{"id":"https://openalex.org/W4417129336","doi":"https://doi.org/10.1109/iccv51701.2025.00629","title":"Hybrid-Grained Feature Aggregation with Coarse-to-Fine Language Guidance for Self-Supervised Monocular Depth Estimation","display_name":"Hybrid-Grained Feature Aggregation with Coarse-to-Fine Language Guidance for Self-Supervised Monocular Depth Estimation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417129336","doi":"https://doi.org/10.1109/iccv51701.2025.00629"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00629","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/2510.09320","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061847709","display_name":"Wenyao Zhang","orcid":"https://orcid.org/0000-0001-7080-9604"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyao Zhang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005337649","display_name":"Hongsi Liu","orcid":"https://orcid.org/0000-0001-6934-8708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongsi Liu","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443971","display_name":"Bohan Li","orcid":"https://orcid.org/0000-0001-7766-9579"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Li","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639951","display_name":"Jiawei He","orcid":"https://orcid.org/0000-0002-6666-5916"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei He","raw_affiliation_strings":["CASIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CASIA","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023962766","display_name":"Zekun Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekun Qi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007302951","display_name":"Yunnan Wang","orcid":"https://orcid.org/0000-0002-1957-2696"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunnan Wang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101102569","display_name":"Shengyang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyang Zhao","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112942734","display_name":"Xinqiang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinqiang Yu","raw_affiliation_strings":["CASIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CASIA","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739843","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-2531-3137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100641352","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-3873-1653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5061847709"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37141323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6678","last_page":"6692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.6243000030517578,"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":0.6243000030517578,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08110000193119049,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.03830000013113022,"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/monocular","display_name":"Monocular","score":0.6158000230789185},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.47049999237060547},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3840999901294708},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.3603000044822693},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6567999720573425},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.47049999237060547},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00629","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:2510.09320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09320","pdf_url":"https://arxiv.org/pdf/2510.09320","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.2510.09320","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.09320","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.09320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09320","pdf_url":"https://arxiv.org/pdf/2510.09320","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":[{"id":"https://openalex.org/G1299811542","display_name":null,"funder_award_id":"LQ23F010008","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G3527258163","display_name":null,"funder_award_id":"62302246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"self-supervised":[1,116],"monocular":[2],"depth":[3,108,125,129],"estimation":[4],"(MDE)":[5],"approaches":[6],"encounter":[7],"performance":[8],"limitations":[9],"due":[10],"to":[11,35,82,106],"insufficient":[12],"semantic-spatial":[13],"knowledge":[14],"extraction.":[15],"To":[16],"address":[17],"this":[18],"challenge,":[19],"we":[20,56,97],"propose":[21],"Hybrid-depth,":[22],"a":[23,49,123],"novel":[24],"framework":[25],"that":[26,157],"systematically":[27],"integrates":[28,113],"foundation":[29],"models":[30],"(e.g.,":[31,119],"CLIP":[32,61],"and":[33,39,64,102,136],"DINO)":[34],"extract":[36],"visual":[37],"priors":[38],"acquire":[40],"sufficient":[41],"contextual":[42],"information":[43,101],"for":[44],"MDE.":[45],"Our":[46],"approach":[47],"introduces":[48],"coarse-to-fine":[50],"progressive":[51],"learning":[52],"framework:":[53],"1)":[54],"Firstly,":[55],"aggregate":[57],"multi-grained":[58],"features":[59],"from":[60],"(global":[62],"semantics)":[63],"DINO":[65],"(local":[66],"spatial":[67,138],"details)":[68],"under":[69],"contrastive":[70],"language":[71,104,141],"guidance.":[72],"A":[73],"proxy":[74],"task":[75],"comparing":[76],"close-distant":[77],"image":[78],"patches":[79],"is":[80,177],"designed":[81],"enforce":[83],"depth-aware":[84],"feature":[85,147],"alignment":[86,105],"using":[87],"text":[88],"prompts;":[89],"2)":[90],"Next,":[91],"building":[92],"on":[93,152],"the":[94,153],"coarse":[95],"features,":[96],"integrate":[98],"camera":[99],"pose":[100],"pixel-wise":[103],"refine":[107],"predictions.":[109],"This":[110],"module":[111],"seamlessly":[112],"with":[114],"existing":[115],"MDE":[117],"pipelines":[118],"Monodepth2,":[120],"ManyDepth)":[121],"as":[122],"plug-and-play":[124],"encoder,":[126],"enhancing":[127],"continuous":[128],"estimation.":[130],"By":[131],"aggregating":[132],"CLIP's":[133],"semantic":[134],"context":[135],"DINO's":[137],"details":[139],"through":[140],"guidance,":[142],"our":[143,158],"method":[144,159],"effectively":[145],"addresses":[146],"granularity":[148],"mismatches.":[149],"Extensive":[150],"experiments":[151],"KITTI":[154],"benchmark":[155],"demonstrate":[156],"significantly":[160],"outperforms":[161],"SOTA":[162],"methods":[163],"across":[164],"all":[165],"metrics,":[166],"which":[167],"also":[168],"indeed":[169],"benefits":[170],"downstream":[171],"tasks":[172],"like":[173],"BEV":[174],"perception.":[175],"Code":[176],"available":[178],"at":[179],"https://github.com/Zhangwenyao1/Hybrid-depth.":[180]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-14T00:00:00"}