{"id":"https://openalex.org/W7084753318","doi":"https://doi.org/10.1109/lra.2025.3617274","title":"MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation","display_name":"MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7084753318","doi":"https://doi.org/10.1109/lra.2025.3617274"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3617274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3617274","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","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":null,"display_name":"Kangjian Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangjian Zhu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haobo Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haobo Jiang","raw_affiliation_strings":["ANGEL CorpLab and College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANGEL CorpLab and College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yigong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yigong Zhang","raw_affiliation_strings":["College of Computer Science, Nankai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianjun Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjun Qian","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jin Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["School of Intelligence Science and Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.62519936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.20730000734329224,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.20730000734329224,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12167","display_name":"Bacterial Identification and Susceptibility Testing","score":0.15559999644756317,"subfield":{"id":"https://openalex.org/subfields/1308","display_name":"Clinical Biochemistry"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.12110000103712082,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6887999773025513},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6854000091552734},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5996999740600586},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.54339998960495},{"id":"https://openalex.org/keywords/diffusion-process","display_name":"Diffusion process","score":0.5349000096321106},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4851999878883362},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47290000319480896}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7639999985694885},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6887999773025513},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6854000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6218000054359436},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6101999878883362},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5860999822616577},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.54339998960495},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.5349000096321106},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5217000246047974},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.35929998755455017},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C126795593","wikidata":"https://www.wikidata.org/wiki/Q7333813","display_name":"Rigid transformation","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.32190001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2025.3617274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3617274","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/217365","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/217365","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"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":{"We":[0],"propose":[1],"MonoSE(3)-Diffusion,":[2],"a":[3,16,27,36,56,128,176,187],"monocular":[4],"SE(3)":[5],"diffusion":[6,19,29,45,88,122],"framework":[7,22],"that":[8],"formulates":[9],"markerless,":[10],"image-based":[11],"robot":[12],"pose":[13,33,42,57,116,148],"estimation":[14],"as":[15],"conditional":[17],"denoising":[18,58,112,142],"process.":[20],"The":[21,44,150],"consists":[23],"of":[24,76,124,179],"two":[25,170],"processes:":[26],"visibility-constrained":[28],"process":[30,39,46,89,105,152],"for":[31,40,54],"diverse":[32,93],"augmentation":[34],"and":[35,92,114,173],"timestep-aware":[37,162],"reverse":[38,104,151],"progressive":[41],"refinement.":[43],"progressively":[47],"perturbs":[48],"ground-truth":[49],"poses":[50,109],"to":[51,79,144],"noisy":[52],"transformations":[53,70],"training":[55,94],"network.":[59],"Importantly,":[60],"we":[61],"integrate":[62],"visibility":[63],"constraints":[64],"into":[65],"the":[66,69,73,80,87,98,103,108,111,121,133,136,141,182,191],"process,":[67],"ensuring":[68],"remain":[71],"within":[72],"camera":[74],"field":[75],"view.":[77],"Compared":[78],"fixed-scale":[81],"perturbations":[82],"used":[83],"in":[84],"current":[85,125],"methods,":[86],"generates":[90],"in-view":[91],"poses,":[95],"thereby":[96],"improving":[97],"network":[99,113,143],"generalization":[100],"capability.":[101],"Furthermore,":[102],"iteratively":[106],"predicts":[107],"by":[110,118],"refines":[115],"estimates":[117],"sampling":[119],"from":[120,160],"posterior":[123],"timestep,":[126],"following":[127],"scheduled":[129],"coarse-to-fine":[130],"procedure.":[131],"Moreover,":[132],"timestep":[134],"indicates":[135],"transformation":[137],"scales,":[138],"which":[139],"guide":[140],"achieve":[145],"more":[146],"accurate":[147],"predictions.":[149],"demonstrates":[153,167],"higher":[154],"robustness":[155],"than":[156],"direct":[157],"prediction,":[158],"benefiting":[159],"its":[161],"refinement":[163],"scheme.":[164],"Our":[165],"approach":[166],"improvements":[168],"across":[169],"benchmarks":[171],"(DREAM":[172],"RoboKeyGen),":[174],"achieving":[175],"notable":[177],"AUC":[178],"66.75":[180],"on":[181],"most":[183],"challenging":[184],"dataset,":[185],"representing":[186],"32.3%":[188],"gain":[189],"over":[190],"<italic":[192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">state-of-the-art</i>.":[194]},"counts_by_year":[],"updated_date":"2026-06-29T08:53:18.405633","created_date":"2025-10-10T00:00:00"}