{"id":"https://openalex.org/W7203797979","doi":"https://doi.org/10.48550/arxiv.2608.16984","title":"PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation","display_name":"PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203797979","doi":"https://doi.org/10.48550/arxiv.2608.16984"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.16984","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16984","pdf_url":"https://arxiv.org/pdf/2608.16984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7203797979"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.16984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147656959","display_name":"Zhiyuan Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Zhiyuan","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133789938","display_name":"Guanying Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Guanying","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036054001","display_name":"Lingteng Qiu","orcid":"https://orcid.org/0000-0002-3250-0486","observed_orcids":["https://orcid.org/0000-0002-3250-0486"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu, Lingteng","raw_affiliation_strings":["CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003608795","display_name":"Ruimao Zhang","orcid":"https://orcid.org/0000-0001-9511-7532","observed_orcids":["https://orcid.org/0000-0001-9511-7532"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Ruimao","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009164482","display_name":"Shuguang Robert Cui","orcid":"https://orcid.org/0000-0003-2608-775X","observed_orcids":["https://orcid.org/0000-0003-2608-775X"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Shuguang","raw_affiliation_strings":["CUHKSZ","Shenzhen-FNii"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen-FNii","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139645811","display_name":"Xiaochun Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Xiaochun","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9848999977111816,"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":0.9848999977111816,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.009700000286102295,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.0015999999595806003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monocular-depth-estimation","display_name":"monocular depth estimation","score":1.0},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.4790000021457672},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.7149999737739563},{"id":"https://openalex.org/keywords/structure-preservation","display_name":"structure preservation","score":0.7480000257492065},{"id":"https://openalex.org/keywords/object-boundaries","display_name":"object boundaries","score":0.5910000205039978},{"id":"https://openalex.org/keywords/global-context-modeling","display_name":"global context modeling","score":0.7089999914169312}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6565999984741211},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6190999746322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6137999892234802},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5792999863624573},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C89720835","wikidata":"https://www.wikidata.org/wiki/Q1531701","display_name":"Global illumination","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.265500009059906},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.16984","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16984","pdf_url":"https://arxiv.org/pdf/2608.16984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.16984","doi":"https://doi.org/10.48550/arxiv.2608.16984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.16984","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.16984","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16984","pdf_url":"https://arxiv.org/pdf/2608.16984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203797979.pdf","grobid_xml":"https://content.openalex.org/works/W7203797979.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2897093520","https://openalex.org/W2962960377","https://openalex.org/W2965851327","https://openalex.org/W3094502228","https://openalex.org/W4322616103","https://openalex.org/W4394671465","https://openalex.org/W4403853671","https://openalex.org/W4403882324","https://openalex.org/W4408882247","https://openalex.org/W4415318366","https://openalex.org/W4416748746","https://openalex.org/W4416958102","https://openalex.org/W6910554155","https://openalex.org/W6967128091","https://openalex.org/W7105740705","https://openalex.org/W7118664066","https://openalex.org/W7125780081","https://openalex.org/W7163047584","https://openalex.org/W7163184259","https://openalex.org/W7167204982","https://openalex.org/W7169858122"],"related_works":["https://openalex.org/W7118542592","https://openalex.org/W4403947105","https://openalex.org/W6947887503","https://openalex.org/W4405138788","https://openalex.org/W4403882324","https://openalex.org/W4390874218","https://openalex.org/W4414271954","https://openalex.org/W6979363912","https://openalex.org/W4409095629","https://openalex.org/W4402753888"],"abstract_inverted_index":{"Recent":[0],"monocular":[1,54],"depth":[2,55,64,89,102,116],"estimators":[3],"achieve":[4],"strong":[5],"zero-shot":[6,106],"generalization,":[7],"yet":[8],"often":[9],"struggle":[10],"to":[11,22],"preserve":[12],"fine-grained":[13],"structures":[14,95],"and":[15,30,96,125],"object":[16],"boundaries.":[17],"We":[18],"attribute":[19],"this":[20,47],"limitation":[21],"the":[23],"prevalent":[24],"combination":[25],"of":[26,79],"large-patch":[27,68],"ViT":[28,69],"encoders":[29],"convolutional":[31],"decoders,":[32],"as":[33],"coarse":[34],"tokenization":[35],"can":[36],"weaken":[37],"pixel-level":[38,63],"cues":[39],"that":[40,57],"upsampling":[41],"cannot":[42],"fully":[43],"recover.":[44],"To":[45],"address":[46],"issue,":[48],"we":[49],"propose":[50],"PXDepth,":[51],"a":[52,67,75],"discriminative":[53],"model":[56,126],"separates":[58],"global":[59,71,101,115],"context":[60],"modeling":[61],"from":[62],"prediction.":[65],"Specifically,":[66],"captures":[70],"scene":[72],"context,":[73],"while":[74,118],"pixel-space":[76],"predictor":[77],"composed":[78],"Context-Modulated":[80],"Pixel":[81],"Transformer":[82],"blocks":[83],"maintains":[84],"high-resolution":[85],"spatial":[86],"representations":[87],"throughout":[88],"estimation.":[90],"This":[91],"design":[92],"preserves":[93],"fine":[94],"sharp":[97],"boundaries":[98],"without":[99],"sacrificing":[100],"consistency.":[103],"Across":[104],"diverse":[105],"benchmarks,":[107],"PXDepth":[108],"combines":[109],"faithful":[110],"local":[111],"geometry":[112],"with":[113],"competitive":[114],"accuracy":[117],"remaining":[119],"efficient":[120],"at":[121,129],"inference.":[122],"Our":[123],"code":[124],"are":[127],"available":[128],"https://yuanzhy29.github.io/PXDepth-Page/.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-20T00:00:00"}