{"id":"https://openalex.org/W4414698849","doi":"https://doi.org/10.1109/iccv51701.2025.01819","title":"Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation","display_name":"Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414698849","doi":"https://doi.org/10.1109/iccv51701.2025.01819"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01819","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.09748","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100374637","display_name":"Lei Yu","orcid":"https://orcid.org/0000-0002-4575-0599"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lei","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009446815","display_name":"Bingde Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingde Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066624863","display_name":"Qingsong Xie","orcid":"https://orcid.org/0000-0001-6974-2019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingsong Xie","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015104631","display_name":"H. J. Lu","orcid":"https://orcid.org/0009-0006-4487-3294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102623510","display_name":"Zhijie Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Deng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":null,"issue":null,"first_page":"19567","last_page":"19576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9704999923706055,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9704999923706055,"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/T12290","display_name":"Human Motion and Animation","score":0.9681000113487244,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9627000093460083,"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/distillation","display_name":"Distillation","score":0.7269999980926514},{"id":"https://openalex.org/keywords/score","display_name":"Score","score":0.31700000166893005},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.29919999837875366},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.29170000553131104},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.28690001368522644},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.28540000319480896}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7269999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5382000207901001},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4138000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3693000078201294},{"id":"https://openalex.org/C65660741","wikidata":"https://www.wikidata.org/wiki/Q3952743","display_name":"Score","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01819","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":"pmh:oai:arXiv.org:2507.09748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09748","pdf_url":"https://arxiv.org/pdf/2507.09748","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":"doi:10.48550/arxiv.2507.09748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.09748","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:2507.09748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09748","pdf_url":"https://arxiv.org/pdf/2507.09748","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/G2622207176","display_name":null,"funder_award_id":"92470118,62306176","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-3D":[0],"generation":[1,117],"based":[2],"on":[3],"score":[4,17,28,85,123,168,207],"distillation":[5,18,29,52],"of":[6,43,79,164,189,199],"pre-trained":[7],"2D":[8],"diffusion":[9],"models":[10],"has":[11],"gained":[12],"increasing":[13],"interest,":[14],"with":[15,185],"variational":[16],"(VSD)":[19],"as":[20],"a":[21,96,161],"remarkable":[22],"example.":[23],"VSD":[24,141],"proves":[25],"that":[26,93,213],"vanilla":[27],"can":[30,108,181,216],"be":[31,182,217],"improved":[32],"by":[33],"introducing":[34],"an":[35,76],"extra":[36],"score-based":[37],"model,":[38,90],"which":[39],"characterizes":[40],"the":[41,51,55,80,83,88,116,122,128,151,165,173,197],"distribution":[42],"images":[44],"rendered":[45],"from":[46,65,144],"3D":[47,89,102,130],"models,":[48],"to":[49,63,114,127,150,159,172],"correct":[50],"gradient.":[53],"Despite":[54],"theoretical":[56],"foundations,":[57],"VSD,":[58],"in":[59,104,147],"practice,":[60],"is":[61],"likely":[62],"suffer":[64,143],"slow":[66],"and":[67,87,91,101,132],"sometimes":[68],"ill-posed":[69],"convergence.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74,157],"perform":[75],"in-depth":[77],"investigation":[78],"interplay":[81],"between":[82,99],"introduced":[84],"model":[86,124,166],"find":[92],"there":[94],"exists":[95],"mismatching":[97],"problem":[98],"LoRA":[100],"distributions":[103],"practical":[105],"implementation.":[106],"We":[107,210],"simply":[109],"adjust":[110],"their":[111],"optimization":[112],"order":[113],"improve":[115],"quality.":[118],"By":[119],"doing":[120],"so,":[121],"looks":[125],"ahead":[126],"current":[129],"state":[131],"hence":[133],"yields":[134],"more":[135],"reasonable":[136],"corrections.":[137],"Nevertheless,":[138],"naive":[139],"lookahead":[140],"may":[142],"unstable":[145],"training":[146],"practice":[148],"due":[149],"potential":[152],"over-fitting.":[153],"To":[154],"address":[155],"this,":[156],"propose":[158],"use":[160],"linearized":[162],"variant":[163],"for":[167],"distillation,":[169],"giving":[170],"rise":[171],"Linearized":[174],"Lookahead":[175],"Variational":[176],"Score":[177],"Distillation":[178],"($L^2$-VSD).":[179],"$L^2$-VSD":[180],"realized":[183],"efficiently":[184],"forward-mode":[186],"autodiff":[187],"functionalities":[188],"existing":[190],"deep":[191],"learning":[192],"libraries.":[193],"Extensive":[194],"experiments":[195],"validate":[196],"efficacy":[198],"$L^2$-VSD,":[200],"revealing":[201],"its":[202],"clear":[203],"superiority":[204],"over":[205],"prior":[206],"distillation-based":[208],"methods.":[209],"also":[211],"show":[212],"our":[214],"method":[215],"seamlessly":[218],"incorporated":[219],"into":[220],"any":[221],"other":[222],"VSD-based":[223],"text-to-3D":[224],"framework.":[225]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}