{"id":"https://openalex.org/W4414739908","doi":"https://doi.org/10.1109/iccv51701.2025.01889","title":"Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching","display_name":"Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414739908","doi":"https://doi.org/10.1109/iccv51701.2025.01889"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.10318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041481220","display_name":"Yuhan Liu","orcid":"https://orcid.org/0000-0003-4328-6427"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Yuhan Liu","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060230441","display_name":"Jingwen Fu","orcid":"https://orcid.org/0000-0003-3256-1497"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jingwen Fu","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076165512","display_name":"Yang Wu","orcid":"https://orcid.org/0000-0003-0699-8134"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Yang Wu","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028226091","display_name":"Kuijun Wu","orcid":"https://orcid.org/0009-0004-0556-8241"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Kangyi Wu","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435506","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-3314-943X"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pengna Li","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026243783","display_name":"Jiang Wu","orcid":"https://orcid.org/0000-0002-6548-9551"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jiayi Wu","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113827261","display_name":"Sanping Zhou","orcid":"https://orcid.org/0000-0003-4100-2304"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Sanping Zhou","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031227866","display_name":"Jingmin Xin","orcid":"https://orcid.org/0000-0003-1906-2327"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jingmin Xin","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence","institution_ids":["https://openalex.org/I4210105595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210105595"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22173592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20313","last_page":"20323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9854000210762024,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9854000210762024,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9613999724388123,"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/feature","display_name":"Feature (linguistics)","score":0.6934000253677368},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6710000038146973},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.5961999893188477},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5356000065803528},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4043000042438507},{"id":"https://openalex.org/keywords/feature-model","display_name":"Feature model","score":0.38679999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070000171661377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6934000253677368},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219000220298767},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.5961999893188477},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.38679999113082886},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.10318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10318","pdf_url":"https://arxiv.org/pdf/2507.10318","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.10318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10318","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.10318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10318","pdf_url":"https://arxiv.org/pdf/2507.10318","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1999039755","display_name":null,"funder_award_id":"2023ZD0121300","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Leveraging":[0],"the":[1,13,24,28,38,41,49,58,69,83,94,130,144,156,185,211,222],"vision":[2],"foundation":[3,29,42,64,136],"models":[4,30,43,65,137,147],"has":[5],"emerged":[6],"as":[7,162],"a":[8,110,121,163,167,189,203],"mainstream":[9],"paradigm":[10],"that":[11,138],"improves":[12],"performance":[14],"of":[15,53,93],"image":[16,179],"feature":[17,32,54,74,102,118],"matching.":[18,33,55],"However,":[19],"previous":[20],"works":[21],"have":[22],"ignored":[23],"misalignment":[25,35,95],"when":[26,99],"introducing":[27],"into":[31,87],"The":[34],"arises":[36],"from":[37,61],"discrepancy":[39],"between":[40,178],"focusing":[44],"on":[45,196],"single-image":[46,84],"understanding":[47,51,85],"and":[48,210],"cross-image":[50,88,169],"requirement":[52],"Specifically,":[56],"1)":[57,128],"embeddings":[59,71],"derived":[60],"commonly":[62,207],"used":[63],"exhibit":[66],"discrepancies":[67],"with":[68,120,125],"optimal":[70],"required":[72],"for":[73],"matching;":[75],"2)":[76,153],"lacking":[77],"an":[78],"effective":[79,113],"mechanism":[80,158],"to":[81,148,173],"leverage":[82,155],"ability":[86],"understanding.":[89],"A":[90],"significant":[91],"consequence":[92],"is":[96],"they":[97],"struggle":[98],"addressing":[100],"multi-instance":[101,197],"matching":[103],"problems.":[104],"To":[105,181],"address":[106],"this,":[107],"we":[108,142,187],"introduce":[109],"simple":[111],"but":[112],"framework,":[114],"called":[115,192],"IMD":[116,201],"(Image":[117],"Matching":[119],"pre-trained":[122],"Diffusion":[123],"model)":[124],"two":[126],"parts:":[127],"Unlike":[129],"dominant":[131],"solutions":[132],"employing":[133],"contrastive-learning":[134],"based":[135],"emphasize":[139],"global":[140],"semantics,":[141],"integrate":[143],"generative-based":[145],"diffusion":[146],"effectively":[149],"capture":[150],"instance-level":[151],"details.":[152],"We":[154],"prompt":[157],"in":[159,206,215],"generative":[160],"model":[161],"natural":[164],"tunnel,":[165],"propose":[166,188],"novel":[168],"interaction":[170,177],"prompting":[171],"module":[172],"facilitate":[174],"bidirectional":[175],"information":[176],"pairs.":[180],"more":[182],"accurately":[183],"measure":[184],"misalignment,":[186],"new":[190,204],"benchmark":[191],"IMIM,":[193],"which":[194],"focuses":[195],"scenarios.":[198],"Our":[199],"proposed":[200],"establishes":[202],"state-of-the-art":[205],"evaluated":[208],"benchmarks,":[209],"superior":[212],"improvement":[213],"12%":[214],"IMIM":[216],"indicates":[217],"our":[218],"method":[219],"efficiently":[220],"mitigates":[221],"misalignment.":[223]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}