{"id":"https://openalex.org/W4413947050","doi":"https://doi.org/10.1109/icra55743.2025.11127837","title":"MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model","display_name":"MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413947050","doi":"https://doi.org/10.1109/icra55743.2025.11127837"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.lancs.ac.uk/id/eprint/235611/1/2504.10433v1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108049455","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0003-0604-8024"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039773171","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-1349-6135"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112361483","display_name":"Hui Yang","orcid":"https://orcid.org/0009-0005-2648-9566"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yang","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100911842","display_name":"Jin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zheng","raw_affiliation_strings":["Central South University,Changsha,China,410082"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University,Changsha,China,410082","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102677599","display_name":"Zichen Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zichen Geng","raw_affiliation_strings":["University of Western Australia,WA,Australia,6009"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia,WA,Australia,6009","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018551679","display_name":"Hossein Rahmani","orcid":"https://orcid.org/0000-0002-5709-0428"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hossein Rahmani","raw_affiliation_strings":["Lancaster University,United Kingdom,LA1 4YW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University,United Kingdom,LA1 4YW","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["University of Western Australia,WA,Australia,6009"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia,WA,Australia,6009","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9703,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76170543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8687","last_page":"8694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T14510","display_name":"Medical Imaging and Analysis","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.9829999804496765,"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":0.9728000164031982,"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":0.664617657661438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6548479795455933},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6461549997329712},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6201775670051575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6196749210357666},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5292360782623291},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4915364682674408},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4771025776863098}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.664617657661438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6548479795455933},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6461549997329712},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6201775670051575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6196749210357666},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5292360782623291},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4915364682674408},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4771025776863098},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra55743.2025.11127837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:235611","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/235611/1/2504.10433v1.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"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":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.lancs.ac.uk:235611","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/235611/1/2504.10433v1.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"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":"PeerReviewed"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1201409244","display_name":null,"funder_award_id":"62473141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3408348127","display_name":null,"funder_award_id":"U22A2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5069660017","display_name":null,"funder_award_id":"202306130074","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G7135151365","display_name":null,"funder_award_id":"2024JJ5098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413947050.pdf","grobid_xml":"https://content.openalex.org/works/W4413947050.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W2128019145","https://openalex.org/W2194775991","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963892972","https://openalex.org/W2964054038","https://openalex.org/W2972211064","https://openalex.org/W3034986117","https://openalex.org/W3094502228","https://openalex.org/W3107372911","https://openalex.org/W3107992529","https://openalex.org/W3113383835","https://openalex.org/W3151772196","https://openalex.org/W3163945288","https://openalex.org/W3177069133","https://openalex.org/W3179923621","https://openalex.org/W3190988267","https://openalex.org/W3193686508","https://openalex.org/W3196328566","https://openalex.org/W3199947443","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3214778407","https://openalex.org/W4224598146","https://openalex.org/W4226321491","https://openalex.org/W4226322645","https://openalex.org/W4280589974","https://openalex.org/W4283808280","https://openalex.org/W4285233964","https://openalex.org/W4312296985","https://openalex.org/W4312491686","https://openalex.org/W4312604533","https://openalex.org/W4312801317","https://openalex.org/W4312818087","https://openalex.org/W4312933868","https://openalex.org/W4313189197","https://openalex.org/W4320002827","https://openalex.org/W4321033239","https://openalex.org/W4384201319","https://openalex.org/W4386075656","https://openalex.org/W4386075813","https://openalex.org/W4386075917","https://openalex.org/W4390872210","https://openalex.org/W4390873470","https://openalex.org/W4391855168","https://openalex.org/W4392979363","https://openalex.org/W4400726600","https://openalex.org/W4401413628","https://openalex.org/W4401416926","https://openalex.org/W4402667888","https://openalex.org/W4402716094","https://openalex.org/W4402716422","https://openalex.org/W4402727359","https://openalex.org/W4402727742","https://openalex.org/W4402753636","https://openalex.org/W4405785669","https://openalex.org/W4408564950"],"related_works":["https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W3201205132","https://openalex.org/W2798721181","https://openalex.org/W4387967917","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4382141741","https://openalex.org/W2951583186","https://openalex.org/W4307623796"],"abstract_inverted_index":{"Object":[0],"pose":[1,55,86,148,168],"estimation":[2,169],"is":[3,61],"a":[4,28,49,100,107,141],"core":[5],"means":[6],"for":[7,74,82,174],"robots":[8],"to":[9,62,70,135,144],"understand":[10],"and":[11,103,124],"interact":[12],"with":[13,120,130],"their":[14],"environment.":[15],"For":[16],"this":[17],"task,":[18],"monocular":[19,51,97,164],"category-level":[20,52,165],"methods":[21,34],"are":[22],"attractive":[23],"as":[24],"they":[25],"require":[26],"only":[27],"single":[29],"RGB":[30],"camera.":[31],"However,":[32],"current":[33],"rely":[35],"on":[36,154],"shape":[37,75,175],"priors":[38,176],"or":[39,79,177],"CAD":[40,77,178],"models":[41,69,179],"of":[42,67,116],"the":[43,64,72,96,113,117,121,126,131,146,172],"intra-class":[44,83],"known":[45],"objects.":[46],"We":[47,88,110],"propose":[48],"diffusion-based":[50],"9D":[53,166],"object":[54,85,147,167],"generation":[56],"method,":[57],"MonoDiff9D.":[58,137],"Our":[59,183],"motivation":[60],"leverage":[63],"probabilistic":[65],"nature":[66],"diffusion":[68],"alleviate":[71],"need":[73,173],"priors,":[76],"models,":[78],"depth":[80,92],"sensors":[81],"unknown":[84],"estimation.":[87],"first":[89],"estimate":[90],"coarse":[91],"via":[93],"DINOv2":[94],"from":[95,149],"image":[98,123],"in":[99],"zero-shot":[101],"manner":[102],"convert":[104],"it":[105],"into":[106],"point":[108,118],"cloud.":[109],"then":[111],"fuse":[112],"global":[114],"features":[115,128],"cloud":[119],"input":[122],"use":[125],"fused":[127],"along":[129],"encoded":[132],"time":[133],"step":[134],"condition":[136],"Finally,":[138],"we":[139],"design":[140],"transformer-based":[142],"denoiser":[143],"recover":[145],"Gaussian":[150],"noise.":[151],"Extensive":[152],"experiments":[153],"two":[155],"popular":[156],"benchmark":[157],"datasets":[158],"show":[159],"that":[160],"MonoDiff9D":[161],"achieves":[162],"state-of-the-art":[163],"accuracy":[170],"without":[171],"at":[180,189],"any":[181],"stage.":[182],"code":[184],"will":[185],"be":[186],"made":[187],"public":[188],"https://github.com/CNJianLiu/MonoDiff9D.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}