{"id":"https://openalex.org/W7155769740","doi":"https://doi.org/10.1109/tip.2026.3684415","title":"SMFormer: Empowering Self-Supervised Stereo Matching via Foundation Models and Data Augmentation","display_name":"SMFormer: Empowering Self-Supervised Stereo Matching via Foundation Models and Data Augmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7155769740","doi":"https://doi.org/10.1109/tip.2026.3684415","pmid":"https://pubmed.ncbi.nlm.nih.gov/42043993"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3684415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3684415","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8384-6981","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073562495","display_name":"Zhengjie Yang","orcid":"https://orcid.org/0000-0002-7530-3562"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210159567","display_name":"M-Gen Mobile Technology (China)","ror":"https://ror.org/051h3ee29","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159567"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhengjie Yang","raw_affiliation_strings":["Hong Kong Generative AI Research and Development Center, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7530-3562","affiliations":[{"raw_affiliation_string":"Hong Kong Generative AI Research and Development Center, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I4210159567","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103108979","display_name":"Jiahao Zheng","orcid":"https://orcid.org/0000-0001-5169-3183"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahao Zheng","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-5169-3183","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061370730","display_name":"Zhanjie Zhang","orcid":"https://orcid.org/0000-0002-8966-1328"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanjie Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8966-1328","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023935378","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-5622-7488"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dapeng Oliver Wu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1755-0183","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121564527","display_name":"Y Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulan Guo","raw_affiliation_strings":["School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0952-476X","affiliations":[{"raw_affiliation_string":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58660555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4494","last_page":"4508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.39570000767707825,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.39570000767707825,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.061900001019239426,"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/T10860","display_name":"Speech and Audio Processing","score":0.04879999905824661,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/matching","display_name":"Matching (statistics)","score":0.44359999895095825},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.3919999897480011},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.36570000648498535},{"id":"https://openalex.org/keywords/image-matching","display_name":"Image matching","score":0.32510000467300415},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.30869999527931213},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.30390000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770000219345093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5580000281333923},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36570000648498535},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26930001378059387}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3684415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3684415","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42043993","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42043993","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.4191715121269226,"id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G7689657786","display_name":"Key Technologies and Applications of Air-to-ground Mobile Crowdsensing for Smart Transportation","funder_award_id":"MHP/061/23","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"self-supervised":[1,159],"stereo":[2],"matching":[3],"methods":[4,160],"have":[5],"made":[6],"significant":[7,43],"progress.":[8],"They":[9],"typically":[10],"rely":[11],"on":[12,146,164],"the":[13,24,65,76,79,129,171],"photometric":[14],"consistency":[15,116,131],"assumption,":[16],"which":[17],"presumes":[18],"corresponding":[19],"points":[20],"across":[21],"views":[22],"share":[23],"same":[25],"appearance.":[26],"However,":[27],"this":[28,52],"assumption":[29],"could":[30],"be":[31],"compromised":[32],"by":[33,64,123],"real-world":[34],"disturbances,":[35],"resulting":[36],"in":[37,93,170],"invalid":[38],"supervisory":[39],"signals":[40],"and":[41,70,87,120,139,161],"a":[42,57,85],"accuracy":[44],"gap":[45],"compared":[46],"to":[47,107],"supervised":[48,167,180],"methods.":[49],"To":[50],"address":[51],"issue,":[53],"we":[54],"propose":[55],"SMFormer,":[56],"framework":[58],"integrating":[59],"more":[60],"reliable":[61],"self-supervision":[62],"guided":[63],"Vision":[66],"Foundation":[67],"Model":[68],"(VFM)":[69],"data":[71,101,111],"augmentation.":[72],"We":[73,96],"first":[74],"incorporate":[75],"VFM":[77],"with":[78,166],"Feature":[80],"Pyramid":[81],"Network":[82],"(FPN),":[83],"providing":[84],"discriminative":[86],"robust":[88],"feature":[89],"representation":[90],"against":[91],"disturbance":[92],"various":[94,108],"scenarios.":[95],"then":[97],"devise":[98],"an":[99],"effective":[100],"augmentation":[102,112],"mechanism":[103,113],"that":[104,151],"ensures":[105],"robustness":[106],"transformations.":[109],"The":[110],"explicitly":[114],"enforces":[115],"between":[117,132],"learned":[118],"features":[119],"those":[121,140],"influenced":[122],"illumination":[124],"variations.":[125],"Additionally,":[126],"it":[127],"regularizes":[128],"output":[130],"disparity":[133],"predictions":[134],"of":[135],"strong":[136],"augmented":[137],"samples":[138],"generated":[141],"from":[142],"standard":[143],"samples.":[144],"Experiments":[145],"multiple":[147],"mainstream":[148],"benchmarks":[149],"demonstrate":[150],"our":[152],"SMFormer":[153,175],"achieves":[154],"state-of-the-art":[155],"(SOTA)":[156],"performance":[157],"among":[158],"even":[162,176],"competes":[163],"par":[165],"ones.":[168],"Remarkably,":[169],"challenging":[172],"Booster":[173],"benchmark,":[174],"outperforms":[177],"some":[178],"SOTA":[179],"methods,":[181],"such":[182],"as":[183],"CFNet.":[184]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-04-28T00:00:00"}