{"id":"https://openalex.org/W4416748964","doi":"https://doi.org/10.1109/iros60139.2025.11246758","title":"Adjacent-view Transformers for Supervised Surround-view Depth Estimation","display_name":"Adjacent-view Transformers for Supervised Surround-view Depth Estimation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748964","doi":"https://doi.org/10.1109/iros60139.2025.11246758"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5084921716","display_name":"Xianda Guo","orcid":"https://orcid.org/0000-0003-2822-4690"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xianda Guo","raw_affiliation_strings":["Wuhan University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100556217","display_name":"Wenjie Yuan","orcid":"https://orcid.org/0009-0006-5866-8291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Yuan","raw_affiliation_strings":["Waytous"],"affiliations":[{"raw_affiliation_string":"Waytous","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457286","display_name":"Yunpeng Zhang","orcid":"https://orcid.org/0009-0002-2722-7128"},"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":"Yunpeng Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387908","display_name":"Yang Tian","orcid":"https://orcid.org/0000-0002-6633-8579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Yang","raw_affiliation_strings":["PhiGent Robotics"],"affiliations":[{"raw_affiliation_string":"PhiGent Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062302579","display_name":"Chenming Zhang","orcid":"https://orcid.org/0000-0003-1426-0092"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Chenming Zhang","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705530","display_name":"Zheng Zhu","orcid":"https://orcid.org/0000-0002-4435-1692"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Zhu","raw_affiliation_strings":["GigaAI"],"affiliations":[{"raw_affiliation_string":"GigaAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113587037","display_name":"Qin Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zou","raw_affiliation_strings":["Wuhan University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113009903","display_name":"Long Chen","orcid":"https://orcid.org/0000-0002-5123-5913"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5084921716"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36935436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9391000270843506,"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":0.9391000270843506,"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":0.006500000134110451,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.006200000178068876,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6486999988555908},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5659000277519226},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.503000020980835},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4722000062465668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43689998984336853}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7106999754905701},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6093999743461609},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5659000277519226},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3804999887943268},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3626999855041504},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1513100184","https://openalex.org/W1905829557","https://openalex.org/W1942767339","https://openalex.org/W2083047701","https://openalex.org/W2108598243","https://openalex.org/W2115579991","https://openalex.org/W2117248802","https://openalex.org/W2132947399","https://openalex.org/W2165114467","https://openalex.org/W2194775991","https://openalex.org/W2259424905","https://openalex.org/W2471962767","https://openalex.org/W2604231069","https://openalex.org/W2609883120","https://openalex.org/W2776879428","https://openalex.org/W2883040756","https://openalex.org/W2950496566","https://openalex.org/W2952813711","https://openalex.org/W2955639361","https://openalex.org/W2962793285","https://openalex.org/W2963231581","https://openalex.org/W2963446712","https://openalex.org/W2963488291","https://openalex.org/W2963496125","https://openalex.org/W2963583471","https://openalex.org/W2963617879","https://openalex.org/W2963619659","https://openalex.org/W2963675327","https://openalex.org/W2963911235","https://openalex.org/W2964153986","https://openalex.org/W2964968086","https://openalex.org/W2985066174","https://openalex.org/W2990394353","https://openalex.org/W2990946490","https://openalex.org/W3034364596","https://openalex.org/W3034514115","https://openalex.org/W3034604951","https://openalex.org/W3035574168","https://openalex.org/W3091300680","https://openalex.org/W3096609285","https://openalex.org/W3096678291","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3141975725","https://openalex.org/W3177322621","https://openalex.org/W3188511781","https://openalex.org/W3203257492","https://openalex.org/W4214493665","https://openalex.org/W4214520160","https://openalex.org/W4289812641","https://openalex.org/W4303449827","https://openalex.org/W4312572946","https://openalex.org/W4312819733","https://openalex.org/W4312977443","https://openalex.org/W4319300976","https://openalex.org/W4321512633","https://openalex.org/W4382464460","https://openalex.org/W4386076096","https://openalex.org/W4390872043","https://openalex.org/W4399938885","https://openalex.org/W4402727359","https://openalex.org/W4402753888","https://openalex.org/W4403947105","https://openalex.org/W4413945797"],"related_works":[],"abstract_inverted_index":{"Depth":[0,65],"estimation":[1,29,66],"has":[2,23,149],"been":[3,24],"widely":[4],"studied":[5],"and":[6,17,106,169],"serves":[7],"as":[8],"the":[9,31,40,49,71,96,104,115,122,127,133,139],"fundamental":[10],"step":[11],"of":[12],"3D":[13],"perception":[14],"for":[15,62,92],"robotics":[16],"autonomous":[18],"driving.":[19],"Though":[20],"significant":[21],"progress":[22],"made":[25],"in":[26,30],"monocular":[27],"depth":[28,72],"past":[32],"decades,":[33],"these":[34],"attempts":[35],"are":[36],"mainly":[37],"conducted":[38],"on":[39,166],"KITTI":[41],"benchmark":[42],"with":[43,89],"only":[44],"front-view":[45],"cameras,":[46],"which":[47,131],"ignores":[48],"correlations":[50],"across":[51,74,135,142],"surround-view":[52,143],"cameras.":[53,77],"In":[54,146],"this":[55],"paper,":[56],"we":[57,79],"propose":[58],"an":[59],"Adjacent-View":[60],"Transformer":[61],"Supervised":[63],"Surround-view":[64],"(AVT-SSDepth),":[67],"to":[68,102,137],"jointly":[69],"predict":[70],"maps":[73],"multiple":[75],"surrounding":[76],"Specifically,":[78],"employ":[80],"a":[81],"global-to-local":[82],"feature":[83,108,144],"extraction":[84],"module":[85,117],"that":[86,156],"combines":[87],"CNN":[88],"transformer":[90],"layers":[91],"enriched":[93],"representations.":[94],"Further,":[95],"adjacent-view":[97],"attention":[98,129,134],"mechanism":[99],"is":[100,112,124,173],"proposed":[101],"enable":[103],"intra-view":[105],"inter-view":[107],"propagation.":[109],"The":[110],"former":[111],"achieved":[113],"by":[114,126],"self-attention":[116],"within":[118],"each":[119],"view,":[120],"while":[121],"latter":[123],"realized":[125],"adjacent":[128],"module,":[130],"computes":[132],"multi-cameras":[136],"exchange":[138],"multi-scale":[140],"representations":[141],"maps.":[145],"addition,":[147],"AVT-SSDepth":[148],"strong":[150],"cross-dataset":[151],"generalization.":[152],"Extensive":[153],"experiments":[154],"show":[155],"our":[157],"method":[158],"achieves":[159],"superior":[160],"performance":[161],"over":[162],"existing":[163],"state-of-the-art":[164],"methods":[165],"both":[167],"DDAD":[168],"nuScenes":[170],"datasets.":[171],"Code":[172],"available":[174],"at":[175],"https://github.com/XiandaGuo/SSDepth.":[176]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}