{"id":"https://openalex.org/W7106714266","doi":"https://doi.org/10.48550/arxiv.2511.18991","title":"Do View-Consistent Representations Matter for Camera-Controlled Video Generation?","display_name":"Do View-Consistent Representations Matter for Camera-Controlled Video Generation?","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W7106714266","doi":"https://doi.org/10.48550/arxiv.2511.18991"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.18991","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.18991","pdf_url":"https://arxiv.org/pdf/2511.18991","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.18991","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Danier, Duolikun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Danier, Duolikun","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gao, Ge","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gao, Ge","raw_affiliation_strings":["University of Bristol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zeng, Chengxi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Chengxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"McDonagh, Steven","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"McDonagh, Steven","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101794527","display_name":"Changjian Li","orcid":"https://orcid.org/0000-0003-0448-4957","observed_orcids":["https://orcid.org/0000-0003-0448-4957"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li, Changjian","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bilen, Hakan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bilen, Hakan","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063600180","display_name":"Oisin Mac Aodha","orcid":"https://orcid.org/0000-0002-5787-5073","observed_orcids":["https://orcid.org/0000-0002-5787-5073"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mac Aodha, Oisin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"cited_by_count":3,"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":9.999999747378752e-05,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.0,"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/text-to-video-diffusion-models","display_name":"text-to-video diffusion models","score":0.8579999804496765},{"id":"https://openalex.org/keywords/view-consistency","display_name":"view consistency","score":0.8500000238418579},{"id":"https://openalex.org/keywords/3d-consistency","display_name":"3D consistency","score":0.9229999780654907}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7093999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002000212669373},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6348000168800354},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6330000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896000266075134},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2778852477","wikidata":"https://www.wikidata.org/wiki/Q313614","display_name":"Video camera","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2782000005245209},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.18991","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.18991","pdf_url":"https://arxiv.org/pdf/2511.18991","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.18991","doi":"https://doi.org/10.48550/arxiv.2511.18991","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.18991","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.18991","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.18991","pdf_url":"https://arxiv.org/pdf/2511.18991","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5730701950","display_name":null,"funder_award_id":"EP/W002876/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7106714266.pdf","grobid_xml":"https://content.openalex.org/works/W7106714266.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W4297750695","https://openalex.org/W4309957684","https://openalex.org/W4388093548","https://openalex.org/W4389115686","https://openalex.org/W4399424705","https://openalex.org/W4405096483","https://openalex.org/W4405956131","https://openalex.org/W4406191642","https://openalex.org/W4407386092","https://openalex.org/W4409092337","https://openalex.org/W4414928226","https://openalex.org/W4415061904","https://openalex.org/W4415235513","https://openalex.org/W4415237773","https://openalex.org/W4416288893","https://openalex.org/W4417076071","https://openalex.org/W4417308036","https://openalex.org/W6910583889","https://openalex.org/W7196964656"],"related_works":["https://openalex.org/W4411726008","https://openalex.org/W4413158471","https://openalex.org/W4392971764","https://openalex.org/W4399424705","https://openalex.org/W4416288893","https://openalex.org/W7159960520","https://openalex.org/W7127154787","https://openalex.org/W4399794937","https://openalex.org/W7164810819","https://openalex.org/W4402951568"],"abstract_inverted_index":{"Camera-controlled":[0],"video":[1,193],"generation":[2,101],"has":[3],"attracted":[4],"increasing":[5],"interest":[6],"for":[7,115,135,188],"its":[8],"applications":[9],"in":[10],"simulation,":[11],"gaming,":[12],"and":[13,23,99,159,169,190],"world":[14],"modeling.":[15],"However,":[16],"current":[17],"models":[18,60],"often":[19],"deform":[20],"rigid":[21],"objects":[22],"scene":[24],"structure":[25],"as":[26,118,184],"the":[27,42,85,112,140,147,157],"viewpoint":[28],"changes.":[29],"We":[30,71,144],"investigate":[31],"whether":[32],"this":[33,73],"failure":[34],"is":[35],"related":[36],"to":[37],"a":[38,49,77,125],"measurable":[39],"internal":[40,89,181],"property:":[41],"view":[43,86,178],"consistency":[44,87,153,179],"of":[45,52,88,180],"diffusion":[46,55,90,137,182],"representations.":[47],"Across":[48,94],"diverse":[50],"collection":[51],"camera-controlled":[53,95,97,126,192],"image-to-video":[54],"models,":[56],"we":[57,110],"find":[58],"that":[59,146],"exhibiting":[61,166],"more":[62,154],"view-consistent":[63],"representations":[64,138,183],"generate":[65],"videos":[66],"with":[67,76],"superior":[68],"3D":[69,107,152],"consistency.":[70,108],"complement":[72],"correlation-based":[74],"evidence":[75],"within-model":[78],"controlled":[79],"intervention,":[80],"ViCoDR,":[81],"which":[82],"directly":[83],"supervises":[84],"representations,":[91],"during":[92],"training.":[93],"image-to-video,":[96],"text-to-video,":[98],"multi-view":[100],"tasks,":[102],"ViCoDR":[103,131,148],"consistently":[104],"improves":[105,150],"output":[106,151],"Finally,":[109],"evaluate":[111],"loss":[113,149],"used":[114],"these":[116,175],"interventions":[117],"an":[119,185],"auxiliary":[120],"training":[121,142,172],"objective":[122],"by":[123],"retraining":[124],"I2V":[127],"model":[128],"using":[129],"either":[130],"or":[132],"existing":[133],"methods":[134],"supervising":[136],"under":[139],"same":[141],"setup.":[143],"show":[145],"reliably":[155],"than":[156],"alternatives":[158],"remains":[160],"effective":[161],"across":[162],"design":[163],"variants,":[164],"while":[165],"camera-control":[167],"trade-offs":[168],"requiring":[170],"additional":[171],"computation.":[173],"Together,":[174],"results":[176],"establish":[177],"important":[186],"property":[187],"analyzing":[189],"improving":[191],"generation.":[194],"Project":[195],"page:":[196],"https://danier97.github.io/ViCoDR.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-27T00:00:00"}
