{"id":"https://openalex.org/W7155212732","doi":"https://doi.org/10.48550/arxiv.2604.19736","title":"Generative Drifting for Conditional Medical Image Generation","display_name":"Generative Drifting for Conditional Medical Image Generation","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155212732","doi":"https://doi.org/10.48550/arxiv.2604.19736"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19736","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.2604.19736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134235215","display_name":"Zirong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zirong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103267120","display_name":"Siyuan Mei","orcid":"https://orcid.org/0009-0002-1136-2501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Siyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077824092","display_name":"Weiwen Wu","orcid":"https://orcid.org/0000-0002-8295-5104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Weiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134253152","display_name":"Andreas Maier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maier, Andreas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012858030","display_name":"Lina G\u00f6lz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00f6lz, Lina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134351324","display_name":"Yan Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Yan","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":0.8460999727249146,"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":0.8460999727249146,"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":0.0421999990940094,"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/T11019","display_name":"Image Enhancement Techniques","score":0.020899999886751175,"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":0.5939000248908997},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.45179998874664307},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44119998812675476},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.43880000710487366},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4343999922275543},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43290001153945923},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4291999936103821},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41659998893737793},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41620001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819000244140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129999756813049},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5939000248908997},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4343999922275543},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.40290001034736633},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19736","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.2604.19736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19736","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conditional":[0],"medical":[1,35,50,75,110,217],"image":[2,51,218],"generation":[3],"plays":[4],"an":[5,78],"important":[6],"role":[7],"in":[8,22,32,98,135],"many":[9],"clinically":[10],"relevant":[11],"imaging":[12,76],"tasks.":[13],"However,":[14],"existing":[15],"methods":[16],"still":[17],"face":[18],"a":[19,43,54,104,109,131,171,209],"fundamental":[20],"challenge":[21],"balancing":[23],"inference":[24,201],"efficiency,":[25],"patient-specific":[26,64],"fidelity,":[27,195],"and":[28,63,89,118,126,146,160,179,200,211],"distribution-level":[29,61,145],"plausibility,":[30],"particularly":[31],"high-dimensional":[33],"3D":[34,74,99,216],"imaging.":[36],"In":[37,129],"this":[38],"work,":[39],"we":[40],"propose":[41],"GDM,":[42],"generative":[44,181],"drifting":[45,72,119],"framework":[46,153,213],"that":[47,81,167,206],"reformulates":[48],"deterministic":[49],"prediction":[52],"as":[53,183,185],"multi-objective":[55],"learning":[56,97],"problem":[57],"to":[58,73,113],"jointly":[59],"promote":[60],"plausibility":[62],"fidelity":[65],"while":[66,189],"retaining":[67],"one-step":[68],"inference.":[69],"GDM":[70,102,168,207],"extends":[71],"through":[77],"attractive-repulsive":[79],"drift":[80],"minimizes":[82],"the":[83,86,90,136,151,191],"discrepancy":[84],"between":[85],"generator":[87],"pushforward":[88],"target":[91],"distribution.":[92],"To":[93],"enable":[94],"stable":[95],"drifting-based":[96],"volumetric":[100],"data,":[101],"constructs":[103],"multi-level":[105],"feature":[106],"bank":[107],"from":[108],"foundation":[111],"encoder":[112],"support":[114],"reliable":[115],"affinity":[116],"estimation":[117],"field":[120],"computation":[121],"across":[122],"complementary":[123],"global,":[124],"local,":[125],"spatial":[127],"representations.":[128],"addition,":[130],"gradient":[132],"coordination":[133],"strategy":[134],"shared":[137],"output":[138],"space":[139],"improves":[140],"optimization":[141],"balance":[142,192],"under":[143],"competing":[144],"fidelity-oriented":[147],"objectives.":[148],"We":[149],"evaluate":[150],"proposed":[152],"on":[154],"two":[155],"representative":[156],"tasks,":[157],"MRI-to-CT":[158],"synthesis":[159],"sparse-view":[161],"CT":[162],"reconstruction.":[163],"Experimental":[164],"results":[165],"show":[166],"consistently":[169],"outperforms":[170],"wide":[172],"range":[173],"of":[174],"baselines,":[175],"including":[176],"GAN-based,":[177],"flow-matching-based,":[178],"SDE-based":[180],"models,":[182],"well":[184],"supervised":[186],"regression":[187],"methods,":[188],"improving":[190],"among":[193],"anatomical":[194],"quantitative":[196],"reliability,":[197],"perceptual":[198],"realism,":[199],"efficiency.":[202],"These":[203],"findings":[204],"suggest":[205],"provides":[208],"practical":[210],"effective":[212],"for":[214],"conditional":[215],"generation.":[219]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-23T00:00:00"}