{"id":"https://openalex.org/W3194727438","doi":null,"title":"An Efficient Dual-reference Training Data Acquisition Method for CNN Image Super-Resolution.","display_name":"An Efficient Dual-reference Training Data Acquisition Method for CNN Image Super-Resolution.","publication_year":2021,"publication_date":"2021-08-05","ids":{"openalex":"https://openalex.org/W3194727438","mag":"3194727438"},"language":"en","primary_location":{"id":"mag:3194727438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2108.02348.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":"http://arxiv.org/pdf/2108.02348.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010685961","display_name":"Yanhui Guo","orcid":"https://orcid.org/0000-0002-9908-3795","observed_orcids":["https://orcid.org/0000-0002-9908-3795"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhui Guo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9908-3795","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705272","display_name":"Xiao Shu","orcid":"https://orcid.org/0000-0002-6215-2507","observed_orcids":["https://orcid.org/0000-0002-6215-2507"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Shu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6215-2507","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101467562","display_name":"Xiaolin Wu","orcid":"https://orcid.org/0000-0002-0103-5374","observed_orcids":["https://orcid.org/0000-0002-0103-5374"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolin Wu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0103-5374","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":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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994999766349792,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994999766349792,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.0,"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":0.0,"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-super-resolution","display_name":"image super-resolution","score":0.996999979019165},{"id":"https://openalex.org/keywords/training-data-acquisition","display_name":"training data acquisition","score":0.9449999928474426}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7916510701179504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7641528248786926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464349269866943},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7262001633644104},{"id":"https://openalex.org/C49608258","wikidata":"https://www.wikidata.org/wiki/Q611705","display_name":"Bicubic interpolation","level":4,"score":0.4821705222129822},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4764176607131958},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4663362503051758},{"id":"https://openalex.org/C28751775","wikidata":"https://www.wikidata.org/wiki/Q2112539","display_name":"Homography","level":4,"score":0.4614078104496002},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4513293504714966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2505711019039154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13180825114250183},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C171836373","wikidata":"https://www.wikidata.org/wiki/Q2266329","display_name":"Linear interpolation","level":3,"score":0.0},{"id":"https://openalex.org/C177846678","wikidata":"https://www.wikidata.org/wiki/Q1501864","display_name":"Projective test","level":2,"score":0.0},{"id":"https://openalex.org/C75280867","wikidata":"https://www.wikidata.org/wiki/Q877775","display_name":"Projective space","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3194727438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2108.02348.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:3194727438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2108.02348.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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1677409904","https://openalex.org/W1885185971","https://openalex.org/W1930824406","https://openalex.org/W1976416062","https://openalex.org/W1978749115","https://openalex.org/W2081321639","https://openalex.org/W2121058967","https://openalex.org/W2149760002","https://openalex.org/W2150081556","https://openalex.org/W2151103935","https://openalex.org/W2158453800","https://openalex.org/W2164551808","https://openalex.org/W2167667767","https://openalex.org/W2214802144","https://openalex.org/W2242218935","https://openalex.org/W2331128040","https://openalex.org/W2476548250","https://openalex.org/W2516563544","https://openalex.org/W2534320940","https://openalex.org/W2580080206","https://openalex.org/W2735224642","https://openalex.org/W2739757502","https://openalex.org/W2799046095","https://openalex.org/W2866634454","https://openalex.org/W2883102461","https://openalex.org/W2891158090","https://openalex.org/W2891165135","https://openalex.org/W2891690292","https://openalex.org/W2915130236","https://openalex.org/W2922435819","https://openalex.org/W2943960148","https://openalex.org/W2949695917","https://openalex.org/W2962903125","https://openalex.org/W2963470893","https://openalex.org/W2964101377","https://openalex.org/W2964121744","https://openalex.org/W2987150909","https://openalex.org/W2990565567","https://openalex.org/W3014816689","https://openalex.org/W3035022492"],"related_works":["https://openalex.org/W3192079315","https://openalex.org/W4283687192","https://openalex.org/W3016361553","https://openalex.org/W2516563544","https://openalex.org/W2950086915","https://openalex.org/W3107890037","https://openalex.org/W2793341016","https://openalex.org/W2796427489","https://openalex.org/W4293151225","https://openalex.org/W2987150909"],"abstract_inverted_index":{"For":[0],"deep":[1],"learning":[2],"methods":[3],"of":[4,27,84,119,128,156,171,220],"image":[5,35,59,87,112,132,160,196,206],"super-resolution,":[6],"the":[7,13,24,51,164,178,195,199,203,216,221,251,282],"most":[8],"critical":[9],"issue":[10],"is":[11,95,138],"whether":[12],"paired":[14],"low":[15],"and":[16,31,106,166,187],"high":[17,32,108,117,217],"resolution":[18,33],"images":[19,141,168,280],"for":[20,134,159,238,242,250],"training":[21,131,259,272],"accurately":[22],"reflect":[23],"sampling":[25],"process":[26],"real":[28,69,90,129,278],"cameras.":[29,91],"Low":[30],"(LR$\\sim$HR)":[34],"pairs":[36,60,88,113,133],"synthesized":[37,57],"by":[38,55,263,274],"existing":[39,275],"degradation":[40],"models":[41],"(e.g.":[42],"bicubic":[43],"downsampling)":[44],"deviate":[45],"from":[46],"those":[47],"in":[48],"reality;":[49],"thus":[50],"super-resolution":[52,261],"CNN":[53,262],"trained":[54],"these":[56],"LR$\\sim$HR":[58,86,130,265],"does":[61],"not":[62],"perform":[63],"well":[64],"when":[65],"being":[66],"applied":[67],"to":[68,79,124,139,183,197,214,233],"images.":[70],"In":[71],"this":[72,225],"paper,":[73],"we":[74,188],"propose":[75],"a":[76,81,126,172,184,212,235,247,260],"novel":[77],"method":[78,158,229],"capture":[80],"large":[82],"set":[83,127],"realistic":[85],"using":[89],"The":[92,116],"data":[93,227],"acquisition":[94],"carried":[96],"out":[97],"under":[98],"controllable":[99],"lab":[100],"conditions":[101],"with":[102],"minimum":[103],"human":[104],"intervention":[105],"at":[107,148,281],"throughput":[109],"(about":[110],"500":[111],"per":[114],"hour).":[115],"level":[118],"automation":[120],"makes":[121,230],"it":[122,231,273],"easy":[123],"produce":[125],"each":[135,239],"camera.Our":[136],"innovation":[137],"shoot":[140],"displayed":[142,204],"on":[143,194,277],"an":[144],"ultra-high":[145],"quality":[146],"screen":[147],"different":[149],"resolutions.":[150],"There":[151],"are":[152,169],"three":[153],"distinctive":[154],"advantages":[155],"our":[157,264],"super-resolution.":[161],"First,":[162],"as":[163,211],"LR":[165],"HR":[167],"taken":[170],"3D":[173],"planar":[174],"surface":[175],"(the":[176],"screen)":[177],"registration":[179,200],"problem":[180],"fits":[181],"exactly":[182],"homography":[185],"model":[186,249],"can":[189,208,245],"display":[190],"specially":[191],"designed":[192],"markers":[193],"improve":[198],"precision.":[201],"Second,":[202],"digital":[205],"file":[207],"be":[209],"exploited":[210],"reference":[213],"optimize":[215],"frequency":[218],"content":[219],"restored":[222],"image.":[223],"Third,":[224],"high-efficiency":[226],"collection":[228],"possible":[232],"collect":[234],"customized":[236],"dataset":[237,266],"camera":[240,253],"sensor,":[241],"which":[243],"one":[244],"train":[246],"specific":[248],"intended":[252],"sensor.":[254],"Experimental":[255],"results":[256],"show":[257],"that":[258],"has":[267],"superior":[268],"restoration":[269],"performance":[270],"than":[271],"datasets":[276],"world":[279],"inference":[283],"stage.":[284]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2021-08-30T00:00:00"}