{"id":"https://openalex.org/W4380077548","doi":"https://doi.org/10.1142/s1793351x23620027","title":"PrimitivePose: Generic Model and Representation for 3D Bounding Box Prediction of Unseen Objects","display_name":"PrimitivePose: Generic Model and Representation for 3D Bounding Box Prediction of Unseen Objects","publication_year":2023,"publication_date":"2023-06-10","ids":{"openalex":"https://openalex.org/W4380077548","doi":"https://doi.org/10.1142/s1793351x23620027"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x23620027","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s1793351x23620027","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"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":"International Journal of Semantic Computing","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/A5014580415","display_name":"Andreas Kriegler","orcid":"https://orcid.org/0000-0002-5653-5181"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Andreas Kriegler","raw_affiliation_strings":["Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 6, Vienna 1210, Austria","Visual Computing and Human-Centered Technology, TU Wien, Favoritenstra\u00dfe 9-11, Vienna 1040, Austria"],"affiliations":[{"raw_affiliation_string":"Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 6, Vienna 1210, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Visual Computing and Human-Centered Technology, TU Wien, Favoritenstra\u00dfe 9-11, Vienna 1040, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010414319","display_name":"Csaba Beleznai","orcid":"https://orcid.org/0000-0003-1880-2979"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Csaba Beleznai","raw_affiliation_strings":["Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 6, Vienna 1210, Austria"],"affiliations":[{"raw_affiliation_string":"Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 6, Vienna 1210, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026627076","display_name":"Margrit Gelautz","orcid":"https://orcid.org/0000-0002-9476-0865"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Margrit Gelautz","raw_affiliation_strings":["Visual Computing and Human-Centered Technology, TU Wien, Favoritenstra\u00dfe 9-11, Vienna 1040, Austria"],"affiliations":[{"raw_affiliation_string":"Visual Computing and Human-Centered Technology, TU Wien, Favoritenstra\u00dfe 9-11, Vienna 1040, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068783661","display_name":"Markus Murschitz","orcid":"https://orcid.org/0000-0002-5199-4602"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Markus Murschitz","raw_affiliation_strings":["Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 4, Vienna 1210, Austria"],"affiliations":[{"raw_affiliation_string":"Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 4, Vienna 1210, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088554342","display_name":"Kai G\u00f6bel","orcid":"https://orcid.org/0000-0001-5074-3652"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Kai G\u00f6bel","raw_affiliation_strings":["Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 6, Vienna 1210, Austria"],"affiliations":[{"raw_affiliation_string":"Vision, Automation and Control, AIT Austrian Institute of Technology, Giefinggasse 6, Vienna 1210, Austria","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014580415"],"corresponding_institution_ids":["https://openalex.org/I132118926","https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05307037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"03","first_page":"387","last_page":"410"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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":0.9991999864578247,"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":0.8151748776435852},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6575218439102173},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6381682753562927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6216822266578674},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5823172926902771},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5720269680023193},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5575907826423645},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5258610248565674},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.475288987159729},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.44665995240211487},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4440922141075134},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4414108097553253},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4220607280731201},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4127490520477295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3871833384037018},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26112812757492065},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19574975967407227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1141141951084137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151748776435852},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6575218439102173},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6381682753562927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6216822266578674},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5823172926902771},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5720269680023193},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5575907826423645},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5258610248565674},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.475288987159729},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.44665995240211487},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4440922141075134},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4414108097553253},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4220607280731201},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4127490520477295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3871833384037018},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26112812757492065},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19574975967407227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1141141951084137},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x23620027","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s1793351x23620027","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"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":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1989231886","https://openalex.org/W2026311529","https://openalex.org/W2123402141","https://openalex.org/W2767364290","https://openalex.org/W2977457315","https://openalex.org/W3025191362","https://openalex.org/W3047682048","https://openalex.org/W3137905681","https://openalex.org/W3139312194","https://openalex.org/W3160041564","https://openalex.org/W3199435047","https://openalex.org/W3209830970","https://openalex.org/W4232395981","https://openalex.org/W4240909545"],"related_works":["https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W3209723314","https://openalex.org/W2952736415","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W2962677013"],"abstract_inverted_index":{"A":[0,269],"considerable":[1],"amount":[2],"of":[3,11,46,55,97,119,179,185,196,245],"research":[4],"is":[5,104],"concerned":[6],"with":[7,74],"the":[8,53,95,110,127,164,171,183,203,225,242,257],"challenging":[9,217],"task":[10],"estimating":[12],"three-dimensional":[13],"(3D)":[14],"pose":[15],"and":[16,38,162,199,232],"size":[17],"for":[18,57,107,216,249,260],"multi-object":[19],"indoor":[20],"scene":[21],"configurations.":[22],"Many":[23],"existing":[24],"models":[25,37,120],"rely":[26],"on":[27,86,123,139,191,228],"a":[28,43,75,177,192,251],"priori":[29],"known":[30],"object":[31,47,262],"models,":[32],"such":[33,250],"as":[34],"3D":[35,78,218,261],"CAD":[36],"are":[39,213],"therefore":[40],"limited":[41],"to":[42,126,142,202],"predefined":[44],"set":[45,195],"categories.":[48],"This":[49,69],"closed-set":[50],"constraint":[51],"limits":[52],"range":[54],"applications":[56],"robots":[58],"interacting":[59],"in":[60,236],"dynamic":[61],"environments":[62],"where":[63],"previously":[64],"unseen":[65],"objects":[66,190],"may":[67],"appear.":[68],"paper":[70],"addresses":[71],"this":[72,108,132],"problem":[73],"highly":[76],"generic":[77],"bounding":[79],"box":[80],"detection":[81,219],"method":[82],"that":[83,210],"relies":[84],"entirely":[85],"geometric":[87],"cues":[88],"obtained":[89],"from":[90,224],"depth":[91,102,137],"data":[92,125,141,194],"percepts.":[93],"While":[94],"generation":[96],"synthetic":[98,101,124,140],"data,":[99],"e.g.":[100],"maps,":[103],"commonly":[105,172],"used":[106,173,259],"task,":[109],"well-known":[111],"synth-to-real":[112],"gap":[113],"often":[114],"emerges,":[115],"which":[116,159],"prohibits":[117],"transition":[118],"trained":[121,227],"solely":[122],"real":[128],"world.":[129],"To":[130],"ameliorate":[131],"problem,":[133],"we":[134,181,240,255],"use":[135],"stereo":[136],"computation":[138],"obtain":[143],"pseudo-realistic":[144],"disparity":[145,229],"maps.":[146],"We":[147,207],"then":[148],"propose":[149],"an":[150,237],"intermediate":[151],"representation,":[152],"namely":[153],"disparity-scaled":[154,233],"surface":[155],"normal":[156],"(SN)":[157],"images,":[158],"encodes":[160],"geometry":[161],"at":[163],"same":[165],"time":[166],"preserves":[167],"depth/scale":[168],"information":[169],"unlike":[170],"standard":[174,211],"SNs.":[175,234],"In":[176],"series":[178],"experiments,":[180],"demonstrate":[182],"usefulness":[184],"our":[186,272],"approach,":[187],"detecting":[188],"everyday":[189],"captured":[193],"tabletop":[197],"scenes,":[198],"compare":[200],"it":[201],"popular":[204],"PoseCNN":[205],"model.":[206],"quantitatively":[208],"show":[209],"SNs":[212,231],"less":[214],"adequate":[215],"tasks":[220],"by":[221],"comparing":[222],"predictions":[223],"model":[226],"alone,":[230],"Additionally,":[235],"ablation":[238],"study":[239],"investigate":[241],"minimal":[243],"number":[244],"training":[246],"samples":[247],"required":[248],"learning":[252],"task.":[253],"Lastly,":[254],"make":[256],"tool":[258],"annotation":[263],"publicly":[264],"available":[265],"at:":[266,277],"https://preview.tinyurl.com/3ycn8v5k":[267],".":[268,279],"video":[270],"showcasing":[271],"results":[273],"can":[274],"be":[275],"found":[276],"https://preview.tinyurl.com/dzdzabek":[278]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
