{"id":"https://openalex.org/W4415967370","doi":"https://doi.org/10.1109/iccv51701.2025.00851","title":"RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation","display_name":"RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415967370","doi":"https://doi.org/10.1109/iccv51701.2025.00851"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.00851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.18521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100588512","display_name":"Junwen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Junwen Huang","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081751860","display_name":"Shishir Reddy Vutukur","orcid":"https://orcid.org/0000-0002-4406-8491"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shishir Reddy Vutukur","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110430490","display_name":"Peter Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter KT Yu","raw_affiliation_strings":["XYZ Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"XYZ Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896448","display_name":"Nassir Navab","orcid":"https://orcid.org/0000-0002-6032-5611"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nassir Navab","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045382199","display_name":"Slobodan Ili\u0107","orcid":"https://orcid.org/0000-0002-3413-1936"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Slobodan Ilic","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067135033","display_name":"Benjamin Busam","orcid":"https://orcid.org/0000-0002-0620-5774"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Busam","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.42313501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9700","last_page":"9710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8251000046730042,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8251000046730042,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.033399999141693115,"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":0.02759999968111515,"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/pose","display_name":"Pose","score":0.8664000034332275},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.6341999769210815},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5206000208854675},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.5159000158309937},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.423799991607666},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.41830000281333923}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8664000034332275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8133999705314636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472000122070312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.741100013256073},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.6341999769210815},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5230000019073486},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5206000208854675},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.5159000158309937},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.41830000281333923},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.41440001130104065},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3334999978542328},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.18521","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.18521","pdf_url":"https://arxiv.org/pdf/2510.18521","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.18521","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.18521","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.18521","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.18521","pdf_url":"https://arxiv.org/pdf/2510.18521","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Typical":[0],"template-based":[1,39],"object":[2,40,97,105,164],"pose":[3,7,32,41,73,128,165],"pipelines":[4],"estimate":[5],"the":[6,10,18,25,49,122,143],"by":[8,67,107],"retrieving":[9],"closest":[11],"matching":[12],"template":[13,27,55,137],"and":[14,103],"aligning":[15],"it":[16],"with":[17,61,89],"observed":[19],"image.":[20,65],"However,":[21],"failure":[22],"to":[23,30,59,112,124,159],"retrieve":[24],"correct":[26],"often":[28],"leads":[29],"inaccurate":[31],"predictions.":[33],"To":[34],"address":[35],"this,":[36],"we":[37,75],"reformulate":[38],"estimation":[42,111],"as":[43],"a":[44,62,80,86,90],"ray":[45],"alignment":[46],"problem,":[47],"where":[48],"viewing":[50],"directions":[51],"from":[52,121],"multiple":[53,149],"posed":[54,93],"images":[56],"are":[57],"learned":[58],"align":[60],"non-posed":[63],"query":[64,87,127],"Inspired":[66],"recent":[68],"progress":[69],"in":[70,162],"diffusion-based":[71],"camera":[72,101],"estimation,":[74],"embed":[76],"this":[77],"formulation":[78],"into":[79],"diffusion":[81],"transformer":[82],"architecture":[83],"that":[84],"aligns":[85],"image":[88],"set":[91],"of":[92,155],"templates.":[94],"We":[95],"reparameterize":[96],"rotation":[98],"using":[99],"object-centered":[100],"rays":[102],"model":[104,117],"translation":[106,110,114],"extending":[108],"scale-invariant":[109],"dense":[113],"offsets.":[115],"Our":[116],"leverages":[118],"geometric":[119],"priors":[120],"templates":[123],"guide":[125],"accurate":[126],"inference.":[129],"A":[130],"coarse-to-fine":[131],"training":[132],"strategy":[133],"based":[134],"on":[135],"narrowed":[136],"sampling":[138],"improves":[139],"performance":[140],"without":[141],"modifying":[142],"network":[144],"architecture.":[145],"Extensive":[146],"experiments":[147],"across":[148],"benchmark":[150],"datasets":[151],"show":[152],"competitive":[153],"results":[154],"our":[156],"method":[157],"compared":[158],"state-of-the-art":[160],"approaches":[161],"unseen":[163],"estimation.":[166]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-24T00:00:00"}