{"id":"https://openalex.org/W7160130088","doi":"https://doi.org/10.48550/arxiv.2605.00719","title":"Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy","display_name":"Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160130088","doi":"https://doi.org/10.48550/arxiv.2605.00719"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00719","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.00719","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135244190","display_name":"Yinghao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yinghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135228486","display_name":"Yeying Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Yeying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135194362","display_name":"Xiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135113712","display_name":"Yanyan Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Yanyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044495197","display_name":"Ziyang Yan","orcid":"https://orcid.org/0009-0006-7531-4057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Ziyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135275518","display_name":"Yaowen Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yaowen","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":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/T11019","display_name":"Image Enhancement Techniques","score":0.9811000227928162,"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":0.9811000227928162,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6152999997138977},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6029999852180481},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47690001130104065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.36059999465942383}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6873999834060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6468999981880188},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00719","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.00719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00719","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0,70],"deraining":[1,46,109,181,202,206,214],"has":[2],"attracted":[3],"attention":[4],"for":[5,27],"its":[6],"ability":[7],"to":[8,30,56,199],"learn":[9],"the":[10,19,28,34,58,84,119,124,147,155,194],"real-world":[11],"distribution":[12],"of":[13,21,37,149],"rain":[14,38],"without":[15],"paired":[16,170,172],"supervision.":[17],"However,":[18],"lack":[20],"strong":[22,209],"constraints":[23],"makes":[24],"it":[25],"difficult":[26],"network":[29],"converge,":[31],"especially":[32],"with":[33],"complex":[35],"diversity":[36],"degradation.":[39],"A":[40],"key":[41,75],"motivation":[42],"is":[43,197],"that":[44,98,160,193],"high-quality":[45,108],"results":[47],"occasionally":[48],"emerge":[49],"during":[50,103],"training,":[51],"which":[52],"can":[53],"be":[54],"leveraged":[55],"guide":[57],"optimization":[59,121,125],"process.":[60],"To":[61],"overcome":[62],"these":[63,116],"challenges,":[64],"we":[65,87,114,145,191],"introduce":[66],"RGSUD":[67],"(Reward-Guided":[68],"Self-Reinforcement":[69],"Image":[71,90],"Deraining),":[72],"comprising":[73],"two":[74],"stages:":[76],"reward":[77,95],"recycling":[78,96],"and":[79,105,127,133,141,153,174,186,204],"self-reinforcement":[80,195],"(SR)":[81],"training.":[82],"For":[83],"former":[85],"stage,":[86,113],"propose":[88],"an":[89],"Quality":[91],"Assessment":[92],"(IQA)-based":[93],"dynamic":[94],"mechanism":[97],"selects":[99],"optimal":[100],"derained":[101,131],"outputs":[102,132],"training":[104],"continuously":[106],"collects":[107],"images.":[110,135],"In":[111],"latter":[112],"incorporate":[115],"rewards":[117],"into":[118],"model's":[120],"process,":[122],"constraining":[123],"space":[126],"improving":[128],"alignment":[129],"between":[130],"clean":[134],"By":[136],"leveraging":[137],"IQA-based":[138],"self-reinforced":[139],"loss":[140],"dynamically":[142],"updated":[143],"rewards,":[144],"enhance":[146],"quality":[148],"synthesized":[150],"pseudo-paired":[151],"data":[152],"stabilize":[154],"optimization.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"our":[161,205],"method":[162],"achieves":[163],"SOTA":[164],"performance":[165],"across":[166,211],"multiple":[167],"datasets,":[168],"including":[169],"synthetic,":[171],"real,":[173],"unpaired":[175],"real":[176],"images,":[177],"outperforming":[178],"existing":[179,212],"unsupervised":[180,201],"approaches":[182],"in":[183],"both":[184],"subjective":[185],"objective":[187],"IQA":[188],"metrics.":[189],"Additionally,":[190],"show":[192],"strategy":[196],"adaptable":[198],"other":[200],"methods":[203],"framework":[207],"demonstrates":[208],"generalization":[210],"supervised":[213],"networks.":[215]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-05T00:00:00"}