{"id":"https://openalex.org/W4414798830","doi":"https://doi.org/10.1109/access.2025.3617488","title":"Boosting the Performance of Image Restoration Models Through Training With Deep-Feature Auxiliary Guidance","display_name":"Boosting the Performance of Image Restoration Models Through Training With Deep-Feature Auxiliary Guidance","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414798830","doi":"https://doi.org/10.1109/access.2025.3617488"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3617488","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3617488","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3617488","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033581723","display_name":"Cheolhun Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Cheolhun Jang","raw_affiliation_strings":["Interdisciplinary Program in Artificial Intelligence, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Interdisciplinary Program in Artificial Intelligence, INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110223580","display_name":"Daehyun Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehyun Ji","raw_affiliation_strings":["AI Center, Samsung Electronics, Suwon-si, Gyeonggi-do, South Korea","AI Center, Samsung Electronics, Suwon-si, Gyueonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"AI Center, Samsung Electronics, Suwon-si, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"AI Center, Samsung Electronics, Suwon-si, Gyueonggi-do, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055171648","display_name":"Nam Ik Cho","orcid":"https://orcid.org/0000-0001-5297-4649"},"institutions":[{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]},{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Ik Cho","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033581723"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28728458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"173398","last_page":"173414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9739000201225281,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9739000201225281,"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/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.930899977684021,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9090999960899353,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.7781000137329102},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7396000027656555},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.552299976348877},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4496000111103058},{"id":"https://openalex.org/keywords/jpeg","display_name":"JPEG","score":0.41589999198913574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41130000352859497},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.39070001244544983},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37560001015663147},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.7781000137329102},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7396000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6521000266075134},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.41589999198913574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2540999948978424},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3617488","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3617488","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:053e8f568a0645ac9c29c47169592c9c","is_oa":true,"landing_page_url":"https://doaj.org/article/053e8f568a0645ac9c29c47169592c9c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 173398-173414 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3617488","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3617488","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1791560514","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1912194039","https://openalex.org/W1930824406","https://openalex.org/W1990592195","https://openalex.org/W2047920195","https://openalex.org/W2069143585","https://openalex.org/W2081418206","https://openalex.org/W2097117768","https://openalex.org/W2121927366","https://openalex.org/W2135065661","https://openalex.org/W2150060382","https://openalex.org/W2150081556","https://openalex.org/W2167191464","https://openalex.org/W2183341477","https://openalex.org/W2192954843","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2508457857","https://openalex.org/W2560023338","https://openalex.org/W2560533888","https://openalex.org/W2799192307","https://openalex.org/W2884068670","https://openalex.org/W2912435603","https://openalex.org/W2962785568","https://openalex.org/W2963372104","https://openalex.org/W2963470893","https://openalex.org/W2965217508","https://openalex.org/W2981899103","https://openalex.org/W2982795046","https://openalex.org/W2985577924","https://openalex.org/W2988641380","https://openalex.org/W3000775737","https://openalex.org/W3035022492","https://openalex.org/W3035326127","https://openalex.org/W3047011367","https://openalex.org/W3083579885","https://openalex.org/W3099686304","https://openalex.org/W3101313813","https://openalex.org/W3106758205","https://openalex.org/W3109494165","https://openalex.org/W3138808092","https://openalex.org/W3155072588","https://openalex.org/W3167568784","https://openalex.org/W3169770376","https://openalex.org/W3170697543","https://openalex.org/W3171125843","https://openalex.org/W3194523157","https://openalex.org/W3202040256","https://openalex.org/W3206479921","https://openalex.org/W3207918547","https://openalex.org/W4214577770","https://openalex.org/W4225672218","https://openalex.org/W4312349930","https://openalex.org/W4312414053","https://openalex.org/W4312678820","https://openalex.org/W4312766126","https://openalex.org/W4312812783","https://openalex.org/W4312938066","https://openalex.org/W4386075704","https://openalex.org/W4386075858","https://openalex.org/W4386076032","https://openalex.org/W4386076603","https://openalex.org/W4386114505","https://openalex.org/W4386952070","https://openalex.org/W4398138244","https://openalex.org/W4399562320","https://openalex.org/W4402186930","https://openalex.org/W4402660092","https://openalex.org/W4402754016","https://openalex.org/W4402776053","https://openalex.org/W4405139396","https://openalex.org/W4409183537","https://openalex.org/W4409326045","https://openalex.org/W4409883308","https://openalex.org/W4411019521"],"related_works":[],"abstract_inverted_index":{"Many":[0],"neural":[1],"network":[2],"architectures":[3],"have":[4,26],"been":[5],"proposed":[6],"for":[7,96,106],"image":[8,59,120,134],"restoration":[9,60,121,156],"to":[10,74,154],"improve":[11],"the":[12,56,75],"accuracy":[13,57],"of":[14,58],"restored":[15],"images":[16],"while":[17],"maintaining":[18],"reasonable":[19],"computational":[20,112],"costs.":[21],"However,":[22],"most":[23],"previous":[24],"studies":[25],"primarily":[27],"focused":[28],"on":[29,37,116],"designing":[30],"new":[31],"architectures,":[32],"with":[33],"relatively":[34],"less":[35],"attention":[36],"optimizing":[38],"training":[39,52,102],"strategies.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"introduce":[45],"deep-feature":[46],"auxiliary":[47,72],"guidance":[48],"(DFAG),":[49],"a":[50],"novel":[51],"method":[53],"that":[54,148],"enhances":[55],"models":[61,167],"without":[62,158],"increasing":[63],"inference":[64],"time":[65],"or":[66],"modifying":[67],"their":[68],"structures.":[69],"DFAG":[70,97,115,149],"adds":[71],"losses":[73],"feature":[76,87,91],"maps":[77],"at":[78],"each":[79],"multi-scale":[80,118],"level":[81],"during":[82,101],"training,":[83],"which":[84],"stabilizes":[85],"deep":[86],"learning":[88],"and":[89,103,143,165],"improves":[90],"quality.":[92],"All":[93],"modules":[94],"used":[95],"are":[98,104],"only":[99],"active":[100],"removed":[105],"inference,":[107],"resulting":[108],"in":[109],"no":[110],"additional":[111],"cost.We":[113],"validate":[114],"various":[117],"encoder-decoder-based":[119],"models.":[122],"Our":[123,145],"experiments":[124],"demonstrate":[125],"consistent":[126],"performance":[127,157],"improvements":[128],"across":[129],"multiple":[130],"tasks,":[131],"including":[132],"real":[133],"denoising,":[135,137],"Gaussian":[136],"motion":[138],"deblurring,":[139],"JPEG":[140],"artifact":[141],"reduction,":[142],"super-resolution.":[144],"results":[146],"highlight":[147],"is":[150],"an":[151],"effective":[152],"strategy":[153],"boost":[155],"any":[159],"architectural":[160],"modifications.":[161],"The":[162],"source":[163],"code":[164],"pre-trained":[166],"will":[168],"be":[169],"released.":[170]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}