{"id":"https://openalex.org/W4408352743","doi":"https://doi.org/10.1109/icassp49660.2025.10887818","title":"SVTNet: Dual Branch of Swin Transformer and Vision Transformer for Monocular Depth Estimation","display_name":"SVTNet: Dual Branch of Swin Transformer and Vision Transformer for Monocular Depth Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352743","doi":"https://doi.org/10.1109/icassp49660.2025.10887818"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5110994661","display_name":"Shuwen Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwen Jia","raw_affiliation_strings":["University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021144916","display_name":"Yongxiong Wang","orcid":"https://orcid.org/0000-0002-7390-3089"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiong Wang","raw_affiliation_strings":["University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325142","display_name":"Han Chen","orcid":"https://orcid.org/0009-0003-6045-3204"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Chen","raw_affiliation_strings":["University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101542272","display_name":"Shuai Huang","orcid":"https://orcid.org/0000-0002-4344-5064"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Huang","raw_affiliation_strings":["University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China","institution_ids":["https://openalex.org/I148128674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148128674"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.991599977016449,"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/transformer","display_name":"Transformer","score":0.5814019441604614},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5710234045982361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.555097758769989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485528111457825},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5205070376396179},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2113298773765564},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16095668077468872},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09628760814666748}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5814019441604614},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5710234045982361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555097758769989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485528111457825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5205070376396179},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2113298773765564},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16095668077468872},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09628760814666748}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2115579991","https://openalex.org/W2605938684","https://openalex.org/W2961343177","https://openalex.org/W2963488291","https://openalex.org/W3138516171","https://openalex.org/W3173727695","https://openalex.org/W3176063055","https://openalex.org/W3203073814","https://openalex.org/W4214520160","https://openalex.org/W4312819733","https://openalex.org/W4313156423","https://openalex.org/W4319300976","https://openalex.org/W4386083069","https://openalex.org/W4386280799","https://openalex.org/W4386723894","https://openalex.org/W4399938885","https://openalex.org/W4405785381","https://openalex.org/W6784094891","https://openalex.org/W6785345353"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,47,80],"monocular":[1],"depth":[2],"estimation,":[3],"effective":[4],"acquisition":[5],"of":[6,69,77,104],"global":[7,43,109],"and":[8,34,44,64,90,106,119],"local":[9,45],"information":[10],"is":[11],"the":[12,31,53,59,66,70,86,92,102,115,129],"key":[13],"to":[14,39],"improving":[15],"accuracy.":[16],"We":[17],"introduce":[18],"a":[19],"novel":[20],"dual":[21],"branch":[22],"network":[23],"called":[24],"Swin":[25,32,48,78],"Vision":[26,35,81,98],"Transformer":[27,33,36,49,82,99],"Net":[28],"(SVTNet),":[29],"where":[30],"are":[37],"combined":[38],"learn":[40],"features":[41,72],"with":[42,125],"information.":[46],"branch,":[50],"we":[51,84],"remove":[52,85],"Feature":[54],"Pyramid":[55],"Networks":[56],"which":[57],"reduces":[58],"noise":[60],"introduced":[61],"by":[62,97],"interpolation":[63],"maintains":[65],"original":[67],"characteristics":[68],"hierarchical":[71],"extracted":[73,96],"from":[74],"each":[75],"layer":[76],"Transformer.":[79],"Branch,":[83],"multi-scale":[87],"convolutional":[88],"structure":[89],"keep":[91],"same-scale":[93],"feature":[94],"maps":[95],"for":[100],"reducing":[101],"consumption":[103],"memory":[105],"extracting":[107],"more":[108],"features.":[110],"The":[111],"experimental":[112],"results":[113],"on":[114],"NYU-Depth":[116],"v2,":[117],"KITTI,":[118],"CityScapes":[120],"datasets":[121],"show":[122],"that":[123],"compared":[124],"existing":[126],"advanced":[127],"methods,":[128],"SVTNet":[130],"has":[131],"achieved":[132],"significant":[133],"performance":[134],"improvements":[135],"in":[136],"multiple":[137],"evaluation":[138],"metrics.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}