{"id":"https://openalex.org/W4414929906","doi":"https://doi.org/10.1109/iccv51701.2025.00757","title":"One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images","display_name":"One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414929906","doi":"https://doi.org/10.1109/iccv51701.2025.00757"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00757","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/2503.22351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023191515","display_name":"Byeongjun Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":true,"raw_author_name":"Byeongjun Kwon","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088335007","display_name":"Munchurl Kim","orcid":"https://orcid.org/0000-0003-1634-7722"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Munchurl Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023191515"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38088572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8077","last_page":"8087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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":0.9914000034332275,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9837999939918518,"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/upsampling","display_name":"Upsampling","score":0.6966999769210815},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5759999752044678},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5687999725341797},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5577999949455261},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5562999844551086},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.516700029373169},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5091999769210815},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.5023000240325928},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.48089998960494995}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7257000207901001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095999717712402},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6966999769210815},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5759999752044678},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5309000015258789},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.5023000240325928},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.42399999499320984},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3675999939441681},{"id":"https://openalex.org/C2777042112","wikidata":"https://www.wikidata.org/wiki/Q5281658","display_name":"Discontinuity (linguistics)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.26089999079704285}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00757","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:2503.22351","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.22351","pdf_url":"https://arxiv.org/pdf/2503.22351","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.22351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.22351","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:2503.22351","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.22351","pdf_url":"https://arxiv.org/pdf/2503.22351","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0,204],"depth":[1,51,69,73,82,89,99,154,223],"estimation":[2,48,74,224],"(DE)":[3],"models":[4,18,186],"exhibit":[5],"strong":[6],"generalization":[7,194],"performance":[8],"as":[9],"they":[10],"are":[11],"trained":[12],"on":[13,50,104,168,201,206],"large-scale":[14],"datasets.":[15],"However,":[16],"existing":[17,222],"struggle":[19],"with":[20,52],"high-resolution":[21,72],"images":[22],"due":[23,107],"to":[24,46,58,96,108,116,189,195],"the":[25,59,67,87,109,153,184],"discrepancy":[26],"in":[27,63,66,92],"image":[28],"resolutions":[29],"of":[30,138],"training":[31,60,200],"(with":[32],"smaller":[33],"resolutions)":[34],"and":[35,131,163,177,211],"inference":[36],"(for":[37],"high":[38],"resolutions).":[39],"Processing":[40],"them":[41],"at":[42],"full":[43],"resolution":[44,61],"leads":[45],"decreased":[47],"accuracy":[49],"tremendous":[53],"memory":[54],"consumption,":[55],"while":[56,151],"downsampling":[57],"results":[62],"blurred":[64],"edges":[65],"estimated":[68,88],"images.":[70],"Prevailing":[71],"methods":[75,102],"adopt":[76],"a":[77,165,173],"patch-based":[78],"approach,":[79],"which":[80],"introduces":[81],"discontinuity":[83,155],"issues":[84],"when":[85],"reassembling":[86],"patches,":[90],"resulting":[91],"test-time":[93,149],"inefficiency.":[94],"Additionally,":[95],"obtain":[97],"fine-grained":[98],"details,":[100],"these":[101,121],"rely":[103],"synthetic":[105,202],"datasets":[106,197],"real-world":[110,196],"sparse":[111],"ground":[112],"truth":[113],"depth,":[114],"leading":[115],"poor":[117],"generalizability.":[118],"To":[119],"tackle":[120],"limitations,":[122],"we":[123],"propose":[124],"Patch":[125,144],"Refine":[126],"Once":[127],"(PRO),":[128],"an":[129],"efficient":[130],"generalizable":[132],"tile-based":[133],"framework.":[134],"Our":[135],"PRO":[136,216],"consists":[137],"two":[139],"key":[140],"components:":[141],"(i)":[142],"Grouped":[143],"Consistency":[145],"Training":[146],"that":[147,182,214],"enhances":[148],"efficiency":[150],"mitigating":[152],"problem":[156],"by":[157],"jointly":[158],"processing":[159],"four":[160],"overlapping":[161,170],"patches":[162],"enforcing":[164],"consistency":[166],"loss":[167],"their":[169],"regions":[171],"within":[172],"single":[174],"backpropagation":[175],"step,":[176],"(ii)":[178],"Bias":[179],"Free":[180],"Masking":[181],"prevents":[183],"DE":[185],"from":[187],"overfitting":[188],"dataset-specific":[190],"biases,":[191],"enabling":[192],"better":[193],"even":[198],"after":[199],"data.":[203],"evaluations":[205],"Booster,":[207],"ETH3D,":[208],"Middlebury":[209],"2014,":[210],"NuScenes":[212],"demonstrate":[213],"our":[215],"can":[217],"be":[218],"seamlessly":[219],"integrated":[220],"into":[221],"models.":[225]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}