{"id":"https://openalex.org/W4402702921","doi":"https://doi.org/10.1109/cvpr52733.2024.01907","title":"Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion","display_name":"Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402702921","doi":"https://doi.org/10.1109/cvpr52733.2024.01907"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01907","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvpr52733.2024.01907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5031959594","display_name":"Linzhan Mou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linzhan Mou","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Kun Chen","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039231803","display_name":"Yu-Xiong Wang","orcid":"https://orcid.org/0000-0003-1195-2739"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Xiong Wang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.097,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91811175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"20176","last_page":"20185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9987000226974487,"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":0.9979000091552734,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7291927933692932},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6283597350120544},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5957842469215393},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5238645076751709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251896142959595},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06185048818588257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291927933692932},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6283597350120544},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5957842469215393},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5238645076751709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251896142959595},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06185048818588257},{"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/cvpr52733.2024.01907","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvpr52733.2024.01907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G539587745","display_name":"RI: Medium: Creating Knowledge with All-Novel-Class Computer Vision","funder_award_id":"2106825","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":51,"referenced_works":["https://openalex.org/W2956900569","https://openalex.org/W3048537404","https://openalex.org/W3096831136","https://openalex.org/W3109585842","https://openalex.org/W3109908659","https://openalex.org/W3153220274","https://openalex.org/W3166396011","https://openalex.org/W3176327543","https://openalex.org/W4200382072","https://openalex.org/W4214731463","https://openalex.org/W4281651265","https://openalex.org/W4287029626","https://openalex.org/W4289785045","https://openalex.org/W4298185919","https://openalex.org/W4298187450","https://openalex.org/W4307324560","https://openalex.org/W4309800375","https://openalex.org/W4312828520","https://openalex.org/W4312891300","https://openalex.org/W4313165271","https://openalex.org/W4318203092","https://openalex.org/W4321488276","https://openalex.org/W4323718574","https://openalex.org/W4385489997","https://openalex.org/W4385527149","https://openalex.org/W4385890375","https://openalex.org/W4386072096","https://openalex.org/W4386075614","https://openalex.org/W4386075787","https://openalex.org/W4386076215","https://openalex.org/W4386113271","https://openalex.org/W4389539682","https://openalex.org/W4390871782","https://openalex.org/W4390871980","https://openalex.org/W4390872653","https://openalex.org/W4390873054","https://openalex.org/W4390873120","https://openalex.org/W4390873135","https://openalex.org/W4391506342","https://openalex.org/W6791353385","https://openalex.org/W6840155194","https://openalex.org/W6841366371","https://openalex.org/W6843813467","https://openalex.org/W6844305113","https://openalex.org/W6846365162","https://openalex.org/W6846793839","https://openalex.org/W6846820273","https://openalex.org/W6848774630","https://openalex.org/W6850636897","https://openalex.org/W6855895270","https://openalex.org/W6860766341"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"This":[0],"paper":[1],"proposes":[2],"Instruct":[3,175],"4D-to-4D":[4,176],"that":[5,155],"achieves":[6,157],"4D":[7,62],"awareness":[8],"and":[9,78,103,123,150,153,159,168,179,184,189],"spatial-temporal":[10],"consistency":[11,74],"for":[12,100,118],"2D":[13,27],"diffusion":[14,28],"models":[15,29],"to":[16,40,53,59,82,127,139,181],"generate":[17],"high-quality":[18],"instruction-guided":[19,51],"dynamic":[20,31],"scene":[21,32,63],"editing":[22,33,44,52,77,122,138,151,162],"results.":[23],"Traditional":[24],"applications":[25],"of":[26,49,132],"in":[30,36,75,113,147],"often":[34],"result":[35],"inconsistency,":[37],"primarily":[38],"due":[39],"their":[41],"inherent":[42],"frame-by-frame":[43],"methodology.":[45],"Addressing":[46],"the":[47,83,91,129,171],"complexities":[48],"extending":[50],"4D,":[54],"our":[55,145],"key":[56],"insight":[57],"is":[58,177],"treat":[60],"a":[61,65,114],"as":[64],"pseudo-3D":[66,84,133],"scene,":[67],"decoupled":[68],"into":[69],"two":[70],"sub-problems:":[71],"achieving":[72],"temporal":[73],"video":[76],"applying":[79],"these":[80],"edits":[81],"scene.":[85],"Following":[86],"this,":[87],"we":[88,107],"first":[89],"enhance":[90],"Instruct-Pix2Pix":[92],"(IP2P)":[93],"model":[94],"with":[95,164],"an":[96],"anchor-aware":[97],"attention":[98],"module":[99],"batch":[101],"processing":[102],"consistent":[104,161],"editing.":[105],"Additionally,":[106],"integrate":[108],"optical":[109],"flow-guided":[110],"appearance":[111],"propagation":[112],"sliding":[115],"window":[116],"fashion":[117],"more":[119,190],"precise":[120],"frame-to-frame":[121],"incorporate":[124],"depth-based":[125],"projection":[126],"manage":[128],"extensive":[130],"data":[131],"scenes,":[134],"followed":[135],"by":[136],"iterative":[137],"achieve":[140],"convergence.":[141],"We":[142],"extensively":[143],"evaluate":[144],"approach":[146],"various":[148],"scenes":[149],"instructions,":[152],"demonstrate":[154],"it":[156],"spatially":[158],"temporally":[160],"results,":[163],"significantly":[165],"enhanced":[166],"detail":[167],"sharpness":[169],"over":[170],"prior":[172],"art.":[173],"Notably,":[174],"general":[178],"applicable":[180],"both":[182],"monocular":[183],"challenging":[185],"multi-camera":[186],"scenes.":[187],"Code":[188],"results":[191],"are":[192],"available":[193],"at":[194],"immortalco.github.io/Instruct-4D-to-4D.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}