{"id":"https://openalex.org/W4413155968","doi":"https://doi.org/10.1109/cvpr52734.2025.00681","title":"IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner","display_name":"IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413155968","doi":"https://doi.org/10.1109/cvpr52734.2025.00681"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00681","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":"conference-paper","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/A5031417341","display_name":"Yuyang Huang","orcid":"https://orcid.org/0000-0001-8150-4902"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055550018","display_name":"Y. R. Chen","orcid":"https://orcid.org/0000-0003-1463-0188"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabo Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945600","display_name":"Li Ding","orcid":"https://orcid.org/0000-0001-6367-0333"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Ding","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614075","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0003-1276-1424"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Huawei Inc.,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Inc.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045342512","display_name":"Wenrui Dai","orcid":"https://orcid.org/0000-0003-2522-5778"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Dai","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016006337","display_name":"Junni Zou","orcid":"https://orcid.org/0000-0002-9694-9880"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junni Zou","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-5165-4325"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Inc.,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Inc.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82158293,"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":"7265","last_page":"7275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998000264167786,"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":0.9998000264167786,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/zero","display_name":"Zero (linguistics)","score":0.7798018455505371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6002638339996338},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5534079074859619},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5133280158042908},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35407355427742004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32058364152908325},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05938008427619934}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7798018455505371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6002638339996338},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5534079074859619},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5133280158042908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35407355427742004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32058364152908325},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05938008427619934},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00681","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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2898200825","https://openalex.org/W4312933868","https://openalex.org/W4383097497","https://openalex.org/W4386066731","https://openalex.org/W4386071957","https://openalex.org/W4386076027","https://openalex.org/W4386076532","https://openalex.org/W4390871856","https://openalex.org/W4390872387","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873331","https://openalex.org/W4390873429","https://openalex.org/W4394625750","https://openalex.org/W4400573519","https://openalex.org/W4401384667","https://openalex.org/W4402623742","https://openalex.org/W4402660110","https://openalex.org/W4402702984","https://openalex.org/W4402715862","https://openalex.org/W4402727736","https://openalex.org/W4402727798","https://openalex.org/W4402754201","https://openalex.org/W4402961675","https://openalex.org/W4403021266","https://openalex.org/W4403840670","https://openalex.org/W4403877911","https://openalex.org/W4403878131","https://openalex.org/W4404439864","https://openalex.org/W4404446894","https://openalex.org/W4404612908","https://openalex.org/W4404971889","https://openalex.org/W4405270825","https://openalex.org/W4405695475","https://openalex.org/W4409365504","https://openalex.org/W4409365923"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Controllability":[0],"of":[1,13,75,106,153,160,167,179,218,226,239,247,253,263],"video":[2,21,59,63,96,145,174,193,219,242],"generation":[3,22,47,64,97,118,194],"has":[4],"been":[5],"recently":[6],"concerned":[7],"in":[8,204,216,241],"addition":[9],"to":[10,19,24,56,108,134,171,189,197],"the":[11,44,73,136,150,165,187,224],"quality":[12],"generated":[14],"videos.":[15],"The":[16],"main":[17],"challenge":[18],"controllable":[20,95],"is":[23,186],"synthesize":[25],"videos":[26,71,170,273],"based":[27],"on":[28],"user-specified":[29],"instance":[30,255],"spatial":[31],"locations":[32],"and":[33,49,69,77,104,123,157,177,195,201,223,228,259,274],"movement":[34,78,202],"trajectories.":[35,79],"However,":[36],"existing":[37,61,214,233],"methods":[38,65,215],"suffer":[39],"from":[40,126,129],"a":[41,85,116,144,205],"dilemma":[42],"between":[43],"resource":[45],"consumption,":[46],"quality,":[48,220],"user":[50],"controllability.":[51],"As":[52],"an":[53],"efficient":[54],"alternative":[55],"prohibitive":[57],"training-based":[58],"generation,":[60,243],"zero-shot":[62,87,206],"cannot":[66],"generate":[67,135],"high-quality":[68,192,275],"motion-consistent":[70],"under":[72],"control":[74,100,198,246,252],"layouts":[76,200],"In":[80],"this":[81,110],"paper,":[82],"we":[83,113,142],"propose":[84],"novel":[86],"method":[88],"named":[89],"IM-Zero":[90,185,212,235],"that":[91,120,148,211],"ameliorates":[92],"instance-level":[93],"motion":[94,102,117,122,139,151,169,175,245,264,269],"with":[98,232],"enhanced":[99],"accuracy,":[101],"consistency,":[103,222],"richness":[105,178],"details":[107],"address":[109],"problem.":[111],"Specifically,":[112],"first":[114,188],"present":[115],"stage":[119,147],"extracts":[121],"textural":[124],"guidance":[125],"keyframe":[127],"candidates":[128],"pre-trained":[130,154,161],"grounded":[131],"text-to-image":[132,162],"model":[133],"desired":[137],"coarse":[138,168],"video.":[140],"Subsequently,":[141],"develop":[143],"refinement":[146],"injects":[149],"priors":[152,159],"text-to-video":[155,276],"models":[156,163],"detail":[158],"into":[164],"latents":[166],"further":[172],"enhance":[173],"consistency":[176],"details.":[180],"To":[181],"our":[182],"best":[183],"knowledge,":[184],"simultaneously":[190],"achieve":[191],"allow":[196],"both":[199],"trajectories":[203],"manner.":[207],"Extensive":[208],"experiments":[209],"demonstrate":[210],"outperforms":[213],"terms":[217],"inter-frame":[221],"alignment":[225],"location":[227],"trajectory.":[229],"Furthermore,":[230],"compared":[231],"methods,":[234],"enjoys":[236],"extra":[237],"advantages":[238],"versatility":[240],"including":[244],"subparts":[248],"within":[249],"instances,":[250],"finer":[251],"specifying":[254],"shapes":[256],"via":[257],"masks,":[258],"more":[260],"difficult":[261],"tasks":[262],"transfer":[265],"for":[266],"customizing":[267],"fine-grained":[268],"patterns":[270],"through":[271],"reference":[272],"generation.":[277]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}