{"id":"https://openalex.org/W4392910306","doi":"https://doi.org/10.1109/icassp48485.2024.10447105","title":"Chat: Cascade Hole-Aware Transformers with Geometric Spatial Consistency for Accurate Monocular Endoscopic Depth Estimation","display_name":"Chat: Cascade Hole-Aware Transformers with Geometric Spatial Consistency for Accurate Monocular Endoscopic Depth Estimation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910306","doi":"https://doi.org/10.1109/icassp48485.2024.10447105"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100669887","display_name":"Ming Wu","orcid":"https://orcid.org/0000-0002-3582-4881"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Wu","raw_affiliation_strings":["Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037660521","display_name":"Qi Hao","orcid":"https://orcid.org/0000-0002-2792-5965"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Qi","raw_affiliation_strings":["Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044224149","display_name":"Wenkang Fan","orcid":"https://orcid.org/0000-0002-8364-5159"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenkang Fan","raw_affiliation_strings":["Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049162666","display_name":"Sunkui Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124907","display_name":"Zhongshan Hospital of Xiamen University","ror":"https://ror.org/02z125451","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210124907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sunkui Ke","raw_affiliation_strings":["Xiamen University,Zhongshan Hospital,Xiamen,China,361004"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Zhongshan Hospital,Xiamen,China,361004","institution_ids":["https://openalex.org/I4210124907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102426266","display_name":"Huiqing Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124907","display_name":"Zhongshan Hospital of Xiamen University","ror":"https://ror.org/02z125451","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210124907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Qing Zeng","raw_affiliation_strings":["Xiamen University,Zhongshan Hospital,Xiamen,China,361004"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Zhongshan Hospital,Xiamen,China,361004","institution_ids":["https://openalex.org/I4210124907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082244615","display_name":"Yinran Chen","orcid":"https://orcid.org/0000-0001-8062-1859"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinran Chen","raw_affiliation_strings":["Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100426928","display_name":"Xiongbiao Luo","orcid":"https://orcid.org/0000-0001-7906-8857"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongbiao Luo","raw_affiliation_strings":["Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005","National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Computer Science and Technology,Xiamen,China,361005","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100669887"],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":0.3693,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58733238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1616","last_page":"1620"},"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":0.8382999897003174,"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":0.8382999897003174,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.8109999895095825,"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/T11666","display_name":"Color Science and Applications","score":0.7753999829292297,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.7307577133178711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6300249099731445},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5768511295318604},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5641432404518127},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49161988496780396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44993284344673157},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42341333627700806},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34401699900627136},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11848518252372742},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10523217916488647}],"concepts":[{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.7307577133178711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6300249099731445},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5768511295318604},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5641432404518127},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49161988496780396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44993284344673157},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42341333627700806},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34401699900627136},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11848518252372742},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10523217916488647},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2609883120","https://openalex.org/W2909309777","https://openalex.org/W2962793481","https://openalex.org/W2989184872","https://openalex.org/W2991639827","https://openalex.org/W3131500599","https://openalex.org/W3152803807","https://openalex.org/W3183672881","https://openalex.org/W3213199079","https://openalex.org/W4200072305","https://openalex.org/W4214520160","https://openalex.org/W4327989205","https://openalex.org/W4376481259","https://openalex.org/W4383109003","https://openalex.org/W4386065386","https://openalex.org/W4386076206","https://openalex.org/W4386083069","https://openalex.org/W6685261749"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W1566155057","https://openalex.org/W2060986072","https://openalex.org/W2052574922","https://openalex.org/W64588465","https://openalex.org/W3120641340","https://openalex.org/W2117825986","https://openalex.org/W3134067061","https://openalex.org/W2079855347"],"abstract_inverted_index":{"Monocular":[0],"endoscopic":[1,36,57,128,144],"depth":[2,58],"estimation":[3,12,59],"is":[4,155],"essential":[5],"for":[6,55],"surgical":[7],"navigation.":[8],"Current":[9],"deeply":[10],"learned":[11],"methods":[13],"still":[14],"suffer":[15],"from":[16],"lack":[17],"of":[18,47,77,97,160],"real":[19,123,143,161],"data":[20,130],"labels":[21],"and":[22,32,79,115,122,136,142,175],"porous,":[23],"artifacts":[24],"(e.g.,":[25,29],"bubbles),":[26],"illumination":[27],"variations":[28],"specular":[30,98],"highlight),":[31],"weak":[33,100],"texture":[34],"in":[35],"video":[37,145],"images.":[38,124],"This":[39],"paper":[40],"proposes":[41],"a":[42,105],"new":[43],"deep":[44,78,183],"learning":[45,184],"framework":[46,67],"cascade":[48,69],"hole-aware":[49,70],"transformers":[50],"with":[51,147],"geometric":[52,106,113],"spatial":[53,107],"consistency":[54,108],"accurate":[56],"without":[60],"using":[61],"any":[62],"image":[63,129],"annotation.":[64],"Specifically,":[65],"this":[66],"employs":[68],"encoders":[71],"to":[72,89,131,157],"powerfully":[73],"extract":[74],"structural":[75],"features":[76],"shallow":[80],"holes,":[81],"while":[82],"it":[83,138],"further":[84],"introduces":[85],"multiscale":[86],"filtering":[87],"decoders":[88],"suppress":[90,116],"non-hole":[91],"region":[92],"features,":[93],"addressing":[94],"the":[95,117,148],"problems":[96],"highlights,":[99],"textures":[101],"or":[102],"bubbles.":[103],"Additionally,":[104],"loss":[109],"can":[110,166],"strongly":[111],"perceive":[112],"information":[114],"color":[118],"difference":[119],"between":[120],"virtual":[121,127,141],"We":[125],"generated":[126],"train":[132],"our":[133,153,164],"network":[134],"architecture":[135],"test":[137],"on":[139],"both":[140],"images,":[146],"experimental":[149],"results":[150],"showing":[151],"that":[152],"method":[154,165],"robust":[156],"zero-shot":[158],"evaluation":[159],"data.":[162],"Particularly,":[163],"attain":[167],"lower":[168],"root":[169],"mean":[170,176],"square":[171],"error":[172,178],"1.551\u00b11.147":[173],"mm":[174,180],"absolute":[177],"1.004\u00b10.632":[179],"than":[181],"state-of-the-art":[182],"approaches.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}