{"id":"https://openalex.org/W4402716314","doi":"https://doi.org/10.1109/cvpr52733.2024.00955","title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","display_name":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402716314","doi":"https://doi.org/10.1109/cvpr52733.2024.00955"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100330776","display_name":"Zhenyu Li","orcid":"https://orcid.org/0000-0003-1048-657X"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Zhenyu Li","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST)","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038170669","display_name":"Shariq Farooq Bhat","orcid":"https://orcid.org/0000-0002-7668-4424"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Shariq Farooq Bhat","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST)","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076768552","display_name":"Peter Wonka","orcid":"https://orcid.org/0000-0003-0627-9746"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Peter Wonka","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST)","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100330776"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":7.5964,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.98156935,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10016","last_page":"10025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7461243867874146},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.6474221348762512},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6197128891944885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5686885714530945},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.492313027381897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46822449564933777},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45839983224868774},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.34105828404426575},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15660080313682556},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1542232632637024},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.076761394739151}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7461243867874146},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.6474221348762512},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6197128891944885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5686885714530945},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.492313027381897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46822449564933777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45839983224868774},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.34105828404426575},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15660080313682556},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1542232632637024},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.076761394739151},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W63091017","https://openalex.org/W125693051","https://openalex.org/W1901129140","https://openalex.org/W2115579991","https://openalex.org/W2133665775","https://openalex.org/W2340897893","https://openalex.org/W2520322935","https://openalex.org/W2594519801","https://openalex.org/W2811153284","https://openalex.org/W2949208911","https://openalex.org/W2951234442","https://openalex.org/W2955639361","https://openalex.org/W2963150697","https://openalex.org/W2963488291","https://openalex.org/W2964153986","https://openalex.org/W2983735215","https://openalex.org/W2985775862","https://openalex.org/W3035563424","https://openalex.org/W3094502228","https://openalex.org/W3095980151","https://openalex.org/W3138516171","https://openalex.org/W3170863103","https://openalex.org/W3173727695","https://openalex.org/W3174865552","https://openalex.org/W3180199962","https://openalex.org/W3181256344","https://openalex.org/W3188511781","https://openalex.org/W3215974962","https://openalex.org/W4200150166","https://openalex.org/W4225949693","https://openalex.org/W4312396555","https://openalex.org/W4312524114","https://openalex.org/W4312973546","https://openalex.org/W4321222415","https://openalex.org/W4322616103","https://openalex.org/W4385804850","https://openalex.org/W4386066348","https://openalex.org/W4386076521","https://openalex.org/W4386083069","https://openalex.org/W4388183180","https://openalex.org/W4390873054","https://openalex.org/W4390873429","https://openalex.org/W4390873622","https://openalex.org/W6685261749","https://openalex.org/W6784333009","https://openalex.org/W6786046587","https://openalex.org/W6787334116","https://openalex.org/W6796761347","https://openalex.org/W6799339439","https://openalex.org/W6855322519","https://openalex.org/W6858005800"],"related_works":["https://openalex.org/W2114959296","https://openalex.org/W38346124","https://openalex.org/W2502442966","https://openalex.org/W2138666621","https://openalex.org/W2383936314","https://openalex.org/W1992771654","https://openalex.org/W2022661278","https://openalex.org/W2777914781","https://openalex.org/W4246369972","https://openalex.org/W4244869112"],"abstract_inverted_index":{"Single":[0],"image":[1],"depth":[2,16,148,161],"estimation":[3,17],"is":[4,154],"a":[5,55,78,175],"foundational":[6],"task":[7],"in":[8,26,181],"computer":[9],"vision":[10],"and":[11,30,111,117,125,138,179,192],"generative":[12],"modeling.":[13],"However,":[14],"prevailing":[15],"models":[18],"grapple":[19],"with":[20,59,82,150],"accom-modating":[21],"the":[22,47,65,69,101,105,128,157,184],"increasing":[23],"resolutions":[24],"commonplace":[25],"to-day's":[27],"consumer":[28],"cameras":[29],"devices.":[31],"Existing":[32],"high-resolution":[33,147],"strategies":[34],"show":[35],"promise,":[36],"but":[37],"they":[38],"often":[39],"face":[40],"limi-tations,":[41],"ranging":[42],"from":[43],"error":[44,188],"propagation":[45],"to":[46,63,100],"loss":[48],"of":[49,68,156,169,177,183],"high-frequency":[50],"details.":[51,152],"We":[52],"present":[53],"PatchFusion,":[54],"novel":[56],"tile-based":[57],"framework":[58,144,165],"three":[60],"key":[61],"components":[62],"improve":[64],"current":[66],"state":[67],"art:":[70],"(1)":[71],"A":[72,92,113],"patch-wise":[73],"fusion":[74,102],"network":[75],"that":[76,96,142],"fuses":[77],"globally-consistent":[79],"coarse":[80],"prediction":[81],"finer,":[83],"in-consistent":[84],"tiled":[85],"predictions":[86],"via":[87],"high-level":[88],"feature":[89],"guidance,":[90],"(2)":[91],"Global-to-Local":[93],"(G2L)":[94],"module":[95],"adds":[97],"vital":[98],"con-text":[99],"network,":[103],"discarding":[104],"need":[106],"for":[107,130,160,174],"patch":[108,122],"selection":[109],"heuristics,":[110],"(3)":[112],"Consistency-Aware":[114],"Training":[115],"(CAT)":[116],"Inference":[118],"(CAI)":[119],"approach,":[120],"emphasizing":[121],"overlap":[123],"consistency":[124],"thereby":[126],"eradicating":[127],"neces-sity":[129],"post-processing.":[131],"Experiments":[132],"on":[133,167,190],"Unreal.":[134],"Stereo":[135],"4K,":[136],"MVS-Synth,":[137,193],"Middleburry":[139],"2014":[140],"demonstrate":[141],"our":[143,164],"can":[145],"generate":[146],"maps":[149],"intricate":[151],"PatchFusion":[153],"independent":[155],"base":[158],"model":[159],"estimation.":[162],"Notably,":[163],"built":[166],"top":[168],"SOTA":[170],"ZoeDepth":[171],"brings":[172],"improvements":[173],"total":[176],"17.3%":[178],"29.4%":[180],"terms":[182],"root":[185],"mean":[186],"squared":[187],"(RMSE)":[189],"UnrealStereo4K":[191],"respectively.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":9}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}