{"id":"https://openalex.org/W4413146722","doi":"https://doi.org/10.1109/cvpr52734.2025.01632","title":"Lifting Motion to the 3D World via 2D Diffusion","display_name":"Lifting Motion to the 3D World via 2D Diffusion","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146722","doi":"https://doi.org/10.1109/cvpr52734.2025.01632"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5009234134","display_name":"Jiaman Li","orcid":"https://orcid.org/0000-0002-1261-3248"},"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":"Jiaman Li","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/A5028366509","display_name":"C. Karen Liu","orcid":"https://orcid.org/0009-0003-5783-7864"},"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":"C. Karen Liu","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/A5100621605","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0002-4176-343X"},"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":"Jiajun Wu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17518","last_page":"17528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9578999876976013,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9578999876976013,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9569000005722046,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.954200029373169,"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/computer-science","display_name":"Computer science","score":0.5750380754470825},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5533678531646729},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.542014479637146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34355658292770386},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12380185723304749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5750380754470825},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5533678531646729},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.542014479637146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34355658292770386},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12380185723304749},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308507","display_name":"Stanford University","ror":"https://ror.org/00f54p054"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Estimating":[0],"3D":[1,21,46,68,112,130,144],"motion":[2,31,92],"from":[3],"2D":[4,82,91,99],"observations":[5],"is":[6,49],"a":[7,62,105],"longstanding":[8],"research":[9],"challenge.":[10],"Prior":[11],"work":[12,135],"typically":[13],"requires":[14],"training":[15],"on":[16,136],"datasets":[17],"containing":[18],"ground":[19,47],"truth":[20,48],"motions,":[22],"limiting":[23],"their":[24],"applicability":[25],"to":[26,39,65,95],"activities":[27],"well-represented":[28],"in":[29,76,108],"existing":[30],"capture":[32],"data.":[33],"This":[34],"dependency":[35],"particularly":[36],"hinders":[37],"generalization":[38],"out-of-distribution":[40],"scenarios":[41],"or":[42,56],"subjects":[43],"where":[44],"collecting":[45],"challenging,":[50],"such":[51],"as":[52],"complex":[53],"athletic":[54],"movements":[55],"animal":[57,125],"motion.":[58,113],"We":[59],"introduce":[60],"MVLift,":[61],"novel":[63],"approach":[64],"predict":[66],"global":[67,111],"motion\u2014including":[69],"both":[70],"joint":[71],"rotations":[72],"and":[73,124],"root":[74],"trajectories":[75],"the":[77],"world":[78],"coordinate":[79],"system\u2014using":[80],"only":[81],"pose":[83,100],"sequences":[84,101],"for":[85],"training.":[86],"Our":[87],"multi-stage":[88],"framework":[89],"leverages":[90],"diffusion":[93],"models":[94],"progressively":[96],"generate":[97],"consistent":[98],"across":[102,116],"multiple":[103],"views,":[104],"key":[106],"step":[107],"recovering":[109],"accurate":[110],"MVLift":[114],"generalizes":[115],"various":[117],"domains,":[118],"including":[119,139],"human":[120],"poses,":[121],"human-object":[122],"interactions,":[123],"poses.":[126],"Despite":[127],"not":[128],"requiring":[129],"supervision,":[131],"it":[132],"outperforms":[133],"prior":[134],"five":[137],"datasets,":[138],"those":[140],"methods":[141],"that":[142],"require":[143],"supervision.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}