{"id":"https://openalex.org/W7163031407","doi":"https://doi.org/10.1109/lra.2026.3699248","title":"SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation","display_name":"SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163031407","doi":"https://doi.org/10.1109/lra.2026.3699248"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3699248","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3699248","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2026.3699248","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002371386","display_name":"C Li","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Changxuan Li","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0003-2409-3598","affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137517917","display_name":"Nadine Berner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156768","display_name":"BMW Group (Germany)","ror":"https://ror.org/044kkbh92","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nadine Berner","raw_affiliation_strings":["BMW Group, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1843-2747","affiliations":[{"raw_affiliation_string":"BMW Group, Munich, Germany","institution_ids":["https://openalex.org/I4210156768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137594695","display_name":"Nassir Navab","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nassir Navab","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6032-5611","affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135219089","display_name":"Federico Tombari","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Federico Tombari","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5598-5212","affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000701918","display_name":"Stefano Gasperini","orcid":"https://orcid.org/0000-0002-7841-1569"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefano Gasperini","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7841-1569","affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65646736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"7","first_page":"8968","last_page":"8975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.24789999425411224,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.24789999425411224,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.11959999799728394,"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":0.11190000176429749,"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/scale","display_name":"Scale (ratio)","score":0.5579000115394592},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4189999997615814},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3400000035762787},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3010999858379364},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29589998722076416}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5895000100135803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5612999796867371},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44359999895095825},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.413100004196167},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.3140999972820282},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3699248","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3699248","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2026.3699248","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3699248","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.7184247970581055}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"depth":[1,13,25,38,60,75,88,120,149],"estimation":[2],"from":[3],"monocular":[4],"sequences":[5],"relies":[6],"on":[7,28,161,168],"the":[8,24,29,46,49,52,57,74,79,87,102,113,118,127,172],"joint":[9],"learning":[10],"of":[11,48,174],"a":[12,15],"and":[14,59,72,100,121,126,145,159,164],"pose":[16,30,58,103,122,176],"network.":[17],"Despite":[18],"abundant":[19],"research":[20],"done":[21],"to":[22,42,68,92],"improve":[23,69],"network,":[26],"efforts":[27],"remain":[31],"limited.":[32],"In":[33],"this":[34,70,153],"context,":[35],"even":[36],"when":[37],"is":[39,131],"estimated":[40,55,89,114],"up":[41],"scale,":[43],"we":[44,63],"highlight":[45],"importance":[47],"alignment":[50,71,108],"between":[51],"scene":[53,115],"scales":[54,116],"by":[56,105,117],"nets.":[61],"Then,":[62],"introduce":[64],"SA4Depth,":[65],"an":[66],"approach":[67],"boost":[73],"predictions":[76],"while":[77],"keeping":[78],"inference":[80],"time":[81],"unchanged.":[82],"Our":[83,136],"proposed":[84],"method":[85],"uses":[86],"during":[90],"training":[91],"reproject":[93],"learnable":[94],"visual":[95],"features":[96],"across":[97,133],"consecutive":[98],"frames":[99],"refine":[101],"estimates":[104],"reducing":[106],"feature":[107],"residuals.":[109],"With":[110],"our":[111,175],"method,":[112],"separate":[119],"networks":[123],"are":[124],"aligned,":[125],"prediction":[128],"scale":[129],"consistency":[130],"improved":[132],"different":[134],"sequences.":[135],"differentiable":[137],"refinement":[138],"integrates":[139],"seamlessly":[140],"into":[141],"existing":[142],"self-supervised":[143],"pipelines":[144],"substantially":[146],"improves":[147],"their":[148],"estimates.":[150],"We":[151],"demonstrate":[152],"with":[154],"extensive":[155],"experiments":[156],"both":[157],"outdoors":[158],"indoors":[160],"KITTI,":[162],"Cityscapes,":[163],"NYUv2.":[165],"Additionally,":[166],"results":[167],"KITTI":[169],"Odometry":[170],"confirm":[171],"effectiveness":[173],"refinement.":[177]},"counts_by_year":[],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2026-06-02T00:00:00"}