{"id":"https://openalex.org/W7160256721","doi":"https://doi.org/10.1109/wacv61042.2026.00746","title":"KMOPS: Keypoint-Driven Method for Multi-Object Pose and Metric Size Estimation from Stereo Images","display_name":"KMOPS: Keypoint-Driven Method for Multi-Object Pose and Metric Size Estimation from Stereo Images","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160256721","doi":"https://doi.org/10.1109/wacv61042.2026.00746"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5110067041","display_name":"Yongkun Wu","orcid":"https://orcid.org/0009-0009-9002-7453"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying-Kun Wu","raw_affiliation_strings":["University of Minnesota,Twin Cities"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota,Twin Cities","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135356948","display_name":"Yi Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Shen","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112985472","display_name":"Tzuhsuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tzuhsuan Huang","raw_affiliation_strings":["Research Center for Information Technology Innovation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059653155","display_name":"I-Sheng Fang","orcid":"https://orcid.org/0009-0001-8347-5938"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Sheng Fang","raw_affiliation_strings":["Research Center for Information Technology Innovation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135357938","display_name":"Jun-Cheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Cheng Chen","raw_affiliation_strings":["Research Center for Information Technology Innovation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation","institution_ids":["https://openalex.org/I29955533"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68351377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7730","last_page":"7739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.652899980545044,"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":0.652899980545044,"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":0.09610000252723694,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.05249999836087227,"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/metric","display_name":"Metric (unit)","score":0.5361999869346619},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3409999907016754},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.3276999890804291},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.29840001463890076},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28929999470710754}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6859999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6807000041007996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555400013923645},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32120001316070557},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2049981393","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2600447016","https://openalex.org/W2963188159","https://openalex.org/W2963351448","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2989604896","https://openalex.org/W3035235920","https://openalex.org/W3096609285","https://openalex.org/W3107992529","https://openalex.org/W3176584633","https://openalex.org/W3177069133","https://openalex.org/W3199947443","https://openalex.org/W3202305750","https://openalex.org/W3202459445","https://openalex.org/W3209571296","https://openalex.org/W3215100485","https://openalex.org/W4225793049","https://openalex.org/W4226322645","https://openalex.org/W4292787291","https://openalex.org/W4312801317","https://openalex.org/W4312894406","https://openalex.org/W4383109669","https://openalex.org/W4386075853","https://openalex.org/W4390871854","https://openalex.org/W4391630742","https://openalex.org/W4402754006","https://openalex.org/W4403889064","https://openalex.org/W4403941285","https://openalex.org/W4403941751","https://openalex.org/W4413147748","https://openalex.org/W7160083737","https://openalex.org/W7160103956"],"related_works":[],"abstract_inverted_index":{"The":[0],"six-degree-of-freedom":[1],"(6-DoF)":[2],"pose":[3],"and":[4,28,49,82,98,152,166],"metric":[5,50,88],"size":[6],"estimation":[7,52],"of":[8,71,76],"multiple":[9],"objects":[10,78],"from":[11,53],"RGB":[12],"images":[13],"alone":[14],"remains":[15],"a":[16,41,54,111,164],"challenging":[17,146],"task,":[18],"particularly":[19],"due":[20],"to":[21,86,106,134],"significant":[22],"variations":[23],"in":[24,31],"object":[25],"shape,":[26],"appearance,":[27],"frequent":[29],"occlusions":[30],"complex":[32],"scenes.":[33],"To":[34],"address":[35],"these":[36],"challenges,":[37],"we":[38,92,154],"introduce":[39],"KMOPS,":[40],"Keypoint-driven":[42],"method":[43,158],"tailored":[44],"specifically":[45],"for":[46,119],"Multi-Object":[47],"Pose":[48],"Size":[51],"single":[55],"calibrated":[56],"stereo":[57,62],"image":[58],"pair.":[59],"Leveraging":[60],"the":[61,68,72,77,102,107,117,136,145],"input,":[63],"our":[64,157],"approach":[65],"first":[66],"extracts":[67],"2D":[69],"keypoints":[70,105],"enclosing":[73],"bounding":[74],"boxes":[75],"across":[79],"both":[80],"views,":[81],"subsequently":[83],"triangulates":[84],"them":[85],"acquire":[87],"3D":[89,104,121,138],"positions.":[90],"Then,":[91],"obtain":[93],"each":[94],"object's":[95],"rotation,":[96],"translation,":[97],"dimensions":[99],"by":[100,131],"aligning":[101],"triangulated":[103],"canonical":[108],"ones":[109],"using":[110],"closed-form":[112],"solution.":[113],"Our":[114],"formulation":[115],"eliminates":[116],"need":[118],"predefined":[120],"search":[122],"spaces":[123],"or":[124],"volumetric":[125],"anchors,":[126],"which":[127],"are":[128],"often":[129],"required":[130],"other":[132],"methods":[133,162],"constrain":[135],"vast":[137],"solution":[139],"space.":[140],"With":[141],"extensive":[142],"experiments":[143],"on":[144],"dataset":[147],"Transparent":[148],"Object":[149],"Dataset":[150],"(TOD)":[151],"StereOBJ-1M,":[153],"show":[155],"that":[156],"outperforms":[159],"all":[160],"competing":[161],"with":[163],"simple":[165],"effective":[167],"architecture.":[168]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}