{"id":"https://openalex.org/W4389363545","doi":"https://doi.org/10.48550/arxiv.2312.01283","title":"Deeper into Self-Supervised Monocular Indoor Depth Estimation","display_name":"Deeper into Self-Supervised Monocular Indoor Depth Estimation","publication_year":2023,"publication_date":"2023-12-03","ids":{"openalex":"https://openalex.org/W4389363545","doi":"https://doi.org/10.48550/arxiv.2312.01283"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.01283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01283","pdf_url":"https://arxiv.org/pdf/2312.01283","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.01283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043121078","display_name":"Chao Fan","orcid":"https://orcid.org/0000-0003-2216-7576"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fan, Chao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003976377","display_name":"Zhenyu Yin","orcid":"https://orcid.org/0000-0001-5403-3922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Zhenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035671153","display_name":"Yue Li","orcid":"https://orcid.org/0000-0002-0222-9859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006243926","display_name":"Feiqing Zhang","orcid":"https://orcid.org/0000-0003-4636-9607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Feiqing","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043121078"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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":0.9994999766349792,"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":0.989799976348877,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9843999743461609,"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":0.7886917591094971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840763330459595},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7657896280288696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7148118019104004},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6884952187538147},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6238861083984375},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6020858287811279},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5868803262710571},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5343294143676758},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49688008427619934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46005767583847046},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45340460538864136},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42861732840538025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3361114263534546},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24848291277885437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14541953802108765},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13597065210342407},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07772630453109741}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7886917591094971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840763330459595},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7657896280288696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7148118019104004},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6884952187538147},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6238861083984375},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6020858287811279},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5868803262710571},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5343294143676758},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49688008427619934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46005767583847046},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45340460538864136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42861732840538025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3361114263534546},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24848291277885437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14541953802108765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13597065210342407},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07772630453109741},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.01283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01283","pdf_url":"https://arxiv.org/pdf/2312.01283","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.01283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.01283","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:2312.01283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01283","pdf_url":"https://arxiv.org/pdf/2312.01283","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2560215812","https://openalex.org/W2347897961","https://openalex.org/W2949601986","https://openalex.org/W2997457842","https://openalex.org/W1997431798"],"abstract_inverted_index":{"Monocular":[0],"depth":[1,21],"estimation":[2],"using":[3],"Convolutional":[4],"Neural":[5],"Networks":[6],"(CNNs)":[7],"has":[8],"shown":[9],"impressive":[10],"performance":[11],"in":[12,91],"outdoor":[13],"driving":[14],"scenes.":[15],"However,":[16],"self-supervised":[17],"learning":[18],"of":[19,31,42,65,98,128,158],"indoor":[20,53],"from":[22,87],"monocular":[23],"sequences":[24],"is":[25,38,48,165],"quite":[26],"challenging":[27],"for":[28],"researchers":[29],"because":[30],"the":[32,39,46,49,85,96,126,134,142,155],"following":[33],"two":[34,66,117],"main":[35],"reasons.":[36],"One":[37],"large":[40,148],"areas":[41],"low-texture":[43,88],"regions":[44],"and":[45],"other":[47],"complex":[50],"ego-motion":[51,100],"on":[52,133,161],"training":[54],"datasets.":[55],"In":[56,68,150],"this":[57],"work,":[58],"our":[59,139,159],"proposed":[60],"method,":[61],"named":[62],"IndoorDepth,":[63],"consists":[64],"innovations.":[67],"particular,":[69],"we":[70,152],"first":[71],"propose":[72],"a":[73,112,147],"novel":[74],"photometric":[75,103],"loss":[76],"with":[77,116],"improved":[78],"structural":[79],"similarity":[80],"(SSIM)":[81],"function":[82],"to":[83,93,110],"tackle":[84],"challenge":[86],"regions.":[89],"Moreover,":[90],"order":[92],"further":[94],"mitigate":[95],"issue":[97],"inaccurate":[99],"prediction,":[101],"multiple":[102],"losses":[104],"at":[105,167],"different":[106],"stages":[107],"are":[108],"used":[109],"train":[111],"deeper":[113],"pose":[114,119],"network":[115],"residual":[118],"blocks.":[120],"Subsequent":[121],"ablation":[122],"study":[123],"can":[124],"validate":[125,154],"effectiveness":[127],"each":[129],"new":[130],"idea.":[131],"Experiments":[132],"NYUv2":[135],"benchmark":[136],"demonstrate":[137],"that":[138],"IndoorDepth":[140],"outperforms":[141],"previous":[143],"state-of-the-art":[144],"methods":[145],"by":[146],"margin.":[149],"addition,":[151],"also":[153],"generalization":[156],"ability":[157],"method":[160],"ScanNet":[162],"dataset.":[163],"Code":[164],"availabe":[166],"https://github.com/fcntes/IndoorDepth.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}