{"id":"https://openalex.org/W6944094120","doi":"https://doi.org/10.15496/publikation-88300","title":"Implicit Object Pose Estimation on RGB Images Using Deep Learning Methods","display_name":"Implicit Object Pose Estimation on RGB Images Using Deep Learning Methods","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W6944094120","doi":"https://doi.org/10.15496/publikation-88300"},"language":"en","primary_location":{"id":"doi:10.15496/publikation-88300","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-88300","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.15496/publikation-88300","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"H\u00f6fer, Timon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"H\u00f6fer, Timon","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.8636999726295471},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7089999914169312},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5927000045776367},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5907999873161316},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5702000260353088},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.5425999760627747},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4593999981880188}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8762999773025513},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8636999726295471},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.772599995136261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717199981212616},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7089999914169312},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5907999873161316},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.5425999760627747},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C14551309","wikidata":"https://www.wikidata.org/wiki/Q4636325","display_name":"3D single-object recognition","level":4,"score":0.2849000096321106},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15496/publikation-88300","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-88300","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.15496/publikation-88300","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-88300","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,9,76,137,156,159,171],"rise":[2],"of":[3,11,158,173],"robotic":[4,49],"and":[5,8,26,122],"camera":[6,39],"systems":[7],"success":[10],"deep":[12,102,128],"learning":[13,103],"in":[14,21,51,65,71,101,112],"computer":[15],"vision,":[16],"there":[17],"is":[18,29,95],"growing":[19],"interest":[20],"precisely":[22],"determining":[23],"object":[24,110,118,120],"positions":[25],"orientations.":[27],"This":[28,79],"crucial":[30],"for":[31,92,133,170],"tasks":[32],"like":[33,117],"automated":[34],"bin":[35],"picking,":[36],"where":[37],"a":[38,48,62,96],"sensor":[40],"analyzes":[41],"images":[42],"or":[43,68],"point":[44],"clouds":[45],"to":[46,108,143,154],"guide":[47],"arm":[50],"grasping":[52],"objects.":[53],"Pose":[54],"recognition":[55],"has":[56],"broader":[57],"applications,":[58],"such":[59],"as":[60],"predicting":[61],"car's":[63],"trajectory":[64],"autonomous":[66],"driving":[67],"adapting":[69],"objects":[70],"virtual":[72],"reality":[73],"based":[74],"on":[75,82,149],"viewer's":[77],"perspective.":[78],"dissertation":[80],"focuses":[81],"RGB-based":[83],"pose":[84,130,144,175],"estimation":[85,131],"methods":[86,132],"that":[87],"use":[88],"depth":[89],"information":[90],"only":[91],"refinement,":[93],"which":[94,165],"challenging":[97],"problem.":[98],"Recent":[99],"advances":[100],"have":[104],"made":[105],"it":[106],"possible":[107],"predict":[109],"poses":[111],"RGB":[113,134],"images,":[114,135],"despite":[115],"challenges":[116],"overlap,":[119],"symmetries":[121],"more.":[123],"We":[124],"introduce":[125],"two":[126],"implicit":[127,161,174],"learning-based":[129],"covering":[136],"entire":[138],"process":[139],"from":[140],"data":[141],"generation":[142],"selection.":[145],"Furthermore,":[146],"theoretical":[147],"findings":[148],"Fourier":[150],"embeddings":[151],"are":[152,166],"shown":[153],"improve":[155],"performance":[157],"so-called":[160],"neural":[162],"representations":[163],"-":[164],"then":[167],"successfully":[168],"utilized":[169],"task":[172],"estimation.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}