{"id":"https://openalex.org/W7162496274","doi":"https://doi.org/10.1109/3dv69130.2026.00017","title":"VideoLifter: Lifting Videos to 3D with Fast and Efficient Hierarchical Stereo Alignment","display_name":"VideoLifter: Lifting Videos to 3D with Fast and Efficient Hierarchical Stereo Alignment","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7162496274","doi":"https://doi.org/10.1109/3dv69130.2026.00017"},"language":null,"primary_location":{"id":"doi:10.1109/3dv69130.2026.00017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","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/A5080151252","display_name":"Wenyan Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenyan Cong","raw_affiliation_strings":["UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137108365","display_name":"Hanqing Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanqing Zhu","raw_affiliation_strings":["UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031454609","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0002-7144-6865"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wang","raw_affiliation_strings":["UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026142235","display_name":"Jinyu Lei","orcid":"https://orcid.org/0009-0008-1108-7953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahui Lei","raw_affiliation_strings":["UPenn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UPenn","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110965555","display_name":"Colton Stearns","orcid":"https://orcid.org/0000-0002-3297-2870"},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colton Stearns","raw_affiliation_strings":["Stanford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford","institution_ids":["https://openalex.org/I4210137306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137122155","display_name":"Yuanhao Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanhao Cai","raw_affiliation_strings":["JHU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JHU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137151412","display_name":"Dilin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dilin Wang","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137102614","display_name":"Rakesh Ranjan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rakesh Ranjan","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055620900","display_name":"Matt Feiszli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matt Feiszli","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137140607","display_name":"Leonidas Guibas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonidas Guibas","raw_affiliation_strings":["Stanford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford","institution_ids":["https://openalex.org/I4210137306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137102867","display_name":"Zhangyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangyang Wang","raw_affiliation_strings":["UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137152721","display_name":"Weiyao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiyao Wang","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137106066","display_name":"Zhiwen Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwen Fan","raw_affiliation_strings":["UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"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":0.85222402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.3012999892234802,"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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.3012999892234802,"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/T11448","display_name":"Face recognition and analysis","score":0.14630000293254852,"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/T10860","display_name":"Speech and Audio Processing","score":0.1356000006198883,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/stereopsis","display_name":"Stereopsis","score":0.31279999017715454},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3025999963283539},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2976999878883362},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2603999972343445},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2467000037431717}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6480000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050000190734863},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2467000037431717},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.23409999907016754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/3dv69130.2026.00017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1929856797","https://openalex.org/W1980635903","https://openalex.org/W2008706659","https://openalex.org/W2021851106","https://openalex.org/W2084613528","https://openalex.org/W2085261163","https://openalex.org/W2108134361","https://openalex.org/W2133665775","https://openalex.org/W2151103935","https://openalex.org/W2158014263","https://openalex.org/W2166090423","https://openalex.org/W2471962767","https://openalex.org/W2738551266","https://openalex.org/W2962785568","https://openalex.org/W2964288609","https://openalex.org/W3166285241","https://openalex.org/W3194532238","https://openalex.org/W3196466825","https://openalex.org/W4200150166","https://openalex.org/W4214564845","https://openalex.org/W4214579621","https://openalex.org/W4312706422","https://openalex.org/W4385318467","https://openalex.org/W4386066457","https://openalex.org/W4386072012","https://openalex.org/W4386076472","https://openalex.org/W4390872820","https://openalex.org/W4395481595","https://openalex.org/W4396786671","https://openalex.org/W4402775411","https://openalex.org/W4404002617","https://openalex.org/W4404769769","https://openalex.org/W4407499437","https://openalex.org/W4413146238","https://openalex.org/W4413155739","https://openalex.org/W4414197737"],"related_works":[],"abstract_inverted_index":{"Efficiently":[0],"reconstructing":[1],"3D":[2,77,87],"scenes":[3],"from":[4],"monocular":[5],"video":[6],"remains":[7],"a":[8,53,59,63,100],"core":[9],"challenge":[10],"in":[11,17],"computer":[12],"vision,":[13],"vital":[14],"for":[15,85,109],"applications":[16],"virtual":[18],"reality,":[19],"robotics,":[20],"and":[21,38,70,94,118],"scene":[22],"understanding.":[23],"Recently,":[24],"frame-by-frame":[25],"progressive":[26],"reconstruction":[27,136],"without":[28],"camera":[29],"poses":[30],"is":[31],"commonly":[32],"adopted,":[33],"incurring":[34],"high":[35],"computational":[36],"overhead":[37],"compounding":[39],"errors":[40],"when":[41],"scaling":[42],"to":[43,79,122],"longer":[44],"videos.":[45],"To":[46],"overcome":[47],"these":[48],"issues,":[49],"we":[50],"introduce":[51],"VideoLifter,":[52],"novel":[54],"video-to-3D":[55],"pipeline":[56],"that":[57],"leverages":[58,75],"local-to-global":[60],"strategy":[61],"on":[62],"fragment":[64],"basis,":[65],"achieving":[66,146],"both":[67],"extreme":[68],"efficiency":[69],"SOTA":[71,151],"quality.":[72],"Locally,":[73],"VideoLifter":[74],"learnable":[76],"priors":[78],"register":[80],"fragments,":[81],"extracting":[82],"essential":[83],"information":[84],"subsequent":[86,119],"Gaussian":[88,115],"initialization":[89],"with":[90,105,114],"enforced":[91],"inter-fragment":[92,110],"consistency":[93,125],"optimized":[95],"efficiency.":[96],"Globally,":[97],"it":[98],"employs":[99],"tree-based":[101],"hierarchical":[102],"merging":[103,113],"method":[104],"key":[106],"frame":[107],"guidance":[108],"alignment,":[111],"pairwise":[112],"point":[116],"pruning,":[117],"joint":[120],"optimization":[121],"ensure":[123],"global":[124],"while":[126,145],"efficiently":[127],"mitigating":[128],"cumulative":[129],"errors.":[130],"This":[131],"approach":[132],"significantly":[133],"accelerates":[134],"the":[135],"process,":[137],"reducing":[138],"training":[139],"time":[140],"by":[141],"over":[142],"82":[143],"%":[144],"better":[147],"visual":[148],"quality":[149],"than":[150],"methods.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}