{"id":"https://openalex.org/W7155182277","doi":"https://doi.org/10.48550/arxiv.2604.19680","title":"IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow","display_name":"IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155182277","doi":"https://doi.org/10.48550/arxiv.2604.19680"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19680","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19680","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.19680","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134223073","display_name":"Zihao Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134274875","display_name":"Xin Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134249663","display_name":"Jie Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134351163","display_name":"Dong Li","orcid":"https://orcid.org/0009-0006-1584-1461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101548656","display_name":"Jie Huang","orcid":"https://orcid.org/0009-0006-1871-0598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079007635","display_name":"Xueyang Fu","orcid":"https://orcid.org/0000-0001-8036-4071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Xueyang","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":0.9326000213623047,"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":0.9326000213623047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03319999948143959,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.010499999858438969,"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/discriminative-model","display_name":"Discriminative model","score":0.8471999764442444},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7678999900817871},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.5705999732017517},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5647000074386597},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.546999990940094},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4975000023841858},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3968999981880188}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8471999764442444},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7678999900817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.598800003528595},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.5705999732017517},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317000150680542},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4975000023841858},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2930999994277954},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19680","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19680","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19680","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19680","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7342957854270935,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"image":[1,33,128],"restoration,":[2],"single-step":[3],"discriminative":[4,50],"mappings":[5],"often":[6],"lack":[7],"fine":[8],"details":[9],"via":[10],"expectation":[11],"learning,":[12],"whereas":[13],"generative":[14,52],"paradigms":[15],"suffer":[16],"from":[17,70],"inefficient":[18],"multi-step":[19,101],"sampling":[20,162],"and":[21,51,71,110,126,147,167],"noise-residual":[22],"coupling.":[23],"To":[24],"address":[25],"this":[26],"dilemma,":[27],"we":[28,55],"propose":[29],"IR-Flow,":[30],"a":[31,43,100,120,160],"novel":[32],"restoration":[34,113],"method":[35],"based":[36],"on":[37,144],"Rectified":[38],"Flow":[39],"that":[40,117,152,170],"serves":[41],"as":[42],"unified":[44],"framework":[45,169],"bridging":[46],"the":[47,64,96],"gap":[48],"between":[49,124],"paradigms.":[53],"Specifically,":[54],"first":[56],"construct":[57],"multilevel":[58],"data":[59],"distribution":[60],"flows,":[61],"which":[62],"expand":[63],"ability":[65],"of":[66,76],"models":[67],"to":[68,73,84,106,139],"learn":[69,85],"adapt":[72],"various":[74],"levels":[75],"degradation.":[77],"Subsequently,":[78],"cumulative":[79],"velocity":[80],"fields":[81],"are":[82],"proposed":[83],"transport":[86,122],"trajectories":[87],"across":[88],"varying":[89],"degradation":[90],"levels,":[91],"guiding":[92],"intermediate":[93],"states":[94],"toward":[95],"clean":[97,127],"target,":[98],"while":[99],"consistency":[102],"constraint":[103],"is":[104,178],"presented":[105],"enforce":[107],"trajectory":[108],"coherence":[109],"boost":[111],"few-step":[112],"performance.":[114],"We":[115],"show":[116],"directly":[118],"establishing":[119],"linear":[121],"flow":[123],"degraded":[125],"domains":[129],"not":[130],"only":[131,159],"enables":[132],"fast":[133],"inference":[134],"but":[135],"also":[136],"improves":[137],"adaptability":[138],"out-of-distribution":[140],"degradations.":[141],"Extensive":[142],"evaluations":[143],"deraining,":[145],"denoising":[146],"raindrop":[148],"removal":[149],"tasks":[150],"demonstrate":[151],"IR-Flow":[153],"achieves":[154],"competitive":[155],"quantitative":[156],"results":[157],"with":[158],"few":[161],"steps,":[163],"offering":[164],"an":[165,172],"efficient":[166],"flexible":[168],"maintains":[171],"excellent":[173],"distortion-perception":[174],"balance.":[175],"Our":[176],"code":[177],"available":[179],"at":[180],"https://github.com/fanzh03/IR-Flow.":[181]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-23T00:00:00"}