{"id":"https://openalex.org/W4413278037","doi":"https://doi.org/10.1109/icip55913.2025.11084506","title":"Leveraging Depth Foundation Models in Self Supervised Monocular Depth Estimation","display_name":"Leveraging Depth Foundation Models in Self Supervised Monocular Depth Estimation","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413278037","doi":"https://doi.org/10.1109/icip55913.2025.11084506"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","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/A5119330172","display_name":"Aaron Jerry Ninan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155601","display_name":"Innovative Research (United States)","ror":"https://ror.org/04dec0k98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Jerry Ninan","raw_affiliation_strings":["Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence","institution_ids":["https://openalex.org/I4210155601"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Atharva Diwan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155601","display_name":"Innovative Research (United States)","ror":"https://ror.org/04dec0k98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atharva Diwan","raw_affiliation_strings":["Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence","institution_ids":["https://openalex.org/I4210155601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062348639","display_name":"Longjiao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155601","display_name":"Innovative Research (United States)","ror":"https://ror.org/04dec0k98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Longjiao Zhao","raw_affiliation_strings":["Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence","institution_ids":["https://openalex.org/I4210155601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073472506","display_name":"Jaechul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155601","display_name":"Innovative Research (United States)","ror":"https://ror.org/04dec0k98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaechul Kim","raw_affiliation_strings":["Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda R&D Co.,Ltd.,Tokyo Computer Science Innovative Research Excellence","institution_ids":["https://openalex.org/I4210155601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210155601"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20927639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2760","last_page":"2765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9523000121116638,"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":0.9523000121116638,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9290000200271606,"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/foundation","display_name":"Foundation (evidence)","score":0.693769633769989},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6770045757293701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6404426097869873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5833438038825989},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.47073137760162354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46082010865211487},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12468942999839783},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09147316217422485}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.693769633769989},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6770045757293701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6404426097869873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5833438038825989},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.47073137760162354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46082010865211487},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12468942999839783},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09147316217422485},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2520707372","https://openalex.org/W2955639361","https://openalex.org/W2985775862","https://openalex.org/W3109908659","https://openalex.org/W3173274332","https://openalex.org/W3176063055","https://openalex.org/W4312253171","https://openalex.org/W4312398233","https://openalex.org/W4319300392","https://openalex.org/W4402716270","https://openalex.org/W4402779285","https://openalex.org/W4406856892","https://openalex.org/W4410719519"],"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":{"Monocular":[0],"depth":[1,37,151],"estimation":[2,38,152],"is":[3],"a":[4,54,75,122,145],"critical":[5],"component":[6],"of":[7,60,84,102,138],"autonomous":[8],"driving,":[9],"enabling":[10],"vehicles":[11],"to":[12,57,69,109,117,148],"perceive":[13],"and":[14,27,31,45,97,124,141],"navigate":[15],"their":[16],"surroundings":[17],"efficiently.":[18],"Existing":[19],"self-supervised":[20,71],"methods":[21,111],"often":[22],"rely":[23,113],"on":[24,114,132],"complicated":[25,94],"architectures":[26],"complex":[28],"loss":[29,98],"functions":[30],"face":[32],"major":[33],"challenges":[34],"like":[35],"inaccurate":[36],"for":[39,81,127],"dynamic":[40,77,85],"objects,":[41],"blurred":[42],"edge":[43,46],"boundary,":[44],"flattening":[47],"[1].":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"introduce":[53],"novel":[55,76],"approach":[56],"leverage":[58],"powers":[59],"high":[61],"quality":[62],"pseudo-depth":[63],"supervision":[64],"from":[65],"DepthAnything-V2":[66],"model":[67],"[2]":[68],"existing":[70,110,149],"approaches.":[72],"We":[73],"propose":[74],"mask":[78],"generation":[79],"method":[80,140],"any":[82],"kind":[83],"objects":[86,89],"including":[87],"non-rigid":[88],"in":[90],"the":[91,136],"scene,":[92],"without":[93],"training":[95],"procedures":[96],"functions.":[99],"The":[100],"simplicity":[101],"our":[103,139],"approach,":[104],"with":[105],"competitive":[106,146],"results":[107],"compared":[108],"that":[112],"sophisticated":[115],"techniques":[116],"solve":[118],"basic":[119],"problems,":[120],"provides":[121],"robust":[123],"practical":[125],"solution":[126],"real-world":[128],"deployment.":[129],"Extensive":[130],"experiments":[131],"Cityscapes":[133],"datasets":[134],"verify":[135],"effectiveness":[137],"establish":[142],"it":[143],"as":[144],"alternative":[147],"monocular":[150],"models.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}