{"id":"https://openalex.org/W4413147574","doi":"https://doi.org/10.1109/cvpr52734.2025.00194","title":"You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale","display_name":"You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147574","doi":"https://doi.org/10.1109/cvpr52734.2025.00194"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00194","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":"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":"https://openalex.org/A5034970671","display_name":"Baorui Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baorui Ma","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052845830","display_name":"Huachen Gao","orcid":"https://orcid.org/0000-0002-5981-8566"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huachen Gao","raw_affiliation_strings":["Westlake University,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University,Zhejiang,China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070145690","display_name":"Haoge Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoge Deng","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029541865","display_name":"Zhengxiong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxiong Luo","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111925815","display_name":"Tiejun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Huang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018805700","display_name":"Lulu Tang","orcid":"https://orcid.org/0000-0003-0612-9780"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lulu Tang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100653846","display_name":"Xinlong Wang","orcid":"https://orcid.org/0000-0002-8137-1692"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlong Wang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.0541,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99623917,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2016","last_page":"2029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6871215105056763},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5189304351806641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44675374031066895},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33687731623649597},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3269352912902832},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0734231173992157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871215105056763},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5189304351806641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44675374031066895},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33687731623649597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3269352912902832},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0734231173992157},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00194","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"3D":[1,8,15,25,53,60,135,141,192,204,243,252,257],"generation":[2,193,233],"models":[3,237],"typically":[4],"rely":[5],"on":[6,47,211,221,239],"limited-scale":[7],"\u2018gold-labels\u2019":[9],"or":[10,143],"2D":[11],"diffusion":[12,44],"priors":[13,26,136],"for":[14,51,152,162,202],"content":[16],"creation.":[17,54],"However,":[18],"their":[19],"performance":[20],"is":[21,147,155],"upper-bounded":[22],"by":[23,62,177,195],"constrained":[24,242],"due":[27],"to":[28,58,181,264],"the":[29,65,69,90,160,182],"lack":[30],"of":[31,120],"scalable":[32,225],"learning":[33,133],"paradigms.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,86,165,187],"present":[39],"See3D,":[40,219],"a":[41,94,114,171,189,199],"visual-conditional":[42,191],"multi-view":[43,103,121],"model":[45,56,247],"trained":[46,220,238],"large-scale":[48,118],"Internet":[49],"videos":[50,138,154],"open-world":[52,232],"The":[55],"aims":[57],"Get":[59],"knowledge":[61],"solely":[63],"Seeing":[64],"visual":[66,174,209],"contents":[67],"from":[68,108,128,137],"vast":[70],"and":[71,105,149,208,213,224,231,241],"rapidly":[72],"growing":[73],"video":[74,130,184,226],"data":[75,92,96],"\u2014":[76],"You":[77,80],"See":[78],"it,":[79],"Got":[81],"it.":[82],"To":[83,158],"achieve":[84],"this,":[85],"first":[87],"scale":[88],"up":[89],"training":[91],"using":[93],"proposed":[95],"curation":[97],"pipeline":[98,201],"that":[99,218],"automatically":[100],"filters":[101],"out":[102],"inconsistencies":[104],"insufficient":[106],"observations":[107],"source":[109],"videos.":[110],"This":[111],"results":[112],"in":[113],"high-quality,":[115],"richly":[116],"diverse,":[117],"dataset":[119],"images,":[122],"termed":[123],"WebVi3D,":[124],"containing":[125],"320M":[126],"frames":[127],"16M":[129],"clips.":[131],"Nevertheless,":[132],"generic":[134],"without":[139,259],"explicit":[140],"geometry":[142],"camera":[144],"pose":[145,163],"annotations":[146],"nontrivial,":[148],"annotating":[150],"poses":[151],"web-scale":[153],"prohibitively":[156],"expensive.":[157],"eliminate":[159],"need":[161],"conditions,":[164],"introduce":[166,188],"an":[167],"innovative":[168],"visual-condition":[169],"-":[170],"purely":[172],"2D-inductive":[173],"signal":[175],"generated":[176],"adding":[178],"time-dependent":[179],"noise":[180],"masked":[183],"data.":[185],"Finally,":[186],"novel":[190],"framework":[194],"integrating":[196],"See3D":[197],"into":[198],"warping-based":[200],"high-fidelity":[203],"generation.":[205],"Our":[206],"numerical":[207],"comparisons":[210],"single":[212],"sparse":[214],"reconstruction":[215],"benchmarks":[216],"show":[217],"cost-":[222],"effective":[223],"data,":[227],"achieves":[228],"notable":[229],"zero-shot":[230],"capabilities,":[234],"markedly":[235],"outperforming":[236],"costly":[240],"datasets.":[244],"Additionally,":[245],"our":[246,265],"naturally":[248],"supports":[249],"other":[250],"image-conditioned":[251],"creation":[253],"tasks,":[254],"such":[255],"as":[256],"editing,":[258],"further":[260],"fine-tuning.":[261],"Please":[262],"refer":[263],"project":[266],"page":[267],"at:":[268],"https://vision.baai.ac.cn/see3d.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}