{"id":"https://openalex.org/W2893396759","doi":"https://doi.org/10.1109/cvprw.2018.00069","title":"Learning 3D Scene Semantics and Structure from a Single Depth Image","display_name":"Learning 3D Scene Semantics and Structure from a Single Depth Image","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2893396759","doi":"https://doi.org/10.1109/cvprw.2018.00069","mag":"2893396759"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw.2018.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2018.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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/A5039611354","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0002-2419-4140"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Bo Yang","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076947156","display_name":"Zihang Lai","orcid":"https://orcid.org/0000-0002-9872-0756"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zihang Lai","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101670414","display_name":"Xiaoxuan Lu","orcid":"https://orcid.org/0000-0003-4760-7523"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaoxuan Lu","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075826891","display_name":"Shu\u2010Yu Lin","orcid":"https://orcid.org/0000-0003-3054-3332"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuyu Lin","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053684989","display_name":"Hongkai Wen","orcid":"https://orcid.org/0000-0003-1159-090X"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hongkai Wen","raw_affiliation_strings":["University of Warwick"],"affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060183988","display_name":"Andrew Markham","orcid":"https://orcid.org/0000-0001-5716-3941"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Markham","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010637110","display_name":"Niki Trigoni","orcid":"https://orcid.org/0000-0001-6236-9645"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niki Trigoni","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5039611354"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.6379,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74829507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"4223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/computer-science","display_name":"Computer science","score":0.7974212765693665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7629798650741577},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.7335741519927979},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6708648204803467},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6441584229469299},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5768415927886963},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5720348954200745},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5229804515838623},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49130430817604065},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4712671935558319},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4640924334526062},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4617711305618286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10246950387954712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7974212765693665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7629798650741577},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.7335741519927979},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6708648204803467},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6441584229469299},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5768415927886963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5720348954200745},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5229804515838623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49130430817604065},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4712671935558319},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4640924334526062},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4617711305618286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10246950387954712},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvprw.2018.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2018.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:bbcdf929-45b7-46f0-8122-996c2da0f9c3","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:bbcdf929-45b7-46f0-8122-996c2da0f9c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W1920022804","https://openalex.org/W2066813062","https://openalex.org/W2067912884","https://openalex.org/W2102605133","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2427751284","https://openalex.org/W2444097022","https://openalex.org/W2520300725","https://openalex.org/W2524140598","https://openalex.org/W2557465155","https://openalex.org/W2559882727","https://openalex.org/W2613718673","https://openalex.org/W2787366651","https://openalex.org/W2962835968","https://openalex.org/W2963150697","https://openalex.org/W2963369474","https://openalex.org/W2963446712","https://openalex.org/W2963640720","https://openalex.org/W2963735494","https://openalex.org/W2963857746","https://openalex.org/W2963893349","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6640300118","https://openalex.org/W6666899075","https://openalex.org/W6684191040","https://openalex.org/W6687483927"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W4388446985","https://openalex.org/W3112772842"],"abstract_inverted_index":{"In":[0,68],"this":[1],"paper,":[2],"we":[3,91],"aim":[4,26],"to":[5,27,62,77,99,118,148,152],"understand":[6],"the":[7,35,51,79,102,154,171],"semantics":[8,103,138],"and":[9,33,72,95,104,131,139,145,168,173],"3D":[10,36,123,155],"structure":[11,105],"of":[12,38,65,84,106,176],"a":[13,16,39,43,58,63,85,107,110,149],"scene":[14,40,52,108,165],"from":[15,109],"single":[17,111],"depth":[18,112],"image.":[19,113],"Recent":[20],"deep":[21],"neural":[22],"networks":[23],"based":[24],"methods":[25],"simultaneously":[28,100],"learn":[29,101],"object":[30],"class":[31],"labels":[32],"infer":[34],"shape":[37,124,150],"represented":[41,56],"by":[42,57],"large":[44,80],"voxel":[45,82],"grid.":[46],"However,":[47],"individual":[48],"objects":[49],"within":[50],"are":[53,75,143,159],"usually":[54],"only":[55],"few":[59],"voxels":[60],"leading":[61],"loss":[64],"geometric":[66],"detail.":[67],"addition,":[69],"significant":[70],"computational":[71],"memory":[73],"resources":[74],"required":[76],"process":[78],"scale":[81],"grid":[83],"whole":[86],"scene.":[87],"To":[88],"address":[89],"this,":[90],"propose":[92],"an":[93,121],"efficient":[94,122],"holistic":[96],"pipeline,":[97],"3R-Depth,":[98],"Our":[114],"key":[115],"idea":[116],"is":[117],"deeply":[119],"fuse":[120],"estimator":[125,151],"with":[126],"existing":[127],"recognition":[128],"(e.g.,":[129,133],"ResNets)":[130],"segmentation":[132],"MaskR-CNN)":[134],"techniques.":[135],"Object":[136],"level":[137],"latent":[140],"feature":[141],"maps":[142],"extracted":[144],"then":[146],"fed":[147],"extract":[153],"shape.":[156],"Extensive":[157],"experiments":[158],"conducted":[160],"on":[161],"large-scale":[162],"synthesized":[163],"indoor":[164],"datasets,":[166],"quantitatively":[167],"qualitatively":[169],"demonstrating":[170],"merits":[172],"superior":[174],"performance":[175],"3R-Depth.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}