{"id":"https://openalex.org/W4415289351","doi":"https://doi.org/10.1109/iccv51701.2025.01126","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","display_name":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415289351","doi":"https://doi.org/10.1109/iccv51701.2025.01126"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045375675","display_name":"Quanhao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanhao Li","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101140026","display_name":"Zhen Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xing","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431435","display_name":"Rui Wang","orcid":"https://orcid.org/0009-0004-5900-605X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341698","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-1681-7926"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102317133","display_name":"Qi Dai","orcid":"https://orcid.org/0000-0002-8549-7225"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Dai","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12112","last_page":"12123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.995199978351593,"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":0.995199978351593,"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/T12290","display_name":"Human Motion and Animation","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.991100013256073,"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/trajectory","display_name":"Trajectory","score":0.7674999833106995},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6470999717712402},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5210000276565552},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5170000195503235},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5127000212669373},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.391400009393692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847999930381775},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7674999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.67330002784729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6722999811172485},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6470999717712402},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5210000276565552},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38449999690055847},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.16421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16421","pdf_url":"https://arxiv.org/pdf/2503.16421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.16421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16421","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.16421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16421","pdf_url":"https://arxiv.org/pdf/2503.16421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5766347838","display_name":null,"funder_award_id":"62032006,62472098","funder_id":"https://openalex.org/F4320320884","funder_display_name":"Camargo Foundation"}],"funders":[{"id":"https://openalex.org/F4320320884","display_name":"Camargo Foundation","ror":"https://ror.org/04hbteb59"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,47,65,72],"video":[3,19,88,154,175],"generation":[4,20,106],"have":[5],"led":[6],"to":[7,23,119],"remarkable":[8],"improvements":[9],"visual":[11,56,145],"quality":[12,176],"and":[13,42,54,93,124,131,144,163,177],"temporal":[14],"coherence.":[15],"Upon":[16],"this,":[17],"trajectory-controllable":[18,87],"has":[21],"emerged":[22],"enable":[24],"precise":[25],"object":[26,40,52,142],"motion":[27,44],"control":[28,64,111,179],"through":[29,112],"explicitly":[30],"defined":[31,138],"spatial":[32],"paths.":[33],"However,":[34],"existing":[35],"methods":[36,60,193],"struggle":[37],"with":[38,157],"complex":[39],"movements":[41],"multi-object":[43],"control,":[45],"resulting":[46],"imprecise":[48],"trajectory":[49,63,110,178],"adherence,":[50],"poor":[51],"consistency,":[53],"compromised":[55],"quality.":[57,146],"Furthermore,":[58,147],"these":[59,98],"only":[61],"support":[62],"a":[66,103,151,169],"single":[67],"format,":[68],"limiting":[69],"their":[70],"applicability":[71],"diverse":[73],"scenarios.":[74],"Additionally,":[75],"there":[76],"is":[77],"no":[78],"publicly":[79,201],"available":[80,202],"dataset":[81],"or":[82],"benchmark":[83,171],"specifically":[84],"tailored":[85],"for":[86,161],"generation,":[89],"hindering":[90],"robust":[91],"training":[92],"systematic":[94],"evaluation.":[95],"To":[96],"address":[97],"challenges,":[99],"we":[100,148],"introduce":[101,167],"MagicMotion,":[102],"novel":[104],"image-to-video":[105],"framework":[107],"that":[108,172,189],"enables":[109],"three":[113],"levels":[114],"of":[115,184],"conditions":[116],"from":[117],"dense":[118],"sparse:":[120],"masks,":[121],"bounding":[122],"boxes,":[123],"sparse":[125],"boxes.":[126],"Given":[127],"an":[128,158],"input":[129],"image":[130],"trajectories,":[132],"MagicMotion":[133,190],"seamlessly":[134],"animates":[135],"objects":[136],"along":[137,156],"trajectories":[139],"while":[140],"maintaining":[141],"consistency":[143],"present":[149],"MagicData,":[150],"large-scale":[152],"trajectory-controlled":[153],"dataset,":[155],"automated":[159],"pipeline":[160],"annotation":[162],"filtering.":[164],"We":[165],"also":[166],"MagicBench,":[168],"comprehensive":[170],"assesses":[173],"both":[174],"accuracy":[180],"across":[181,194],"different":[182],"numbers":[183],"objects.":[185],"Extensive":[186],"experiments":[187],"demonstrate":[188],"outperforms":[191],"previous":[192],"various":[195],"metrics.":[196],"Our":[197],"project":[198],"page":[199],"are":[200],"at":[203],"https://quanhaol.github.io/magicmotion-site.":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-17T00:00:00"}