{"id":"https://openalex.org/W4415190867","doi":"https://doi.org/10.1109/iccv51701.2025.00494","title":"Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens","display_name":"Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415190867","doi":"https://doi.org/10.1109/iccv51701.2025.00494"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00494","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.04928","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053347486","display_name":"Suchisrit Gangopadhyay","orcid":"https://orcid.org/0000-0001-5685-5014"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suchisrit Gangopadhyay","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766232","display_name":"Jung Hee Kim","orcid":"https://orcid.org/0000-0001-5435-6166"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jung-Hee Kim","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070319256","display_name":"Xien Chen","orcid":"https://orcid.org/0000-0002-3782-0454"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xien Chen","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014151797","display_name":"Patrick Rim","orcid":"https://orcid.org/0000-0003-4966-3668"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Rim","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076683187","display_name":"Hyoungseob Park","orcid":"https://orcid.org/0000-0003-0787-2082"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyoungseob Park","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108322251","display_name":"Alex Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Wong","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053347486"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24354946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5198","last_page":"5209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12983","display_name":"Satellite Image Processing and Photogrammetry","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10531","display_name":"Advanced Vision and Imaging","score":0.9858999848365784,"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/perspective","display_name":"Perspective (graphical)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5547000169754028},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5299999713897705},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.508899986743927},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5019000172615051},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.46639999747276306},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4099999964237213},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.3763999938964844}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.705299973487854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643999814987183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6302000284194946},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C2779844322","wikidata":"https://www.wikidata.org/wiki/Q2919140","display_name":"Tilt (camera)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00494","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:2508.04928","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.04928","pdf_url":"https://arxiv.org/pdf/2508.04928","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.04928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.04928","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.04928","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.04928","pdf_url":"https://arxiv.org/pdf/2508.04928","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8377316191","display_name":null,"funder_award_id":"2112562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,173],"propose":[1],"a":[2,81,87,129,193],"method":[3,49,138],"to":[4,15,30,44,59,128,162],"extend":[5],"foundational":[6],"monocular":[7],"depth":[8,46],"estimators":[9],"(FMDEs),":[10],"trained":[11,20],"on":[12,21,180],"perspective":[13,62,152,160],"images,":[14,26,63,164],"fisheye":[16,57,70,145,163],"images.":[17],"Despite":[18],"being":[19],"tens":[22],"of":[23,25,53,61,67,83,105,117,196],"millions":[24],"FMDEs":[27,68],"are":[28],"susceptible":[29],"the":[31,51,65,93,100,114,134],"covariate":[32],"shift":[33],"introduced":[34,121],"by":[35,158],"changes":[36],"in":[37,122,133],"camera":[38],"calibration":[39],"(intrinsic,":[40],"distortion)":[41],"parameters,":[42],"leading":[43],"erroneous":[45],"estimates.":[47],"Our":[48,137],"aligns":[50],"distribution":[52],"latent":[54,94,103],"embeddings":[55,95,112],"encoding":[56],"images":[58,146,161],"those":[60],"enabling":[64],"reuse":[66],"for":[69,96,198],"cameras":[71],"without":[72],"retraining":[73],"or":[74,125],"finetuning.":[75],"To":[76],"this":[77],"end,":[78],"we":[79,107,186],"introduce":[80],"set":[82,195],"Calibration":[84],"Tokens":[85],"as":[86],"light-weight":[88],"adaptation":[89],"mechanism":[90],"that":[91,109],"modulates":[92],"alignment.":[97],"By":[98],"exploiting":[99],"already":[101],"expressive":[102],"space":[104],"FMDEs,":[106,179],"posit":[108],"modulating":[110],"their":[111,169],"avoids":[113],"negative":[115],"impact":[116],"artifacts":[118],"and":[119,141,165,183],"loss":[120],"conventional":[123],"recalibration":[124],"map":[126],"projection":[127],"canonical":[130],"reference":[131],"frame":[132],"image":[135,153],"space.":[136],"is":[139,156],"self-supervised":[140],"does":[142],"not":[143],"require":[144],"but":[147],"leverages":[148],"publicly":[149],"available":[150,201],"large-scale":[151],"datasets.":[154],"This":[155],"done":[157],"recalibrating":[159],"enforcing":[166],"consistency":[167],"between":[168],"estimates":[170],"during":[171],"training.":[172],"evaluate":[174],"our":[175],"approach":[176],"with":[177],"several":[178],"both":[181],"indoors":[182],"outdoors,":[184],"where":[185],"consistently":[187],"improve":[188],"over":[189],"state-of-the-art":[190],"methods":[191],"using":[192],"single":[194],"tokens":[197],"both.":[199],"Code":[200],"at:":[202],"https://github.com/JungHeeKim29/calibration-token.":[203]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-15T00:00:00"}