{"id":"https://openalex.org/W4413156830","doi":"https://doi.org/10.1109/cvpr52734.2025.00258","title":"Instruction-based Image Manipulation by Watching How Things Move","display_name":"Instruction-based Image Manipulation by Watching How Things Move","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413156830","doi":"https://doi.org/10.1109/cvpr52734.2025.00258"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5013983776","display_name":"Mingdeng Cao","orcid":"https://orcid.org/0000-0002-6577-4715"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mingdeng Cao","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089383771","display_name":"Xuaner Zhang","orcid":"https://orcid.org/0000-0002-7679-800X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuaner Zhang","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698163","display_name":"Yinqiang Zheng","orcid":"https://orcid.org/0000-0001-7434-5069"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yinqiang Zheng","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110653548","display_name":"Zhihao Xia","orcid":"https://orcid.org/0000-0003-1548-2113"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihao Xia","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013983776"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.8987,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91857022,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2704","last_page":"2713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.49639999866485596,"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"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.49639999866485596,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.44279998540878296,"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":0.6921548843383789},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44653478264808655},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.42527467012405396},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4080890119075775},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3960827887058258},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3809647262096405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3539612293243408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6921548843383789},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44653478264808655},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.42527467012405396},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4080890119075775},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3960827887058258},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3809647262096405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3539612293243408}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338243","display_name":"JST-Mirai Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W3109908659","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4385527149","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4388994505","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4393148714","https://openalex.org/W4394596927","https://openalex.org/W4402715857","https://openalex.org/W4402716223","https://openalex.org/W4402727613","https://openalex.org/W4402753379","https://openalex.org/W4402753991","https://openalex.org/W4403760949","https://openalex.org/W4404965485","https://openalex.org/W4412636516"],"related_works":["https://openalex.org/W2949816130","https://openalex.org/W2225239186","https://openalex.org/W2037030319","https://openalex.org/W2042193908","https://openalex.org/W2096230562","https://openalex.org/W4307186884","https://openalex.org/W2788541584","https://openalex.org/W3093158276","https://openalex.org/W3183170284","https://openalex.org/W2572781942"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,82,88],"novel":[4],"dataset":[5,75,84],"construction":[6],"pipeline":[7],"that":[8,95],"samples":[9],"pairs":[10],"of":[11,38,91],"frames":[12,33],"from":[13],"videos":[14],"and":[15,40,59,118],"uses":[16],"multimodal":[17],"large":[18],"language":[19],"models":[20],"(MLLMs)":[21],"to":[22,65,85,98],"generate":[23],"editing":[24],"instructions":[25],"for":[26,73],"training":[27],"instruction-based":[28,92],"image":[29],"manipulation":[30],"models.":[31],"Video":[32],"inherently":[34],"preserve":[35],"the":[36],"identity":[37],"subjects":[39],"scenes,":[41],"ensuring":[42],"consistent":[43],"content":[44],"preservation":[45],"during":[46],"editing.":[47],"Additionally,":[48],"video":[49],"data":[50],"captures":[51],"diverse,":[52],"natural":[53],"dynamics\u2014such":[54],"as":[55,112],"non-rigid":[56],"subject":[57,114],"motion":[58],"complex":[60,93],"camera":[61,120],"movements\u2014that":[62],"are":[63,96],"difficult":[64,97],"model":[66,89,105],"otherwise,":[67],"making":[68],"it":[69],"an":[70],"ideal":[71],"source":[72],"scalable":[74],"construction.":[76],"Using":[77],"this":[78],"approach,":[79],"we":[80],"create":[81],"new":[83],"train":[86],"InstructMove,":[87],"capable":[90],"manipulations":[94],"achieve":[99],"with":[100],"synthetically":[101],"generated":[102],"datasets.":[103],"Our":[104],"demonstrates":[106],"state-of-the-art":[107],"performance":[108],"in":[109],"tasks":[110],"such":[111],"adjusting":[113],"poses,":[115],"rearranging":[116],"elements,":[117],"altering":[119],"perspectives.":[121],"The":[122],"project":[123],"page":[124],"is":[125],"available":[126],"here.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}