{"id":"https://openalex.org/W4403791617","doi":"https://doi.org/10.1145/3664647.3681394","title":"Zero-Shot Controllable Image-to-Video Animation via Motion Decomposition","display_name":"Zero-Shot Controllable Image-to-Video Animation via Motion Decomposition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791617","doi":"https://doi.org/10.1145/3664647.3681394"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5059195621","display_name":"Shoubin Yu","orcid":"https://orcid.org/0009-0006-1670-0054"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shoubin Yu","raw_affiliation_strings":["University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101333483","display_name":"Jacob Zhiyuan Fang","orcid":"https://orcid.org/0000-0001-6740-6855"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Zhiyuan Fang","raw_affiliation_strings":["Amazon, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, San Jose, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102369458","display_name":"Jian Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Zheng","raw_affiliation_strings":["Amazon, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, San Jose, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035681753","display_name":"Gunnar A. Sigurdsson","orcid":"https://orcid.org/0000-0001-8967-7322"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gunnar Sigurdsson","raw_affiliation_strings":["Amazon, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, San Jose, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027328044","display_name":"Vicente Ord\u00f3\u00f1ez","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vicente Ordonez","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018704921","display_name":"Robinson Piramuthu","orcid":"https://orcid.org/0000-0002-1767-8382"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robinson Piramuthu","raw_affiliation_strings":["Amazon, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, San Jose, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112364306","display_name":"Mohit Bansal","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":["University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5059195621"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55589049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3332","last_page":"3341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994000196456909,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994000196456909,"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":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/animation","display_name":"Animation","score":0.7078529596328735},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6593931913375854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.621597409248352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6149020195007324},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5879537463188171},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5521845817565918},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.550987720489502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5332180261611938},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5103356242179871},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.44959038496017456},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4296822249889374},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07794508337974548}],"concepts":[{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7078529596328735},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6593931913375854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.621597409248352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6149020195007324},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5879537463188171},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5521845817565918},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.550987720489502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332180261611938},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5103356242179871},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.44959038496017456},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4296822249889374},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07794508337974548},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":26,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2064076387","https://openalex.org/W2470139095","https://openalex.org/W2612690371","https://openalex.org/W2799055999","https://openalex.org/W2883127586","https://openalex.org/W2962785568","https://openalex.org/W2963092440","https://openalex.org/W2964245526","https://openalex.org/W2965833116","https://openalex.org/W2994586138","https://openalex.org/W3035590142","https://openalex.org/W3176504418","https://openalex.org/W3177617830","https://openalex.org/W3196049079","https://openalex.org/W3204588463","https://openalex.org/W4200150166","https://openalex.org/W4221166385","https://openalex.org/W4312913021","https://openalex.org/W4312933868","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4386076532","https://openalex.org/W4386952562","https://openalex.org/W4390873135","https://openalex.org/W4402726937"],"related_works":["https://openalex.org/W2121378366","https://openalex.org/W3112102641","https://openalex.org/W2013184069","https://openalex.org/W2989004599","https://openalex.org/W1976926596","https://openalex.org/W126583968","https://openalex.org/W2535923857","https://openalex.org/W2532377291","https://openalex.org/W2359575859","https://openalex.org/W2999276620"],"abstract_inverted_index":{"In":[0],"this":[1,64,92,198],"paper,":[2],"we":[3,155],"introduce":[4,59],"a":[5,60,157,172,176],"new":[6,173,177],"challenging":[7],"task":[8,78,193,200],"called":[9,69],"Zero-Shot":[10],"Controllable":[11],"Image-to-Video":[12,76],"Animation,":[13],"where":[14],"the":[15,28,32,49,180,188],"goal":[16],"is":[17],"to":[18,48,91,137,147],"animate":[19],"an":[20],"image":[21,101],"based":[22],"on":[23,99],"motion":[24,55,88,105,115],"trajectories":[25],"defined":[26],"by":[27,79],"user,":[29],"without":[30],"fine-tuning":[31],"base":[33],"model.":[34],"Primary":[35],"challenges":[36,126],"include":[37],"maintaining":[38],"consistency":[39,42],"of":[40,43,54,192],"background,":[41],"object":[44,149],"in":[45],"motion,":[46],"faithfulness":[47],"user-defined":[50],"trajectory,":[51],"and":[52,86,107,141,165,190,195,206],"quality":[53],"animation.":[56,89,153],"We":[57],"also":[58,123],"novel":[61,158,199],"approach":[62],"for":[63,103,113,127,179,197,201],"task,":[65],"leveraging":[66],"diffusion":[67],"models":[68],"Img2VidAnim-Zero":[70],"(IVA0).":[71],"IVA0":[72,94,170],"tackles":[73],"our":[74],"controllable":[75,128,159,182],"(I2V)":[77],"decomposing":[80],"it":[81],"into":[82],"two":[83],"subtasks:":[84],"'out-of-place'":[85],"'in-place'":[87],"Due":[90],"decomposition,":[93],"can":[95],"leverage":[96],"existing":[97,108],"work":[98],"layout-conditioned":[100],"generation":[102,111],"out-of-place":[104,152],"generation,":[106],"text-conditioned":[109],"video":[110],"methods":[112],"in-place":[114],"animation,":[116,129],"thus":[117],"facilitating":[118],"zero-shot":[119,181],"generation.":[120],"Our":[121,185,204],"model":[122],"addresses":[124],"key":[125],"such":[130],"as":[131,171],"Layout":[132],"Conditioning":[133],"via":[134],"Spatio-Temporal":[135],"Masking":[136],"incorporate":[138],"user":[139],"guidance":[140],"Motion":[142],"Afterimage":[143],"Suppression":[144],"(MAS)":[145],"scheme":[146],"reduce":[148],"ghosting":[150],"during":[151],"Finally,":[154],"design":[156],"I2V":[160,183],"benchmark":[161],"featuring":[162],"diverse":[163],"local-":[164],"global-level":[166],"metrics.":[167],"Results":[168],"show":[169],"state-of-the-art,":[174],"establishing":[175],"standard":[178],"task.":[184],"method":[186],"highlights":[187],"simplicity":[189],"effectiveness":[191],"decomposition":[194],"modularization":[196],"future":[202],"studies.":[203],"code":[205],"visualizations":[207],"are":[208],"available":[209],"at":[210],"https://img2vidanim-0.github.io/":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
