{"id":"https://openalex.org/W4404985095","doi":"https://doi.org/10.1145/3680528.3687656","title":"I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models","display_name":"I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4404985095","doi":"https://doi.org/10.1145/3680528.3687656"},"language":"en","primary_location":{"id":"doi:10.1145/3680528.3687656","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680528.3687656","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687656","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Conference Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687656","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069241707","display_name":"Wenqi Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wenqi Ouyang","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-2273-5984","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101245630","display_name":"Yi Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Dong","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-6017-2886","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043951834","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-0571-5924"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0571-5924","affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079767760","display_name":"Jianlou Si","orcid":"https://orcid.org/0000-0002-2029-6588"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlou Si","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2029-6588","affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052549072","display_name":"Xingang Pan","orcid":"https://orcid.org/0000-0002-5825-9467"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xingang Pan","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5825-9467","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069241707"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":3.3331,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93675537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9932000041007996,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9932000041007996,"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/T11439","display_name":"Video Analysis and Summarization","score":0.987500011920929,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.934499979019165,"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/computer-science","display_name":"Computer science","score":0.7596149444580078},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6404898166656494},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5486347675323486},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.5338415503501892},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.531482458114624},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4969048798084259},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.462284117937088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4466085433959961},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10914003849029541},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.058199137449264526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596149444580078},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6404898166656494},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5486347675323486},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5338415503501892},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.531482458114624},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4969048798084259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.462284117937088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4466085433959961},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10914003849029541},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.058199137449264526},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3680528.3687656","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680528.3687656","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687656","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/201827","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/201827","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3680528.3687656","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680528.3687656","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687656","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404985095.pdf","grobid_xml":"https://content.openalex.org/works/W4404985095.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1989192603","https://openalex.org/W2002955791","https://openalex.org/W2017745767","https://openalex.org/W2031171237","https://openalex.org/W2148880081","https://openalex.org/W2956900569","https://openalex.org/W3153469116","https://openalex.org/W4251428492","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386113271","https://openalex.org/W4387969181","https://openalex.org/W4389539288","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4400582084","https://openalex.org/W4401024496"],"related_works":["https://openalex.org/W2751894797","https://openalex.org/W4239647412","https://openalex.org/W2071802525","https://openalex.org/W2795296510","https://openalex.org/W2386796262","https://openalex.org/W2912356887","https://openalex.org/W2389546251","https://openalex.org/W2776044948","https://openalex.org/W2369556382","https://openalex.org/W2357549071"],"abstract_inverted_index":{"The":[0],"remarkable":[1],"generative":[2],"capabilities":[3],"of":[4,35,48,62,95,103,125],"diffusion":[5],"models":[6],"have":[7],"motivated":[8],"extensive":[9],"research":[10],"in":[11,25,178],"both":[12],"image":[13,29,63],"and":[14,40,55,92,112,144],"video":[15,19,78,98,169,180],"editing.":[16],"Compared":[17],"to":[18,66,75,135,160,185],"editing":[20,30,64],"which":[21,116],"faces":[22],"additional":[23],"challenges":[24],"the":[26,33,60,76,90,96,101,104,123,141],"time":[27],"dimension,":[28],"has":[31],"witnessed":[32],"development":[34],"more":[36,41],"diverse,":[37],"high-quality":[38],"approaches":[39],"capable":[42],"software":[43],"like":[44],"Photoshop.":[45],"In":[46],"light":[47],"this":[49],"gap,":[50],"we":[51],"introduce":[52],"a":[53,72,80,157],"novel":[54],"generic":[56],"solution":[57],"that":[58],"extends":[59],"applicability":[61],"tools":[65],"videos":[67],"by":[68],"propagating":[69],"edits":[70],"from":[71,164],"single":[73],"frame":[74],"entire":[77],"using":[79,150],"pre-trained":[81],"image-to-video":[82],"model.":[83],"Our":[84,191],"method,":[85],"dubbed":[86],"I2VEdit,":[87],"adaptively":[88],"preserves":[89],"visual":[91],"motion":[93,138],"integrity":[94],"source":[97],"depending":[99],"on":[100],"extent":[102],"edits,":[105,109,111],"effectively":[106],"handling":[107],"global":[108],"local":[110],"moderate":[113],"shape":[114],"changes,":[115],"existing":[117],"methods":[118],"cannot":[119],"fully":[120],"achieve.":[121],"At":[122],"core":[124],"our":[126,174],"method":[127],"are":[128],"two":[129],"main":[130],"processes:":[131],"Coarse":[132],"Motion":[133],"Extraction":[134],"align":[136],"basic":[137],"patterns":[139],"with":[140],"original":[142],"video,":[143],"Appearance":[145],"Refinement":[146],"for":[147],"precise":[148],"adjustments":[149],"fine-grained":[151,179],"attention":[152],"matching.":[153],"We":[154],"also":[155],"incorporate":[156],"skip-interval":[158],"strategy":[159],"mitigate":[161],"quality":[162],"degradation":[163],"auto-regressive":[165],"generation":[166],"across":[167],"multiple":[168],"clips.":[170],"Experimental":[171],"results":[172],"demonstrate":[173],"framework\u2019s":[175],"superior":[176],"performance":[177],"editing,":[181],"proving":[182],"its":[183],"capability":[184],"produce":[186],"high-quality,":[187],"temporally":[188],"consistent":[189],"outputs.":[190],"website":[192],"is":[193],"at":[194],"https://i2vedit.github.io/.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}