{"id":"https://openalex.org/W7140079247","doi":"https://doi.org/10.48550/arxiv.2603.20186","title":"Improving Image-to-Image Translation via a Rectified Flow Reformulation","display_name":"Improving Image-to-Image Translation via a Rectified Flow Reformulation","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140079247","doi":"https://doi.org/10.48550/arxiv.2603.20186"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20186","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.2603.20186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130388816","display_name":"Satoshi Iizuka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iizuka, Satoshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130377146","display_name":"Shun Okamoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Okamoto, Shun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101567870","display_name":"Kazuhiro Fukui","orcid":"https://orcid.org/0000-0002-4201-1096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fukui, Kazuhiro","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9628999829292297,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9628999829292297,"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":0.009399999864399433,"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":0.007000000216066837,"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/inference","display_name":"Inference","score":0.7226999998092651},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.704800009727478},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5354999899864197},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.49939998984336853},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45399999618530273},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4262000024318695},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.40529999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448999881744385},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7226999998092651},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.704800009727478},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5354999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5178999900817871},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4262000024318695},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3718999922275543},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.27469998598098755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20186","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.2603.20186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20186","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":{"In":[0,110],"this":[1],"work,":[2],"we":[3],"propose":[4],"Image-to-Image":[5],"Rectified":[6],"Flow":[7],"Reformulation":[8],"(I2I-RFR),":[9],"a":[10,70,79,87,127,154,174,187],"practical":[11],"plug-in":[12],"reformulation":[13],"that":[14,148],"recasts":[15],"standard":[16,106],"I2I":[17,26,183],"regression":[18,27],"networks":[19],"as":[20],"continuous-time":[21,179],"transport":[22],"models.":[23],"While":[24],"pixel-wise":[25],"is":[28],"simple,":[29],"stable,":[30],"and":[31,41,53,57,77,121,143,159,168],"easy":[32],"to":[33,177],"adapt":[34],"across":[35,139,153],"tasks,":[36],"it":[37],"often":[38,47],"over-smooths":[39],"ill-posed":[40],"multimodal":[42],"targets,":[43],"whereas":[44],"generative":[45,189],"alternatives":[46],"require":[48],"additional":[49],"components,":[50],"task-specific":[51],"tuning,":[52],"more":[54],"complex":[55],"training":[56,108],"inference":[58,100,122],"pipelines.":[59],"Our":[60],"method":[61],"augments":[62],"the":[63,74,105,118],"backbone":[64],"input":[65,119],"by":[66],"channel-wise":[67],"concatenation":[68],"with":[69,126,161],"noise-corrupted":[71],"version":[72],"of":[73,157],"ground-truth":[75],"target":[76],"optimizes":[78],"simple":[80],"t-reweighted":[81],"pixel":[82],"loss.":[83],"This":[84],"objective":[85],"admits":[86],"rectified-flow":[88],"interpretation":[89],"via":[90],"an":[91],"induced":[92],"velocity":[93],"field,":[94],"enabling":[95],"ODE-based":[96],"progressive":[97],"refinement":[98,180],"at":[99],"time":[101],"while":[102],"largely":[103],"preserving":[104],"supervised":[107],"pipeline.":[109,190],"most":[111],"cases,":[112],"adopting":[113],"I2I-RFR":[114,149,172],"requires":[115],"only":[116],"expanding":[117],"channels,":[120],"can":[123],"be":[124],"performed":[125],"few":[128],"explicit":[129],"solver":[130],"steps":[131],"(e.g.,":[132],"3":[133],"steps)":[134],"without":[135,185],"distillation.":[136],"Extensive":[137],"experiments":[138],"multiple":[140],"image-to-image":[141],"translation":[142],"video":[144],"restoration":[145],"tasks":[146,158],"show":[147],"generally":[150],"improves":[151],"performance":[152],"wide":[155],"range":[156],"backbones,":[160],"particularly":[162],"clear":[163],"gains":[164],"in":[165],"perceptual":[166],"quality":[167],"detail":[169],"preservation.":[170],"Overall,":[171],"provides":[173],"lightweight":[175],"way":[176],"incorporate":[178],"into":[181],"conventional":[182],"models":[184],"requiring":[186],"heavy":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-24T00:00:00"}