{"id":"https://openalex.org/W7164864618","doi":"https://doi.org/10.1145/3805622.3810840","title":"GeoPro-Depth: Geometrically Consistent Prompting for Robust Metric Depth Completion","display_name":"GeoPro-Depth: Geometrically Consistent Prompting for Robust Metric Depth Completion","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164864618","doi":"https://doi.org/10.1145/3805622.3810840"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810840","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810840","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810840","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112108533","display_name":"Xun Fang","orcid":"https://orcid.org/0009-0006-7302-4662"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Fang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1615-1723","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138651141","display_name":"Zixuan Hua","orcid":"https://orcid.org/0009-0000-2603-2797"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Hua","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-2603-2797","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414906","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0003-0467-4347"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0467-4347","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94122988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.7145000100135803,"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":0.7145000100135803,"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":0.2313999980688095,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/consistency","display_name":"Consistency (knowledge bases)","score":0.6600000262260437},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6363000273704529},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3894999921321869},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.37279999256134033},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.36570000648498535},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.3555999994277954},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3537999987602234},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.3319000005722046}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6363000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5582000017166138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47519999742507935},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3894999921321869},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3287999927997589},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810840","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810840","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810840","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810840","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5324591994285583}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1905829557","https://openalex.org/W2021851106","https://openalex.org/W2026203852","https://openalex.org/W2125310925","https://openalex.org/W2132947399","https://openalex.org/W2139905387","https://openalex.org/W2520707372","https://openalex.org/W2794739174","https://openalex.org/W2955639361","https://openalex.org/W2963316641","https://openalex.org/W4205991051","https://openalex.org/W4214520160","https://openalex.org/W4235111023","https://openalex.org/W4312651322","https://openalex.org/W4312933868","https://openalex.org/W4386075593","https://openalex.org/W4390873054","https://openalex.org/W4390873101","https://openalex.org/W4390874575","https://openalex.org/W4395481595","https://openalex.org/W4402727359","https://openalex.org/W4402753888","https://openalex.org/W4402753924","https://openalex.org/W4402754057","https://openalex.org/W4408352007","https://openalex.org/W4413145918","https://openalex.org/W4413147070","https://openalex.org/W4413696186","https://openalex.org/W4415798746","https://openalex.org/W7133193597"],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,46,84,154],"vision":[3],"foundation":[4,70],"models":[5,14],"has":[6],"significantly":[7],"advanced":[8],"monocular":[9],"depth":[10,38,61,116],"estimation;":[11],"however,":[12],"these":[13],"inherently":[15],"suffer":[16],"from":[17,50],"scale":[18],"ambiguity,":[19],"limiting":[20],"their":[21],"utility":[22],"in":[23,118],"downstream":[24],"metric":[25,112],"applications.":[26],"To":[27,80],"address":[28],"this,":[29],"we":[30],"propose":[31],"GeoPro-Depth,":[32],"a":[33,41,55,68,73,103,139],"novel":[34],"framework":[35],"that":[36],"reformulates":[37],"completion":[39],"as":[40],"geometric":[42,104,149],"prompting":[43],"task.":[44],"Instead":[45],"training":[47,106],"reconstruction":[48,152],"networks":[49],"scratch,":[51],"our":[52,155],"method":[53],"leverages":[54],"lightweight":[56],"PromptNet":[57],"to":[58,76,98,110],"encode":[59],"sparse":[60],"measurements,":[62],"which":[63],"are":[64],"then":[65],"integrated":[66],"into":[67],"pre-trained":[69],"model":[71],"via":[72],"zero-initialization":[74],"strategy":[75],"safeguard":[77],"semantic":[78],"features.":[79],"mitigate":[81],"the":[82,127,147],"impact":[83],"sensor":[85],"noise,":[86],"an":[87],"Instance-Aware":[88],"Geometric":[89],"Filtering":[90],"(IAGF)":[91],"module":[92],"is":[93,108],"introduced,":[94],"utilizing":[95],"instance":[96],"constraints":[97],"robustly":[99],"filter":[100],"outliers.":[101],"Furthermore,":[102],"consistency":[105,150],"objective":[107],"formulated":[109],"align":[111],"predictions":[113],"with":[114],"relative":[115],"priors":[117],"unobserved":[119],"regions,":[120],"ensuring":[121],"structural":[122],"fidelity.":[123],"Extensive":[124],"experiments":[125],"on":[126,138],"ScanNet++,":[128],"TUM-RGBD,":[129],"and":[130,151],"Replica":[131],"datasets":[132],"demonstrate":[133],"state-of-the-art":[134],"performance.":[135],"Downstream":[136],"evaluation":[137],"3D":[140],"Gaussian":[141],"Splatting":[142],"SLAM":[143],"system":[144],"further":[145],"confirms":[146],"superior":[148],"quality":[153],"model.":[156]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}