377815","https://openalex.org/W2155838693","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2263237637","https://openalex.org/W2508457857","https://openalex.org/W2556068545","https://openalex.org/W2556872594","https://openalex.org/W2735224642","https://openalex.org/W2755686313","https://openalex.org/W2773272881","https://openalex.org/W2787700404","https://openalex.org/W2792690686","https://openalex.org/W2890691497","https://openalex.org/W2902220826","https://openalex.org/W2962814024","https://openalex.org/W2964350391","https://openalex.org/W2972987928","https://openalex.org/W2985577924","https://openalex.org/W3010638262","https://openalex.org/W3012166502","https://openalex.org/W3033707728","https://openalex.org/W3035331337","https://openalex.org/W3035373645","https://openalex.org/W3035496815","https://openalex.org/W3035542568","https://openalex.org/W3035557850"],"related_works":["https://openalex.org/W4378648416","https://openalex.org/W2883112417","https://openalex.org/W2921595853","https://openalex.org/W4387663896","https://openalex.org/W4399565046","https://openalex.org/W2793676054","https://openalex.org/W2971711696","https://openalex.org/W3035373645","https://openalex.org/W127774432","https://openalex.org/W2902220826"],"abstract_inverted_index":{"Image":[0],"demosaicking":[1,96,107,180],"and":[2,23,32,97,113,144,173,204],"denoising":[3,21,67],"are":[4,229],"the":[5,47,51,55,89,101,126,130,157,179,201,217],"two":[6],"key":[7,158],"steps":[8],"for":[9,65,140,224],"color":[10,123,194],"image":[11,48,124,133,172,207],"production":[12],"pipeline.":[13],"The":[14],"classical":[15],"processing":[16,92],"sequence":[17,28],"consists":[18],"of":[19,54,185,219,249],"applying":[20],"first,":[22],"then":[24,98],"demosaicking.":[25],"However,":[26],"this":[27,43,76,82],"leads":[29],"to":[30,41,80,119,160,177,189],"oversmoothing":[31],"unpleasant":[33],"checkerboard":[34,202],"effect.":[35],"Moreover,":[36],"it":[37,210],"is":[38,49,62,156],"very":[39,213],"difficult":[40],"change":[42],"order,":[44],"because":[45],"once":[46],"demosaicked,":[50],"statistical":[52,73],"properties":[53],"noise":[56,182,215,225],"will":[57],"be":[58],"changed":[59],"dramatically.":[60],"This":[61,149],"extremely":[63],"challenging":[64],"traditional":[66,90,111],"models":[68],"that":[69,109,155,187,236],"strongly":[70],"rely":[71],"on":[72],"assumptions.":[74],"In":[75,100],"paper,":[77],"we":[78,87,104,135,167],"attempt":[79],"tackle":[81],"prickly":[83],"problem.":[84],"Indeed,":[85],"here":[86],"invert":[88],"CFA":[91],"pipeline":[93],"by":[94],"first":[95,102],"denoising.":[99],"stage,":[103],"design":[105],"a":[106,114,121,169,191],"algorithm":[108,198],"combines":[110],"methods":[112,223,241],"convolutional":[115],"neural":[116],"network":[117],"(CNN)":[118],"reconstruct":[120],"full":[122,193],"ignoring":[125],"noise.":[127],"To":[128],"improve":[129],"performance":[131],"in":[132,247],"demosaicking,":[134,166],"modify":[136],"an":[137],"Inception":[138],"architecture":[139],"fusing":[141],"R,":[142],"G":[143],"B":[145],"three":[146],"channels":[147],"information.":[148],"stage":[150],"retains":[151,205],"all":[152],"known":[153],"information":[154],"point":[159],"obtain":[161,190],"pleasurable":[162],"final":[163],"results.":[164],"After":[165],"get":[168],"noisy":[170],"full-color":[171],"use":[174],"another":[175],"CNN":[176,221],"learn":[178],"residual":[181],"(including":[183],"artifacts)":[184],"it,":[186],"allows":[188],"restored":[192],"image.":[195],"Our":[196],"proposed":[197],"completely":[199],"avoids":[200],"effect":[203],"more":[206],"detail.":[208],"Furthermore,":[209],"can":[211],"process":[212],"high-level":[214],"while":[216],"performances":[218],"other":[220],"based":[222],"higher":[226],"than":[227],"20":[228],"rather":[230],"limited.":[231],"Experimental":[232],"results":[233],"show":[234],"clearly":[235],"our":[237],"method":[238],"outperforms":[239],"state-of-the-art":[240],"both":[242],"quantitatively":[243],"as":[244,246],"well":[245],"terms":[248],"visual":[250],"quality.":[251]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2020-09-21T00:00:00"}