{"id":"https://openalex.org/W3193924749","doi":"https://doi.org/10.1109/icip42928.2021.9506744","title":"Rethinking Training Objective For Self-Supervised Monocular Depth Estimation: Semantic Cues To Rescue","display_name":"Rethinking Training Objective For Self-Supervised Monocular Depth Estimation: Semantic Cues To Rescue","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3193924749","doi":"https://doi.org/10.1109/icip42928.2021.9506744","mag":"3193924749"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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/A5057139613","display_name":"Keyao Li","orcid":"https://orcid.org/0000-0002-6220-7459"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyao Li","raw_affiliation_strings":["Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering,Shenzhen,China","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447691","display_name":"Ge Li","orcid":"https://orcid.org/0000-0003-0140-0949"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering,Shenzhen,China","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101509081","display_name":"Thomas Li","orcid":"https://orcid.org/0000-0001-9950-4679"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Li","raw_affiliation_strings":["Advanced Institute of Information Technology, Peking University,Hangzhou,China","Advanced Institute of Information Technology, Peking University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Institute of Information Technology, Peking University,Hangzhou,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Advanced Institute of Information Technology, Peking University, Hangzhou, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.09738553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"3308","last_page":"3312"},"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/T10638","display_name":"Optical measurement and interference techniques","score":0.998199999332428,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/computer-science","display_name":"Computer science","score":0.7614154815673828},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6863076090812683},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6799346208572388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6415175199508667},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.629113495349884},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6003679633140564},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5352450609207153},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49959397315979004},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4738726317882538},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47085756063461304},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4593712091445923},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43290627002716064},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42086362838745117},{"id":"https://openalex.org/keywords/depth-perception","display_name":"Depth perception","score":0.41609278321266174},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4156970977783203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40746212005615234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10139480233192444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614154815673828},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6863076090812683},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6799346208572388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6415175199508667},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.629113495349884},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6003679633140564},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5352450609207153},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49959397315979004},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4738726317882538},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47085756063461304},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4593712091445923},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43290627002716064},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42086362838745117},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.41609278321266174},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4156970977783203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40746212005615234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10139480233192444},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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":25,"referenced_works":["https://openalex.org/W1921093919","https://openalex.org/W2115579991","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2300779272","https://openalex.org/W2340897893","https://openalex.org/W2520707372","https://openalex.org/W2609883120","https://openalex.org/W2948647700","https://openalex.org/W2951234442","https://openalex.org/W2963412495","https://openalex.org/W2963583471","https://openalex.org/W2963906250","https://openalex.org/W2964968086","https://openalex.org/W3014641072","https://openalex.org/W3107156787","https://openalex.org/W4287863801","https://openalex.org/W6685261749","https://openalex.org/W6687483927","https://openalex.org/W6697658144","https://openalex.org/W6726644806","https://openalex.org/W6736677999","https://openalex.org/W6767071366","https://openalex.org/W6771531989","https://openalex.org/W6781070145"],"related_works":["https://openalex.org/W2074216034","https://openalex.org/W2073100926","https://openalex.org/W1976277412","https://openalex.org/W2785517206","https://openalex.org/W4213085014","https://openalex.org/W2066222094","https://openalex.org/W4225386930","https://openalex.org/W2017236227","https://openalex.org/W2051061664","https://openalex.org/W2031714422"],"abstract_inverted_index":{"Monocular":[0],"depth":[1,84,93,184],"estimation":[2],"finds":[3],"a":[4,32,44,65],"wide":[5],"range":[6],"of":[7,26,67,132],"applications":[8],"in":[9,31,75,80],"modeling":[10],"3D":[11],"scenes.":[12],"Since":[13],"it":[14],"is":[15,38,58,162],"expensive":[16],"to":[17,22,39,51,60,72,110,129,150],"collect":[18],"ground":[19],"truth":[20],"labels":[21],"supervise":[23],"training,":[24],"plenty":[25],"works":[27],"have":[28],"been":[29],"done":[30],"self-supervised":[33],"manner.":[34],"A":[35],"common":[36],"practice":[37],"train":[40],"the":[41,120,130,133,152],"network":[42],"optimizing":[43],"photometric":[45,136],"objective":[46,57,161],"(i.e.,":[47],"view":[48,156],"synthesis)":[49],"due":[50,128],"its":[52],"effectiveness.":[53],"However,":[54],"this":[55,96],"training":[56,138],"sensitive":[59],"optical":[61],"changes":[62],"and":[63,83,187],"lacks":[64],"consideration":[66],"object-level":[68,171],"cues,":[69],"which":[70],"leads":[71],"sub-optimal":[73],"results":[74],"some":[76],"cases,":[77],"e.g.,":[78],"artifacts":[79],"complex":[81],"regions":[82],"discontinuities":[85],"around":[86],"thin":[87],"structures.":[88],"We":[89],"summarize":[90],"them":[91],"as":[92],"ambiguities.":[94],"In":[95],"paper,":[97],"we":[98,122,141],"propose":[99],"an":[100,170],"easy":[101],"yet":[102],"effective":[103],"architecture,":[104],"introducing":[105,177],"semantic":[106,148],"cues":[107,149],"into":[108],"supervision":[109],"solve":[111],"problems":[112,121],"mentioned":[113],"above.":[114],"First":[115],"through":[116],"our":[117,145,181],"study":[118],"on":[119,193],"Figure":[123],"out":[124],"that":[125,175],"they":[126],"are":[127],"limitation":[131],"commonly":[134],"applied":[135],"reconstruction":[137],"objective.":[139],"Then":[140],"come":[142],"up":[143],"with":[144,190],"method":[146,182],"using":[147],"encode":[151],"geometry":[153],"constraint":[154],"behind":[155],"synthesis.":[157],"The":[158],"proposed":[159],"novel":[160],"more":[163],"credible":[164],"towards":[165],"confusing":[166],"pixels,":[167],"also":[168],"takes":[169],"perception.":[172],"Experiments":[173],"show":[174],"without":[176],"extra":[178],"inference":[179],"complexity,":[180],"alleviates":[183],"ambiguities":[185],"greatly":[186],"performs":[188],"comparably":[189],"state-of-the-art":[191],"methods":[192],"KITTI":[194],"benchmark.":[195]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}