{"id":"https://openalex.org/W7162495368","doi":"https://doi.org/10.1109/3dv69130.2026.00150","title":"HDEdit: Editing Videos and 3D Scenes with Video Diffusion Through Hierarchical Task Decomposition","display_name":"HDEdit: Editing Videos and 3D Scenes with Video Diffusion Through Hierarchical Task Decomposition","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7162495368","doi":"https://doi.org/10.1109/3dv69130.2026.00150"},"language":null,"primary_location":{"id":"doi:10.1109/3dv69130.2026.00150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00150","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/A5081343160","display_name":"Y Zhang","orcid":null},"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":"Yanming Zhang","raw_affiliation_strings":["University of Illinois Urbana-Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137189882","display_name":"Jun-Kun Chen","orcid":null},"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,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072030431","display_name":"Jipeng Lyu","orcid":null},"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":"Jipeng Lyu","raw_affiliation_strings":["University of Illinois Urbana-Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137167592","display_name":"Yu-Xiong Wang","orcid":null},"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,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.85218414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1577","last_page":"1587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.3264000117778778,"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/T11439","display_name":"Video Analysis and Summarization","score":0.3264000117778778,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.16300000250339508,"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":0.07329999655485153,"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/task","display_name":"Task (project management)","score":0.505299985408783},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4036000072956085},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.38659998774528503},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3084999918937683},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2953000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775000095367432},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6363999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230999827384949},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2842000126838684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/3dv69130.2026.00150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00150","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":[{"id":"https://openalex.org/G2903752559","display_name":null,"funder_award_id":"N00014-26-1-2099","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6577414521","display_name":null,"funder_award_id":"2106825,2519216","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6770826516","display_name":null,"funder_award_id":"2020-67021-32799","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2956900569","https://openalex.org/W3109585842","https://openalex.org/W4312933868","https://openalex.org/W4378450585","https://openalex.org/W4386071686","https://openalex.org/W4386071957","https://openalex.org/W4386076215","https://openalex.org/W4387806972","https://openalex.org/W4390871782","https://openalex.org/W4390872653","https://openalex.org/W4390873135","https://openalex.org/W4402702921","https://openalex.org/W4402704551","https://openalex.org/W4402727941","https://openalex.org/W4402753812","https://openalex.org/W4402753826","https://openalex.org/W4402753991","https://openalex.org/W4402951568","https://openalex.org/W4402952492","https://openalex.org/W4403601051","https://openalex.org/W4403888760","https://openalex.org/W4404770105","https://openalex.org/W4415798777","https://openalex.org/W7133218093","https://openalex.org/W7133227460","https://openalex.org/W7133244582"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"HDEdit,":[2],"a":[3,98],"training-free":[4],"framework":[5],"for":[6,54],"instruction-guided":[7],"video":[8],"and":[9,21,78,117,126],"3D":[10,95,128],"scene":[11],"editing":[12,96],"that":[13,104],"resolves":[14],"the":[15],"fundamental":[16],"tension":[17],"between":[18],"instruction":[19,56],"fulfillment":[20],"original":[22],"content":[23],"preservation":[24],"through":[25],"Hierarchical":[26],"task":[27],"Decomposition.":[28],"Our":[29],"key":[30],"insight":[31],"is":[32],"to":[33,65,94],"progressively":[34],"decompose":[35],"complex":[36],"edits":[37],"into":[38],"simpler":[39],"subtasks.":[40],"This":[41],"hierarchical":[42],"strategy":[43],"aligns":[44],"with":[45],"dual":[46],"objectives:":[47],"an":[48],"LLMguided":[49],"planner":[50],"structures":[51],"high-level":[52],"subgoals":[53],"reliable":[55],"fulfillment,":[57],"while":[58],"embedding-space":[59],"interpolation":[60],"further":[61],"refines":[62],"each":[63],"subgoal":[64],"preserve":[66],"unedited":[67],"content.":[68],"Two":[69],"tailored":[70],"control":[71],"mechanisms":[72],"-":[73,82],"word-level":[74],"attention":[75],"map":[76],"propagation":[77],"parallel":[79],"denoising":[80],"synchronization":[81],"ensure":[83],"temporally":[84],"consistent,":[85],"hyperparameter":[86],"tuning-free":[87],"execution.":[88],"Beyond":[89],"video,":[90],"we":[91],"extend":[92],"HDEdit":[93],"via":[97],"simple":[99],"yet":[100],"effective":[101],"render-edit-reconstruct":[102],"process":[103],"maintains":[105],"strong":[106],"geometric":[107,129],"consistency.":[108],"Extensive":[109],"experiments":[110],"demonstrate":[111],"our":[112],"state-of-the-art":[113],"results":[114],"across":[115],"diverse":[116],"challenging":[118],"edits,":[119],"including":[120],"longduration":[121],"videos,":[122],"fast":[123],"camera":[124],"motion,":[125],"significant":[127],"changes.":[130]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}
