{"id":"https://openalex.org/W7164395252","doi":"https://doi.org/10.48550/arxiv.2606.12368","title":"DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images","display_name":"DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164395252","doi":"https://doi.org/10.48550/arxiv.2606.12368"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.12368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12368","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.12368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138407056","display_name":"Pengfei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138428557","display_name":"Shihao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138424602","display_name":"Liyi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Liyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138438379","display_name":"Zhiyuan Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Zhiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138413587","display_name":"Guowen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Guowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138459443","display_name":"Lei Zhang (38117)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9664000272750854,"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":0.9664000272750854,"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":0.011500000022351742,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.003800000064074993,"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/panorama","display_name":"Panorama","score":0.8374000191688538},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7146000266075134},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6844000220298767},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5349000096321106},{"id":"https://openalex.org/keywords/perspective-distortion","display_name":"Perspective distortion","score":0.39100000262260437},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.362199991941452},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.35749998688697815},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.8374000191688538},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7146000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6862999796867371},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6844000220298767},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5799999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5788999795913696},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C2779989122","wikidata":"https://www.wikidata.org/wiki/Q15889487","display_name":"Perspective distortion","level":3,"score":0.39100000262260437},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3537999987602234},{"id":"https://openalex.org/C99404194","wikidata":"https://www.wikidata.org/wiki/Q163362","display_name":"Vanishing point","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.12368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12368","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.12368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12368","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"While":[0],"monocular":[1],"depth":[2,11,41,82],"estimation":[3,12,83],"has":[4],"achieved":[5],"significant":[6],"progress,":[7],"achieving":[8],"generalized":[9],"metric":[10,40,71,81,183],"for":[13],"both":[14,220],"narrow":[15],"field-of-view":[16],"(FoV)":[17],"perspectives":[18],"and":[19,35,60,63,129,148,174,222],"$360^\\circ$":[20],"panoramas":[21],"remains":[22],"an":[23],"unsolved":[24],"challenge.":[25],"Existing":[26],"methods":[27,111,213],"are":[28],"often":[29],"tailored":[30],"to":[31,37,90,118,139],"specific":[32],"camera":[33],"types":[34],"struggle":[36],"produce":[38],"accurate":[39],"that":[42,112,194],"generalizes":[43],"across":[44],"diverse":[45,207],"settings.":[46],"This":[47,158],"limitation":[48],"stems":[49],"from":[50,108,185],"two":[51],"key":[52],"challenges:":[53],"the":[54,64,96,142,150,162],"inherent":[55],"geometric":[56,135,163],"discrepancy":[57],"between":[58],"perspective":[59,104,172,187,221],"panoramic":[61,67,100,223],"cameras,":[62],"scarcity":[65,178],"of":[66],"training":[68],"data":[69,177],"with":[70,154],"annotations.":[72],"In":[73],"this":[74],"work,":[75],"we":[76,94,121],"introduce":[77,122],"DepthMaster,":[78],"a":[79,123,170,191],"unified":[80],"framework.":[84],"Rather":[85],"than":[86],"employing":[87],"specialized":[88,146],"networks":[89],"learn":[91],"spherical":[92],"distortions,":[93],"reformulate":[95],"problem":[97],"by":[98,165,179],"decomposing":[99],"images":[101],"into":[102,169],"overlapping":[103],"patches.":[105],"Crucially,":[106],"distinct":[107],"prior":[109],"projection-based":[110],"rely":[113],"on":[114,190,205],"ad-hoc":[115],"architectural":[116],"modifications":[117],"handle":[119],"boundaries,":[120],"novel":[124],"Correspondence":[125],"Consistency":[126],"Loss":[127],"(CCL)":[128],"inject":[130],"virtual":[131],"projection":[132],"cameras":[133],"as":[134],"priors,":[136],"allowing":[137],"us":[138],"seamlessly":[140],"stitch":[141],"patches":[143],"while":[144],"avoiding":[145],"operators":[147],"keeping":[149],"backbone":[151],"largely":[152],"compatible":[153],"standard":[155],"Transformer":[156],"designs.":[157],"strategy":[159],"also":[160,215],"resolves":[161],"differences":[164],"unifying":[166],"all":[167],"inputs":[168],"canonical":[171],"representation,":[173],"effectively":[175],"circumvents":[176],"directly":[180],"unlocking":[181],"powerful":[182],"priors":[184],"vast":[186],"datasets.":[188],"Trained":[189],"mixed":[192],"dataset":[193],"contains":[195],"only":[196,211],"one":[197],"panorama":[198],"dataset,":[199],"DepthMaster":[200],"achieves":[201],"state-of-the-art":[202],"zero-shot":[203],"performance":[204],"13":[206],"datasets,":[208],"outperforming":[209],"not":[210],"universal":[212],"but":[214],"leading":[216],"specialist":[217],"models":[218],"in":[219],"domains.":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}