{"id":"https://openalex.org/W4417221662","doi":"https://doi.org/10.1109/iccv51701.2025.01153","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","display_name":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417221662","doi":"https://doi.org/10.1109/iccv51701.2025.01153"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01153","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/2503.14489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jensen Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jensen Zhou","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012620879","display_name":"Hang Gao","orcid":"https://orcid.org/0000-0002-1163-5533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Gao","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013102998","display_name":"Vikram Voleti","orcid":"https://orcid.org/0000-0003-0941-7227"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikram Voleti","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106276631","display_name":"Aaryaman Vasishta","orcid":"https://orcid.org/0000-0002-8037-9350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aaryaman Vasishta","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101059709","display_name":"Chun-Han Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun-Han Yao","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019170551","display_name":"Mark Boss","orcid":"https://orcid.org/0000-0001-7515-4934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Boss","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109615038","display_name":"Philip Torr","orcid":"https://orcid.org/0000-0001-5545-7217"},"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":"Philip Torr","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083153177","display_name":"Christian Rupprecht","orcid":"https://orcid.org/0000-0003-3994-8045"},"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":"Christian Rupprecht","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085870393","display_name":"Varun Jampani","orcid":"https://orcid.org/0000-0002-1508-6498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varun Jampani","raw_affiliation_strings":["Stability AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"12405","last_page":"12414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.43220001459121704,"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":0.43220001459121704,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2903999984264374,"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/T11019","display_name":"Image Enhancement Techniques","score":0.07010000199079514,"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/task","display_name":"Task (project management)","score":0.6348999738693237},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6305000185966492},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5651999711990356},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.548799991607666},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4932999908924103},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46880000829696655},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44290000200271606},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44040000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6348999738693237},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5651999711990356},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.548799991607666},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4932999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44290000200271606},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41990000009536743},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25279998779296875},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01153","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:2503.14489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14489","pdf_url":"https://arxiv.org/pdf/2503.14489","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.2503.14489","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.14489","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.14489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14489","pdf_url":"https://arxiv.org/pdf/2503.14489","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"Stable":[2],"Virtual":[3],"Camera":[4],"(Seva),":[5],"a":[6,15,71,105],"generalist":[7],"diffusion":[8],"model":[9,52],"that":[10,61,94,114],"creates":[11],"novel":[12],"views":[13,22],"of":[14,20],"scene,":[16],"given":[17],"any":[18],"number":[19],"input":[21],"and":[23,57,122,128],"target":[24],"cameras.":[25],"Existing":[26],"works":[27],"struggle":[28],"to":[29,103],"generate":[30,98],"either":[31],"large":[32],"viewpoint":[33],"changes":[34],"or":[35],"temporally":[36],"smooth":[37],"samples,":[38],"while":[39],"relying":[40],"on":[41],"specific":[42],"task":[43],"configurations.":[44],"Our":[45],"approach":[46],"overcomes":[47],"these":[48],"limitations":[49],"through":[50],"simple":[51],"design,":[53],"optimized":[54],"training":[55],"recipe,":[56],"flexible":[58],"sampling":[59],"strategy":[60],"generalize":[62],"across":[63,119],"view":[64,86],"synthesis":[65,87],"tasks":[66],"at":[67],"test":[68],"time.":[69],"As":[70],"result,":[72],"our":[73,95],"samples":[74],"maintain":[75],"high":[76],"consistency":[77],"without":[78],"requiring":[79],"additional":[80],"3D":[81],"representation-based":[82],"distillation,":[83],"thus":[84],"streamlining":[85],"in":[88],"the":[89],"wild.":[90],"Furthermore,":[91],"we":[92],"show":[93],"method":[96],"can":[97],"high-quality":[99],"videos":[100],"lasting":[101],"up":[102],"half":[104],"minute":[106],"with":[107,126],"seamless":[108],"loop":[109],"closure.":[110],"Extensive":[111],"benchmarking":[112],"demonstrates":[113],"Seva":[115],"outperforms":[116],"existing":[117],"methods":[118],"different":[120],"datasets":[121],"settings.":[123],"Project":[124],"page":[125],"code":[127],"model:":[129],"https://stable-virtual-camera.github.io/.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
