{"id":"https://openalex.org/W4415975186","doi":"https://doi.org/10.1109/iccv51701.2025.01149","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","display_name":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415975186","doi":"https://doi.org/10.1109/iccv51701.2025.01149"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01149","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/2503.23368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101530688","display_name":"Xinyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xindi Yang","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008481358","display_name":"Baolu Li","orcid":"https://orcid.org/0009-0002-4741-8626"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baolu Li","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042229671","display_name":"Yiming Zhang","orcid":"https://orcid.org/0000-0002-9570-8962"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063953932","display_name":"Zhenfei Yin","orcid":"https://orcid.org/0000-0002-8666-1103"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhenfei Yin","raw_affiliation_strings":["Oxford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028486493","display_name":"Lei Bai","orcid":"https://orcid.org/0000-0003-3378-7201"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Bai","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027446640","display_name":"Liqian Ma","orcid":"https://orcid.org/0000-0002-0814-9876"},"institutions":[{"id":"https://openalex.org/I4210113141","display_name":"Krajsk\u00e1 nemocnice T. Bati","ror":"https://ror.org/02341a605","country_code":"CZ","type":"healthcare","lineage":["https://openalex.org/I4210113141"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Liqian Ma","raw_affiliation_strings":["ZMO AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZMO AI","institution_ids":["https://openalex.org/I4210113141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443935","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-8043-0312"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["The University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635804","display_name":"Jianfei Cai","orcid":"https://orcid.org/0000-0002-9444-3763"},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianfei Cai","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017857966","display_name":"Tien\u2010Tsin Wong","orcid":"https://orcid.org/0000-0002-7792-9307"},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tien-Tsin Wong","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102749145","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0003-3162-1929"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100296405","display_name":"Xu Jia","orcid":"https://orcid.org/0009-0009-6543-4188"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Jia","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"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":"12360","last_page":"12370"},"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":0.7448999881744385,"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":0.7448999881744385,"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":0.1445000022649765,"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":0.01640000008046627,"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/motion","display_name":"Motion (physics)","score":0.7153000235557556},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5274999737739563},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5092999935150146},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.42010000348091125},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.41940000653266907},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421000003814697},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4293999969959259},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.42010000348091125},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2669000029563904}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01149","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:2503.23368","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23368","pdf_url":"https://arxiv.org/pdf/2503.23368","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.2503.23368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.23368","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:2503.23368","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23368","pdf_url":"https://arxiv.org/pdf/2503.23368","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/G6950432041","display_name":null,"funder_award_id":"62441231,62472065,U23B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"diffusion":[1],"models":[2],"(VDMs)":[3],"have":[4],"advanced":[5],"significantly":[6],"in":[7,24,52,154],"recent":[8],"years,":[9],"enabling":[10],"the":[11,19,22,82,115,119,124,130,137,152,177],"generation":[12,68,132],"of":[13,21,47,49,133,180],"highly":[14],"realistic":[15],"videos":[16,41],"and":[17,55,76,99,173],"drawing":[18],"attention":[20],"community":[23],"their":[25,32],"potential":[26],"as":[27,92],"world":[28],"simulators.":[29],"However,":[30],"despite":[31],"capabilities,":[33],"VDMs":[34],"often":[35],"fail":[36],"to":[37,43,102,128,148,151],"produce":[38,169],"physically":[39,170],"plausible":[40,171],"due":[42],"an":[44],"inherent":[45],"lack":[46],"understanding":[48],"physics,":[50],"resulting":[51],"incorrect":[53],"dynamics":[54,112],"event":[56],"sequences.":[57],"To":[58],"address":[59],"this":[60],"limitation,":[61],"we":[62,85,122],"propose":[63],"a":[64,87,93,104,134],"novel":[65],"two-stage":[66],"image-to-video":[67],"framework":[69,167],"that":[70,108,165],"explicitly":[71],"incorporates":[72],"physics":[73],"with":[74,157],"vision":[75],"language":[77],"informed":[78],"physical":[79,111],"prior.":[80],"In":[81,118],"first":[83],"stage,":[84,121],"employ":[86],"Vision":[88],"Language":[89],"Model":[90],"(VLM)":[91],"coarse-grained":[94],"motion":[95,106,126,139,156],"planner,":[96],"integrating":[97],"chain-of-thought":[98],"physics-aware":[100],"reasoning":[101],"predict":[103],"rough":[105],"trajectories/changes":[107,127,140],"approximate":[109],"real-world":[110],"while":[113],"ensuring":[114],"inter-frame":[116],"consistency.":[117],"second":[120],"use":[123],"predicted":[125,138],"guide":[129],"video":[131,187],"VDM.":[135],"As":[136],"are":[141,189],"rough,":[142],"noise":[143],"is":[144],"added":[145],"during":[146],"inference":[147],"provide":[149],"freedom":[150],"VDM":[153],"generating":[155],"more":[158],"fine":[159],"details.":[160],"Extensive":[161],"experimental":[162],"results":[163,188],"demonstrate":[164],"our":[166,181,192],"can":[168],"motion,":[172],"comparative":[174],"evaluations":[175],"highlight":[176],"notable":[178],"superiority":[179],"approach":[182],"over":[183],"existing":[184],"methods.":[185],"More":[186],"available":[190],"on":[191],"Project":[193],"Page:":[194],"https://madaoer.github.io/projects/physically_plausible_video_generation.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
