{"id":"https://openalex.org/W7172304970","doi":"https://doi.org/10.48550/arxiv.2607.29627","title":"FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control","display_name":"FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control","publication_year":2026,"publication_date":"2026-07-31","ids":{"openalex":"https://openalex.org/W7172304970","doi":"https://doi.org/10.48550/arxiv.2607.29627"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.29627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29627","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.29627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059916557","display_name":"Songchun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Songchun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020373369","display_name":"Guo Sitong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Sitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144258253","display_name":"Xianghao Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Xianghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144268334","display_name":"Pengwei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Pengwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144307670","display_name":"Yuwei Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079385579","display_name":"Lvmin Zhang","orcid":"https://orcid.org/0000-0003-3503-5791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lvmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5144248630","display_name":"Anyi Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Anyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7570000290870667,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7570000290870667,"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":0.11649999767541885,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.027000000700354576,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/trajectory","display_name":"Trajectory","score":0.6445000171661377},{"id":"https://openalex.org/keywords/compositing","display_name":"Compositing","score":0.5763000249862671},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.503600001335144},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46869999170303345},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46309998631477356},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4542999863624573},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.3668999969959259},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3596999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853999733924866},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6111999750137329},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5924000144004822},{"id":"https://openalex.org/C129315195","wikidata":"https://www.wikidata.org/wiki/Q1121886","display_name":"Compositing","level":3,"score":0.5763000249862671},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46869999170303345},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4542999863624573},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3124000132083893},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2953999936580658},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.29627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29627","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2607.29627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29627","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"video":[1,11,64],"compositing,":[2],"which":[3],"involves":[4],"inserting":[5],"external":[6],"assets":[7],"seamlessly":[8],"into":[9,108],"existing":[10,22],"sequences,":[12],"is":[13],"essential":[14],"for":[15,49,189],"content":[16],"creation":[17],"and":[18,80,140,145,155,164,183,210],"visual":[19,206],"effects.":[20],"However,":[21],"approaches":[23],"suffer":[24],"from":[25,33,101,173],"a":[26,59,67,90,109,115,137,142],"control-fidelity":[27],"trade-off:":[28],"they":[29],"either":[30],"hallucinate":[31],"motion":[32,100,181],"static":[34,78],"images,":[35],"failing":[36],"to":[37,129,158,176],"preserve":[38],"the":[39,73,122,187],"dynamics":[40],"of":[41,76,125],"pre-animated":[42],"assets,":[43],"or":[44,193],"lack":[45],"fine-grained":[46],"spatial":[47],"control":[48,182],"precise":[50],"asset":[51],"placement":[52],"along":[53],"user-defined":[54],"trajectories.":[55],"We":[56],"propose":[57],"FlexComposer,":[58],"unified":[60,168],"framework":[61],"that":[62,95,120,148,200],"standardizes":[63],"compositing":[65],"as":[66],"trajectory-guided":[68],"conditional":[69],"generation":[70],"task,":[71],"enabling":[72],"seamless":[74],"integration":[75,185],"both":[77],"images":[79],"dynamic":[81,177],"footage.":[82],"Our":[83],"approach":[84],"introduces":[85],"three":[86],"key":[87],"designs:":[88],"(1)":[89],"Unified":[91],"Canonical":[92],"Foreground":[93],"Representation":[94],"decouples":[96],"an":[97],"object's":[98],"intrinsic":[99],"its":[102],"global":[103],"displacement,":[104],"standardizing":[105],"heterogeneous":[106],"inputs":[107,172],"stabilized,":[110],"centered":[111],"latent":[112,127],"space;":[113],"(2)":[114],"Spatial-Aware":[116],"Latent":[117],"Injection":[118],"strategy":[119],"exploits":[121],"translation":[123],"equivariance":[124],"VAE":[126],"spaces":[128],"transport":[130],"canonical":[131],"features":[132],"onto":[133],"target":[134],"trajectories":[135],"via":[136],"parameter-free":[138],"mechanism;":[139],"(3)":[141],"Hybrid":[143],"Dataset":[144],"Synthetic-to-Real":[146],"Curriculum":[147],"synergizes":[149],"procedural":[150],"simulation,":[151],"real-world":[152],"cinematic":[153],"footage,":[154],"generative":[156],"data":[157],"implicitly":[159],"learn":[160],"physically":[161],"plausible":[162],"illumination":[163],"shadow":[165],"harmonization.":[166],"This":[167],"design":[169],"handles":[170],"diverse":[171],"product":[174],"photos":[175],"subjects":[178],"achieving":[179],"high-fidelity":[180],"environmental":[184],"without":[186],"need":[188],"explicit":[190],"3D":[191],"reconstruction":[192],"auxiliary":[194],"learnable":[195],"adapters.":[196],"Extensive":[197],"experiments":[198],"demonstrate":[199],"FlexComposer":[201],"outperforms":[202],"state-of-the-art":[203],"methods":[204],"in":[205],"quality,":[207],"temporal":[208],"consistency,":[209],"trajectory":[211],"adherence.":[212]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2026-08-04T00:00:00"}