{"id":"https://openalex.org/W4414971070","doi":"https://doi.org/10.1109/iccv51701.2025.00545","title":"Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-Level 6D Pose Estimation","display_name":"Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-Level 6D Pose Estimation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414971070","doi":"https://doi.org/10.1109/iccv51701.2025.00545"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00545","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/2510.04125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100426775","display_name":"Seunghyun Lee","orcid":"https://orcid.org/0000-0001-7139-1764"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Seunghyun Lee","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100653784","display_name":"Tae\u2010Kyun Kim","orcid":"https://orcid.org/0000-0002-7587-6053"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Tae-Kyun Kim","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"5757","last_page":"5768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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":0.9739999771118164,"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":0.970300018787384,"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/pose","display_name":"Pose","score":0.8238000273704529},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.691100001335144},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5105000138282776},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.483599990606308},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.46950000524520874},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4447000026702881},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.41780000925064087}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8238000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7376000285148621},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.691100001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571000218391418},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5149000287055969},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.46950000524520874},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C156140930","wikidata":"https://www.wikidata.org/wiki/Q860417","display_name":"Bilateral filter","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00545","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:2510.04125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04125","pdf_url":"https://arxiv.org/pdf/2510.04125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2510.04125","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.04125","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2510.04125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04125","pdf_url":"https://arxiv.org/pdf/2510.04125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G5339338047","display_name":null,"funder_award_id":"RS-2025-25443318","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Latest":[0],"diffusion":[1,38,101],"models":[2],"have":[3],"shown":[4],"promising":[5],"results":[6],"in":[7,41,185],"category-level":[8],"6D":[9],"object":[10],"pose":[11,17,52,58,86,151],"estimation":[12],"by":[13,72],"modeling":[14],"the":[15,37,77,81,84,92,95,99,121,128,131,168],"conditional":[16],"distribution":[18],"with":[19,36,83,178],"depth":[20],"image":[21],"input.":[22],"The":[23,135],"existing":[24],"methods,":[25],"however,":[26],"suffer":[27],"from":[28],"slow":[29],"convergence":[30,106],"during":[31],"training,":[32],"learning":[33],"its":[34],"encoder":[35,82],"denoising":[39,100,146],"network":[40,48],"end-to-end":[42],"fashion,":[43],"and":[44,89,98,164,188],"require":[45],"an":[46],"additional":[47,132],"that":[49,68,167],"evaluates":[50],"sampled":[51],"hypotheses":[53],"to":[54],"filter":[55],"out":[56],"low-quality":[57],"candidates.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"a":[65],"novel":[66],"pipeline":[67],"tackles":[69],"these":[70],"limitations":[71],"two":[73],"key":[74],"components.":[75],"First,":[76],"proposed":[78,119,169],"method":[79],"pretrains":[80],"direct":[85],"regression":[87,96],"head,":[88,102],"jointly":[90],"learns":[91],"networks":[93],"via":[94,114],"head":[97],"significantly":[103],"accelerating":[104],"training":[105,187],"while":[107,148,181],"achieving":[108],"higher":[109],"accuracy.":[110],"Second,":[111],"sampling":[112,136],"guidance":[113,137],"time-dependent":[115],"score":[116],"scaling":[117],"is":[118,124],"s.t.":[120],"exploration-exploitation":[122],"trade-off":[123],"effectively":[125],"taken,":[126],"eliminating":[127],"need":[129],"for":[130],"evaluation":[133],"network.":[134],"maintains":[138],"multi-modal":[139],"characteristics":[140],"of":[141],"symmetric":[142],"objects":[143],"at":[144,153],"early":[145],"steps":[147],"ensuring":[149],"high-quality":[150],"generation":[152],"final":[154],"steps.":[155],"Extensive":[156],"experiments":[157],"on":[158],"multiple":[159],"benchmarks":[160],"including":[161],"REAL275,":[162],"HouseCat6D,":[163],"ROPE,":[165],"demonstrate":[166],"method,":[170],"simple":[171],"yet":[172],"effective,":[173],"achieves":[174],"state-of-the-art":[175],"accuracies":[176],"even":[177],"single-pose":[179],"inference,":[180],"being":[182],"more":[183],"efficient":[184],"both":[186],"inference.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-09T00:00:00"}