{"id":"https://openalex.org/W7127312387","doi":"https://doi.org/10.1109/tip.2026.3659033","title":"Cross360: 360\u00b0 Monocular Depth Estimation via Cross Projections Across Scales","display_name":"Cross360: 360\u00b0 Monocular Depth Estimation via Cross Projections Across Scales","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127312387","doi":"https://doi.org/10.1109/tip.2026.3659033","pmid":"https://pubmed.ncbi.nlm.nih.gov/41632651"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3659033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3659033","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5124890767","display_name":"Kun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Kun Huang","raw_affiliation_strings":["School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-7812-4562","affiliations":[{"raw_affiliation_string":"School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124921553","display_name":"Fang-Lue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Fang-Lue Zhang","raw_affiliation_strings":["School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-8728-8726","affiliations":[{"raw_affiliation_string":"School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049195176","display_name":"Neil A. Dodgson","orcid":"https://orcid.org/0000-0001-7649-8528"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Neil Dodgson","raw_affiliation_strings":["School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-7649-8528","affiliations":[{"raw_affiliation_string":"School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41156924"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11217742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2901","last_page":"2912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9668999910354614,"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":0.9668999910354614,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.00559999980032444,"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/feature-extraction","display_name":"Feature extraction","score":0.5138000249862671},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5131999850273132},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5077000260353088},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.482699990272522},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4269999861717224},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.41940000653266907}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208999752998352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5570999979972839},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4934999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4593999981880188},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.41940000653266907},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.349700003862381},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C157157409","wikidata":"https://www.wikidata.org/wiki/Q909601","display_name":"Tangent space","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C65557600","wikidata":"https://www.wikidata.org/wiki/Q7249451","display_name":"Projection method","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3659033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3659033","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41632651","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41632651","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G336524778","display_name":null,"funder_award_id":"20-VUW-180","funder_id":"https://openalex.org/F4320335369","funder_display_name":"Marsden Fund"},{"id":"https://openalex.org/G569852861","display_name":null,"funder_award_id":"400876","funder_id":"https://openalex.org/F4320320006","funder_display_name":"Royal Society"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320335369","display_name":"Marsden Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"360\u00b0depth":[0],"estimation":[1,140],"is":[2,120,159],"a":[3,13,76],"challenging":[4],"research":[5],"problem":[6],"due":[7],"to":[8,29,101],"the":[9,53,65,108,123,155],"difficulty":[10],"of":[11,113,122],"finding":[12],"representation":[14,56],"that":[15],"both":[16],"preserves":[17],"global":[18,40,50,55,83,124],"continuity":[19],"and":[20,41,52,82,166,173],"avoids":[21],"distortion":[22],"in":[23,61,153,164],"spherical":[24],"images.":[25],"Existing":[26],"methods":[27,146],"attempt":[28],"leverage":[30],"complementary":[31],"information":[32,84],"from":[33],"multiple":[34],"projections,":[35],"but":[36],"struggle":[37],"with":[38,90,107,131],"balancing":[39],"local":[42,45,81,103],"consistency.":[43],"Their":[44],"patch":[46,119],"features":[47,106,136],"have":[48],"limited":[49],"perception,":[51],"combined":[54],"does":[57],"not":[58],"address":[59,70],"discrepancies":[60],"feature":[62],"extraction":[63],"at":[64,177],"boundaries":[66],"between":[67],"patches.":[68],"To":[69],"these":[71],"issues,":[72],"we":[73],"propose":[74],"Cross360,":[75],"novel":[77],"cross-attention-based":[78],"architecture":[79],"integrating":[80],"using":[85],"less-distorted":[86],"tangent":[87,104,117],"patches":[88],"along":[89],"equirectangular":[91,109],"features.":[92],"Our":[93],"Cross":[94],"Projection":[95],"Feature":[96,129],"Alignment":[97],"module":[98,133],"employs":[99],"cross-attention":[100],"align":[102],"projection":[105,118],"projection's":[110],"360\u00b0":[111,157],"field":[112],"view,":[114],"ensuring":[115],"each":[116],"aware":[121],"context.":[125],"Additionally,":[126],"our":[127],"Progressive":[128],"Aggregation":[130],"Attention":[132],"refines":[134],"multi-scaled":[135],"progressively,":[137],"enhancing":[138],"depth":[139,169],"accuracy.":[141],"Cross360":[142],"significantly":[143],"outperforms":[144],"existing":[145],"across":[147],"most":[148],"benchmark":[149],"datasets,":[150],"especially":[151],"those":[152],"which":[154],"entire":[156],"image":[158],"available,":[160],"demonstrating":[161],"its":[162],"effectiveness":[163],"accurate":[165],"globally":[167],"consistent":[168],"estimation.":[170],"The":[171],"code":[172],"model":[174],"are":[175],"available":[176],"https://github.com/huangkun101230/Cross360.":[178]},"counts_by_year":[],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2026-02-04T00:00:00"}