{"id":"https://openalex.org/W4391512429","doi":"https://doi.org/10.1142/s2811032324400034","title":"Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth","display_name":"Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391512429","doi":"https://doi.org/10.1142/s2811032324400034"},"language":"en","primary_location":{"id":"doi:10.1142/s2811032324400034","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2811032324400034","pdf_url":null,"source":{"id":"https://openalex.org/S4387283707","display_name":"World Scientific Annual Review of Artificial Intelligence","issn_l":"2811-0323","issn":["2811-0323","2811-0331"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Scientific Annual Review of Artificial Intelligence","raw_type":"journal-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/A5034805835","display_name":"Chenhang He","orcid":"https://orcid.org/0000-0001-5069-3587"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Chenhang He","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433899","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2078-4215"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034805835"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00992751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"02","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7599514722824097},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7506334781646729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7489651441574097},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7065539956092834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6955395936965942},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5742406249046326},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5509296655654907},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.5292120575904846},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4584817886352539},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.45749223232269287},{"id":"https://openalex.org/keywords/virtual-image","display_name":"Virtual image","score":0.431090384721756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2808881402015686},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2596074342727661},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09668657183647156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599514722824097},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7506334781646729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7489651441574097},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7065539956092834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6955395936965942},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5742406249046326},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5509296655654907},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.5292120575904846},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4584817886352539},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.45749223232269287},{"id":"https://openalex.org/C51970089","wikidata":"https://www.wikidata.org/wiki/Q44415","display_name":"Virtual image","level":2,"score":0.431090384721756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2808881402015686},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2596074342727661},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09668657183647156},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2811032324400034","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2811032324400034","pdf_url":null,"source":{"id":"https://openalex.org/S4387283707","display_name":"World Scientific Annual Review of Artificial Intelligence","issn_l":"2811-0323","issn":["2811-0323","2811-0331"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Scientific Annual Review of Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2115579991","https://openalex.org/W2193145675","https://openalex.org/W2348664362","https://openalex.org/W2495603374","https://openalex.org/W2798872691","https://openalex.org/W2949708697","https://openalex.org/W2963727135","https://openalex.org/W2963794551","https://openalex.org/W2971011093","https://openalex.org/W2981857055","https://openalex.org/W2984013788","https://openalex.org/W3043547428","https://openalex.org/W3106250896","https://openalex.org/W3114509423","https://openalex.org/W6600002382","https://openalex.org/W6600018615","https://openalex.org/W6600129504","https://openalex.org/W6600195515","https://openalex.org/W6600286444","https://openalex.org/W6600339963","https://openalex.org/W6600351811","https://openalex.org/W6600756316","https://openalex.org/W6601258443","https://openalex.org/W6601548533","https://openalex.org/W6601658864","https://openalex.org/W6602106023","https://openalex.org/W6606745006","https://openalex.org/W6607167723","https://openalex.org/W6813246551","https://openalex.org/W6832756385"],"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/W3210711677","https://openalex.org/W4200218943","https://openalex.org/W3111845905","https://openalex.org/W2041414833","https://openalex.org/W43141082"],"abstract_inverted_index":{"Exploiting":[0],"geometric":[1],"features":[2,110],"is":[3,16,68],"a":[4,55,61,92],"common":[5],"approach":[6,41],"to":[7,19,36,84,111,124],"enhance":[8],"monocular":[9,63],"3D":[10,64],"object":[11,65],"detection.":[12],"However,":[13],"their":[14,80],"performance":[15],"limited":[17],"due":[18],"the":[20,44,49,106,122,130,146],"absence":[21],"of":[22,48,52,94],"depth":[23,31,57,82,112,131],"information.":[24],"To":[25],"address":[26],"this":[27,40],"limitation,":[28],"an":[29,86,117],"external":[30],"estimator":[32],"can":[33],"be":[34],"employed":[35],"predict":[37],"depth,":[38],"but":[39],"significantly":[42],"reduces":[43],"efficiency":[45],"and":[46,79],"flexibility":[47],"model.":[50],"Instead":[51],"relying":[53],"on":[54],"costly":[56],"estimator,":[58],"we":[59,75,115],"propose":[60],"depth-aware":[62],"detector":[66,107],"that":[67,120],"trained":[69],"using":[70],"augmented":[71],"training":[72],"data.":[73],"Specifically,":[74],"utilize":[76],"reference":[77],"images":[78,96],"corresponding":[81],"maps":[83],"train":[85],"efficient":[87],"rendering":[88],"module,":[89],"which":[90],"synthesizes":[91],"variety":[93],"photo-realistic":[95],"with":[97],"different":[98],"virtual":[99],"depths.":[100],"By":[101],"learning":[102],"from":[103,129],"these":[104],"images,":[105],"adapts":[108],"its":[109],"variations.":[113],"Furthermore,":[114],"introduce":[116],"auxiliary":[118],"module":[119],"guides":[121],"network":[123],"learn":[125],"more":[126],"informative":[127],"representations":[128],"images.":[132],"Both":[133],"modules":[134],"are":[135],"removed":[136],"after":[137],"training,":[138],"resulting":[139],"in":[140],"no":[141],"additional":[142],"computational":[143],"overhead":[144],"during":[145],"final":[147],"deployment.":[148]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}