{"id":"https://openalex.org/W4400582084","doi":"https://doi.org/10.1145/3641519.3657497","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","display_name":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400582084","doi":"https://doi.org/10.1145/3641519.3657497"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657497","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","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/A5017719741","display_name":"Xiaoyu Shi","orcid":"https://orcid.org/0009-0003-3696-4442"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xiaoyu Shi","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0003-3696-4442","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562598","display_name":"Zhaoyang Huang","orcid":"https://orcid.org/0000-0001-7688-1471"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhaoyang Huang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7688-1471","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014747290","display_name":"Fu-Yun Wang","orcid":"https://orcid.org/0000-0003-1323-4933"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fu-Yun Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-1323-4933","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023250570","display_name":"Weikang Bian","orcid":"https://orcid.org/0000-0001-9986-3348"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weikang Bian","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9986-3348","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086473524","display_name":"Dasong Li","orcid":"https://orcid.org/0000-0001-6766-7529"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dasong Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6766-7529","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029151761","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-1704-4144"},"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":"Yi Zhang","raw_affiliation_strings":["SenseTime, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1704-4144","affiliations":[{"raw_affiliation_string":"SenseTime, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047451771","display_name":"Manyuan Zhang","orcid":"https://orcid.org/0009-0003-2148-1085"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Manyuan Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0003-2148-1085","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113286583","display_name":"Ka Chun Cheung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091318","display_name":"NanoBioImaging (China)","ror":"https://ror.org/00k388f40","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091318"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ka Chun Cheung","raw_affiliation_strings":["NVIDIA, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-5610-1298","affiliations":[{"raw_affiliation_string":"NVIDIA, Hong Kong","institution_ids":["https://openalex.org/I4210091318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109745973","display_name":"Simon See","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091318","display_name":"NanoBioImaging (China)","ror":"https://ror.org/00k388f40","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091318"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simon See","raw_affiliation_strings":["NVIDIA, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8310-7820","affiliations":[{"raw_affiliation_string":"NVIDIA, Hong Kong","institution_ids":["https://openalex.org/I4210091318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108326390","display_name":"Hongwei Qin","orcid":null},"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":"Hongwei Qin","raw_affiliation_strings":["SenseTime, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7498-6755","affiliations":[{"raw_affiliation_string":"SenseTime, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051797244","display_name":"Yifeng Dai","orcid":"https://orcid.org/0000-0002-5037-3695"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifeng Dai","raw_affiliation_strings":["Tsinghua University, China, China"],"raw_orcid":"https://orcid.org/0000-0002-5037-3695","affiliations":[{"raw_affiliation_string":"Tsinghua University, China, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2664-7975","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5017719741"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":12.2003,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.99205933,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"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/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9986000061035156,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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-vision","display_name":"Computer vision","score":0.686347484588623},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6293835639953613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6261205673217773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6056409478187561},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.5450558662414551},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5244172811508179},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3866976499557495}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.686347484588623},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6293835639953613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6261205673217773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6056409478187561},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.5450558662414551},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5244172811508179},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3866976499557495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641519.3657497","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","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":36,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W2155302366","https://openalex.org/W2207941348","https://openalex.org/W2548527721","https://openalex.org/W2560474170","https://openalex.org/W2902266071","https://openalex.org/W2963782415","https://openalex.org/W2964156315","https://openalex.org/W2964318715","https://openalex.org/W2981852735","https://openalex.org/W2990375436","https://openalex.org/W3007471652","https://openalex.org/W3034921716","https://openalex.org/W3109908659","https://openalex.org/W3166285241","https://openalex.org/W3173935672","https://openalex.org/W3176504418","https://openalex.org/W3178284600","https://openalex.org/W4240153047","https://openalex.org/W4254373586","https://openalex.org/W4286696412","https://openalex.org/W4288089799","https://openalex.org/W4312326540","https://openalex.org/W4312828807","https://openalex.org/W4312933868","https://openalex.org/W4321766409","https://openalex.org/W4385535562","https://openalex.org/W4386071957","https://openalex.org/W4386076323","https://openalex.org/W4386076658","https://openalex.org/W4390871746","https://openalex.org/W4390872738","https://openalex.org/W4390873054","https://openalex.org/W4390874168","https://openalex.org/W4394625831","https://openalex.org/W6600339457"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W4386051551","https://openalex.org/W2779427294","https://openalex.org/W2725946685","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2069885731","https://openalex.org/W2563206327"],"abstract_inverted_index":{"We":[0],"introduce":[1],"Motion-I2V,":[2],"a":[3,42,122],"novel":[4],"framework":[5],"for":[6,126],"consistent":[7,108,184],"and":[8,117,139,145,172,185],"controllable":[9,186],"text-guided":[10],"image-to-video":[11,24,187],"generation":[12],"(I2V).":[13],"In":[14],"contrast":[15],"to":[16,67,87,134],"previous":[17],"methods":[18],"that":[19],"directly":[20],"learn":[21],"the":[22,37,51,54,59,69,91,97,112,127,152,176],"complicated":[23],"mapping,":[25],"Motion-I2V":[26,104,130,179],"factorizes":[27],"I2V":[28,153],"into":[29],"two":[30],"stages":[31],"with":[32,90,101,142],"explicit":[33],"motion":[34,44,116,137,140],"modeling.":[35],"For":[36,58],"first":[38,98,128],"stage,":[39,61,129],"we":[40,62],"propose":[41,63],"diffusion-based":[43],"field":[45],"predictor,":[46],"which":[47],"focuses":[48],"on":[49,158],"deducing":[50],"trajectories":[52,95,138],"of":[53,93,114,151,178],"reference":[55,84],"image\u2019s":[56],"pixels.":[57],"second":[60,163],"motion-augmented":[64],"temporal":[65,72],"attention":[66,73],"enhance":[68],"limited":[70],"1-D":[71],"in":[74,111,183],"video":[75],"latent":[76],"diffusion":[77],"models.":[78],"This":[79,147],"module":[80],"can":[81,105,131],"effectively":[82],"propagate":[83],"image":[85],"features":[86],"synthesized":[88],"frames":[89],"guidance":[92],"predicted":[94],"from":[96],"stage.":[99],"Compared":[100],"existing":[102],"methods,":[103],"generate":[106],"more":[107,149],"videos":[109],"even":[110],"presence":[113],"large":[115],"viewpoint":[118],"variation.":[119],"By":[120],"training":[121],"sparse":[123,143],"trajectory":[124,144],"ControlNet":[125],"support":[132],"users":[133],"precisely":[135],"control":[136],"regions":[141],"region.":[146],"offers":[148],"controllability":[150],"process":[154],"than":[155],"solely":[156],"relying":[157],"textual":[159],"instructions.":[160],"Additionally,":[161],"Motion-I2V\u2019s":[162],"stage":[164],"naturally":[165],"supports":[166],"zero-shot":[167],"video-to-video":[168],"translation.":[169],"Both":[170],"qualitative":[171],"quantitative":[173],"comparisons":[174],"demonstrate":[175],"advantages":[177],"over":[180],"prior":[181],"approaches":[182],"generation.":[188],"Please":[189],"see":[190],"our":[191],"project":[192],"page":[193],"at":[194],"https://xiaoyushi97.github.io/Motion-I2V/.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":9}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
