{"id":"https://openalex.org/W4399658917","doi":"https://doi.org/10.1145/3641584.3641635","title":"A deep bilateral learning based GAN for non-homogeneous dehazing","display_name":"A deep bilateral learning based GAN for non-homogeneous dehazing","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4399658917","doi":"https://doi.org/10.1145/3641584.3641635"},"language":"en","primary_location":{"id":"doi:10.1145/3641584.3641635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031643983","display_name":"Peizhe Li","orcid":"https://orcid.org/0009-0009-3642-0270"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peizhe Li","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0009-3642-0270","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757104","display_name":"Weiwei Kong","orcid":"https://orcid.org/0000-0002-5013-3739"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Kong","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-5013-3739","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101672366","display_name":"Jiamei Dai","orcid":"https://orcid.org/0009-0005-4211-0181"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamei Dai","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0005-4211-0181","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031643983"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22278197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":1.0,"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9872000217437744,"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/homogeneous","display_name":"Homogeneous","score":0.7735736966133118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5824725031852722},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5470356941223145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46031448245048523},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4126471281051636},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.34547263383865356},{"id":"https://openalex.org/keywords/optoelectronics","display_name":"Optoelectronics","score":0.32669001817703247},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08464139699935913},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.05248540639877319}],"concepts":[{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.7735736966133118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824725031852722},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5470356941223145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46031448245048523},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4126471281051636},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.34547263383865356},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.32669001817703247},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08464139699935913},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.05248540639877319},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641584.3641635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2128254161","https://openalex.org/W2526468814","https://openalex.org/W2735974062","https://openalex.org/W2799539975","https://openalex.org/W2900461037","https://openalex.org/W2928165649","https://openalex.org/W2998249728","https://openalex.org/W3021381664","https://openalex.org/W3034659433","https://openalex.org/W3125028070","https://openalex.org/W3128913384","https://openalex.org/W3130421032","https://openalex.org/W4221162268","https://openalex.org/W4229017565","https://openalex.org/W4287780400","https://openalex.org/W4291128317","https://openalex.org/W4297792614","https://openalex.org/W6684667240","https://openalex.org/W6779573556","https://openalex.org/W6793999024"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"Affected":[0],"by":[1,61,115,175],"haze,":[2],"images":[3,46,81],"often":[4,25,50],"face":[5],"color":[6,164],"distortion,":[7],"resolution":[8],"reduction":[9],"and":[10,86,133,156,166],"other":[11],"image":[12],"quality":[13],"degradation":[14],"problems.":[15],"The":[16],"existing":[17],"dehazing":[18,104],"methods":[19],"based":[20,106],"on":[21,28,107],"convolutional":[22],"neural":[23],"network(CNN)":[24],"perform":[26],"well":[27],"large-scale":[29],"synthetic":[30],"datasets,":[31],"but":[32],"lack":[33],"robustness":[34],"in":[35,47,120],"the":[36,54,57,62,74,78,87,118,121,127,131,137,148,151,154,163,172,182],"processing":[37,65],"of":[38,130,150,184],"real":[39,63],"haze":[40,45,58,64],"images.":[41],"This":[42],"is":[43,66,70,91,144],"because":[44],"reality":[48],"are":[49,82],"non-homogeneous.":[51],"Due":[52],"to":[53,72,84,93,95,125,146,160],"fact":[55],"that":[56],"texture":[59,75],"faced":[60],"more":[67],"complex,":[68],"it":[69],"easier":[71],"destroy":[73],"details.":[76],"Meanwhile,":[77],"paired":[79],"training":[80],"difficult":[83],"collect,":[85],"small-scale":[88],"data":[89,138],"set":[90],"easy":[92],"lead":[94],"overfitting.":[96,135],"To":[97],"address":[98],"these":[99],"challenges,":[100],"we":[101,180],"propose":[102],"a":[103,176],"approach":[105,186],"ensemble":[108],"learning,":[109],"DB-GAN,":[110],"which":[111],"uses":[112],"Res2Net":[113],"pre-trained":[114],"ImageNet":[116],"as":[117],"encoder":[119],"knowledge":[122],"adaptation":[123],"branch":[124],"improve":[126],"generalization":[128],"ability":[129],"network":[132],"avoid":[134],"In":[136],"fitting":[139],"branch,":[140],"deep":[141],"bilateral":[142],"learning":[143],"used":[145],"learn":[147,162],"structure":[149],"features":[152,165,174],"from":[153],"full-resolution":[155],"low-resolution":[157],"inputs,":[158],"respectively,":[159],"better":[161],"boundary":[167],"features.":[168],"We":[169],"then":[170],"map":[171],"different":[173],"fusion":[177],"tail.":[178],"Finally,":[179],"demonstrate":[181],"effectiveness":[183],"our":[185],"through":[187],"extensive":[188],"experimental":[189],"results.":[190]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}