{"id":"https://openalex.org/W4416552489","doi":"https://doi.org/10.1109/iccv51701.2025.00961","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","display_name":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416552489","doi":"https://doi.org/10.1109/iccv51701.2025.00961","pmid":"https://pubmed.ncbi.nlm.nih.gov/42079508"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00961","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01126","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085976775","display_name":"Chaitanya Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitanya Patel","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006451525","display_name":"Hiroki Nakamura","orcid":"https://orcid.org/0000-0002-2356-8470"},"institutions":[{"id":"https://openalex.org/I1283155146","display_name":"Panasonic (Japan)","ror":"https://ror.org/011tm7n37","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283155146"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Nakamura","raw_affiliation_strings":["Panasonic Holdings Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Panasonic Holdings Corporation","institution_ids":["https://openalex.org/I1283155146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086962252","display_name":"Yuta Kyuragi","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuta Kyuragi","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006012153","display_name":"Kazuki Kozuka","orcid":null},"institutions":[{"id":"https://openalex.org/I1283155146","display_name":"Panasonic (Japan)","ror":"https://ror.org/011tm7n37","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283155146"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Kozuka","raw_affiliation_strings":["Panasonic Holdings Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Panasonic Holdings Corporation","institution_ids":["https://openalex.org/I1283155146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018518655","display_name":"Juan Carlos Niebles","orcid":"https://orcid.org/0000-0001-8225-9793"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Carlos Niebles","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015355317","display_name":"Ehsan Adeli","orcid":"https://orcid.org/0000-0002-0579-7763"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ehsan Adeli","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"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":"2025","issue":null,"first_page":"10318","last_page":"10329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.40459999442100525,"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/T12290","display_name":"Human Motion and Animation","score":0.40459999442100525,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.22310000658035278,"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":0.10289999842643738,"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/motion","display_name":"Motion (physics)","score":0.7516000270843506},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.541100025177002},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5232999920845032},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4941999912261963},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/motion-field","display_name":"Motion field","score":0.4690000116825104},{"id":"https://openalex.org/keywords/structure-from-motion","display_name":"Structure from motion","score":0.4090999960899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631000280380249},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7516000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7032999992370605},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6721000075340271},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4941999912261963},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47029998898506165},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.4690000116825104},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C48575856","wikidata":"https://www.wikidata.org/wiki/Q852504","display_name":"Motion perception","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iccv51701.2025.00961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00961","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":"pmid:42079508","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42079508","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Computer Vision","raw_type":null},{"id":"pmh:oai:arXiv.org:2508.01126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01126","pdf_url":"https://arxiv.org/pdf/2508.01126","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":"pmh:oai:pubmedcentral.nih.gov:13132493","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13132493/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Comput Vis","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2508.01126","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01126","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:2508.01126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01126","pdf_url":"https://arxiv.org/pdf/2508.01126","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/G2919293100","display_name":null,"funder_award_id":"R01 AG089169","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"}],"funders":[{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Egocentric":[0,75,79],"human":[1],"motion":[2,42,91,105,112,125,173,181,189,210],"generation":[3,129],"and":[4,20,28,63,78,128,183,212],"forecasting":[5],"with":[6,44,108,170],"scene-context":[7],"is":[8,184],"crucial":[9],"for":[10,89,115,208,216],"enhancing":[11],"AR/VR":[12],"experiences,":[13],"improving":[14],"human-robot":[15],"interaction,":[16],"advancing":[17],"assistive":[18],"technologies,":[19],"enabling":[21],"adaptive":[22],"healthcare":[23],"solutions":[24],"by":[25],"accurately":[26],"predicting":[27],"simulating":[29],"movement":[30],"from":[31,130,167,190],"a":[32,102,109,135,163,191,205],"first-person":[33,87,131],"perspective.":[34],"However,":[35],"existing":[36],"methods":[37],"primarily":[38],"focus":[39],"on":[40,95],"third-person":[41],"synthesis":[43,92],"structured":[45],"3D":[46,97,155,172],"scene":[47,67,143,150],"contexts,":[48],"limiting":[49],"their":[50],"effectiveness":[51,199],"in":[52,134,179],"real-world":[53],"egocentric":[54,116,124,180,193,209,217],"settings":[55],"where":[56],"limited":[57],"field":[58],"of":[59,200],"view,":[60],"frequent":[61],"occlusions,":[62],"dynamic":[64],"cameras":[65],"hinder":[66],"perception.":[68],"To":[69,157],"bridge":[70],"this":[71],"gap,":[72],"we":[73,160],"introduce":[74,161],"Motion":[76,80],"Generation":[77],"Forecasting,":[81],"two":[82],"novel":[83,110],"tasks":[84],"that":[85,141],"utilize":[86],"images":[88],"scene-aware":[90],"without":[93],"relying":[94],"explicit":[96],"scene.":[98],"We":[99],"propose":[100],"UniEgoMotion,":[101],"unified":[103,136,202],"conditional":[104],"diffusion":[106],"model":[107,146],"head-centric":[111],"representation":[113],"tailored":[114],"devices.":[117],"UniEgoMotion's":[118],"simple":[119],"yet":[120],"effective":[121],"design":[122],"supports":[123],"reconstruction,":[126],"forecasting,":[127],"visual":[132],"inputs":[133],"framework.":[137],"Unlike":[138],"previous":[139],"works":[140],"overlook":[142],"semantics,":[144],"our":[145,201],"effectively":[147],"extracts":[148],"image-based":[149],"context":[151],"to":[152,187],"infer":[153],"plausible":[154],"motion.":[156],"facilitate":[158],"training,":[159],"EE4D-Motion,":[162],"large-scale":[164],"dataset":[165],"derived":[166],"EgoExo4D,":[168],"augmented":[169],"pseudo-ground-truth":[171],"annotations.":[174],"UniEgoMotion":[175],"achieves":[176],"state-of-the-art":[177],"performance":[178],"reconstruction":[182],"the":[185,198],"first":[186],"generate":[188],"single":[192],"image.":[194],"Extensive":[195],"evaluations":[196],"demonstrate":[197],"framework,":[203],"setting":[204],"new":[206,214],"benchmark":[207],"modeling":[211],"unlocking":[213],"possibilities":[215],"applications.":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}