{"id":"https://openalex.org/W4386883366","doi":"https://doi.org/10.1109/rcar58764.2023.10250088","title":"RGB-Depth Structure Similarity for Self-supervised Monocular Depth Estimation","display_name":"RGB-Depth Structure Similarity for Self-supervised Monocular Depth Estimation","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4386883366","doi":"https://doi.org/10.1109/rcar58764.2023.10250088"},"language":"en","primary_location":{"id":"doi:10.1109/rcar58764.2023.10250088","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rcar58764.2023.10250088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5100431545","display_name":"Lulu Zhang","orcid":"https://orcid.org/0000-0001-9076-1898"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lulu Zhang","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037873810","display_name":"Meng Yang","orcid":"https://orcid.org/0000-0002-0795-3221"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100431545"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.1228,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41600064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"841","last_page":"846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9975000023841858,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8307743668556213},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7192105054855347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6536048650741577},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.6514867544174194},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6462055444717407},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6157600283622742},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5978883504867554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45955929160118103},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4336886703968048},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23647579550743103},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13044476509094238}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8307743668556213},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7192105054855347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536048650741577},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.6514867544174194},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6462055444717407},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6157600283622742},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5978883504867554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45955929160118103},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4336886703968048},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23647579550743103},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13044476509094238}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar58764.2023.10250088","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rcar58764.2023.10250088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1803059841","https://openalex.org/W2023438021","https://openalex.org/W2083047701","https://openalex.org/W2124907686","https://openalex.org/W2150066425","https://openalex.org/W2300779272","https://openalex.org/W2520707372","https://openalex.org/W2561074213","https://openalex.org/W2609883120","https://openalex.org/W2612785661","https://openalex.org/W2886322387","https://openalex.org/W2951234442","https://openalex.org/W2955639361","https://openalex.org/W2963488291","https://openalex.org/W2963591054","https://openalex.org/W2981518351","https://openalex.org/W2985775862","https://openalex.org/W3034604951","https://openalex.org/W3035563424","https://openalex.org/W3035679448","https://openalex.org/W3081167590","https://openalex.org/W3108829545","https://openalex.org/W4308190001","https://openalex.org/W4318269780","https://openalex.org/W4321020947","https://openalex.org/W6678569853","https://openalex.org/W6685261749"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W1991834176","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W2003805688","https://openalex.org/W3210711677","https://openalex.org/W4200218943","https://openalex.org/W3111845905","https://openalex.org/W3010374521"],"abstract_inverted_index":{"Monocular":[0],"depth":[1,24,51,60,81,121,136,152,183],"estimation":[2,122],"is":[3,37,106,114,127,143],"a":[4],"fundamental":[5],"technique":[6],"for":[7],"robots":[8],"to":[9,31,38,117,130,146],"perceive":[10],"the":[11,41,72,75,80,84,91,101,119,132,148,155,159,166],"real":[12],"(unseen)":[13],"scene.":[14],"Supervised":[15],"methods":[16],"rely":[17],"on":[18,43,97,158],"large-scale":[19],"datasets":[20,163],"with":[21,49,181,186],"groundtruth":[22],"(GT)":[23],"labels,":[25],"which":[26],"cannot":[27],"be":[28],"well":[29],"generalized":[30],"other":[32],"scenes.":[33],"A":[34],"dominant":[35],"solution":[36],"directly":[39],"train":[40],"model":[42,76],"target":[44],"scenes":[45],"in":[46,83,123,154],"self-supervised":[47,120],"way":[48],"pseudo":[50,59,135],"labels":[52,61,137],"(e.g.":[53],"generated":[54],"by":[55],"stereo":[56],"matching).":[57],"However,":[58],"are":[62],"often":[63],"unreliable":[64,140],"especially":[65],"near":[66],"object":[67],"boundaries.":[68],"It":[69,126,142],"may":[70],"disturb":[71],"training":[73],"of":[74,94,103,134,150],"and":[77,138,175],"consequently":[78],"decrease":[79],"quality":[82],"inference.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"investigate":[90],"structure":[92,102,111,149],"similarity":[93,112],"RGB-Depth":[95,110],"based":[96],"Gaussian":[98],"kernels,":[99],"because":[100],"RGB":[104],"image":[105],"always":[107,176],"reliable.":[108],"Such":[109],"measurement":[113],"then":[115,144],"used":[116],"improve":[118],"two":[124],"aspects.":[125],"first":[128],"utilized":[129,145],"measure":[131],"confidence":[133],"filter":[139],"pixels.":[141],"limit":[147],"predicted":[151],"maps":[153],"loss.":[156],"Experiments":[157],"KITTI":[160],"Eigen":[161],"Splits":[162],"verify":[164],"that":[165],"proposed":[167],"method":[168],"achieves":[169,177],"better":[170,178],"or":[171],"comparable":[172],"quantitative":[173],"results":[174,180],"visual":[179],"clear":[182],"boundaries":[184],"compared":[185],"five":[187],"recent":[188],"baselines.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}