{"id":"https://openalex.org/W7164929613","doi":"https://doi.org/10.48550/arxiv.2606.15162","title":"GeoStream: Toward Precise Camera Controlled Streaming Video Generation","display_name":"GeoStream: Toward Precise Camera Controlled Streaming Video Generation","publication_year":2026,"publication_date":"2026-06-13","ids":{"openalex":"https://openalex.org/W7164929613","doi":"https://doi.org/10.48550/arxiv.2606.15162"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15162","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.15162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138696654","display_name":"Yizhou Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yizhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138713679","display_name":"Yifan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138695484","display_name":"Xiaoyuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035370488","display_name":"Yushu Wu","orcid":"https://orcid.org/0000-0001-9883-7973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yushu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138735262","display_name":"Hao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135341346","display_name":"Moayed Haji-Ali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haji-Ali, Moayed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079360389","display_name":"Rameen Abdal","orcid":"https://orcid.org/0000-0002-2177-8327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdal, Rameen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138700776","display_name":"Ashkan Mirzaei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirzaei, Ashkan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138732849","display_name":"Yanyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052645912","display_name":"Willi Menapace","orcid":"https://orcid.org/0000-0002-0715-9300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Menapace, Willi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138757878","display_name":"Laszlo Jeni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeni, Laszlo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138740673","display_name":"Sergey Tulyakov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tulyakov, Sergey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138714494","display_name":"Peter Wonka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wonka, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138700510","display_name":"Chaoyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chaoyang","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/T10531","display_name":"Advanced Vision and Imaging","score":0.5297999978065491,"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":0.5297999978065491,"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":0.27970001101493835,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.03269999846816063,"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/cache","display_name":"Cache","score":0.6154000163078308},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4733999967575073},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4717000126838684},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.421099990606308},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.40639999508857727},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.34389999508857727},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.3424000144004822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616999745368958},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6154000163078308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353999733924866},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C199996500","wikidata":"https://www.wikidata.org/wiki/Q14369636","display_name":"Pinhole camera model","level":4,"score":0.30090001225471497},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15162","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":"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":"doi:10.48550/arxiv.2606.15162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15162","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":"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"},"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":{"Accurate":[0],"interactive":[1],"camera":[2,15,67,205],"control":[3,21,68],"is":[4,82,128,190],"essential":[5],"for":[6,116],"video-based":[7],"world":[8],"models,":[9],"but":[10,30],"most":[11,96],"existing":[12,31],"approaches":[13],"learn":[14],"motion":[16],"implicitly,":[17],"leading":[18],"to":[19,101,109],"inaccurate":[20],"under":[22],"out-of-distribution":[23],"trajectories.":[24],"Explicit":[25],"geometric":[26,114,181],"conditioning":[27,115,124,149],"improves":[28,204],"controllability,":[29],"methods":[32],"are":[33],"non-autoregressive":[34],"and":[35,103,147,178,196],"rely":[36],"on":[37],"a":[38,61,77,138],"static":[39],"3D":[40,79],"cache":[41,80,188],"built":[42],"from":[43,86,94,131,192],"an":[44],"initial":[45],"frame,":[46,99],"which":[47],"becomes":[48],"ineffective":[49],"once":[50],"the":[51,55,87,95,106,120,123,132,145,162,165,179,187],"viewpoint":[52],"moves":[53],"beyond":[54],"original":[56],"frustum.":[57],"We":[58],"propose":[59],"GeoStream,":[60],"framework":[62],"that":[63,81,142,154,184,200],"enables":[64],"precise":[65],"metric-scale":[66],"in":[69],"autoregressive":[70,176],"streaming":[71],"video":[72],"generation.":[73],"Our":[74],"method":[75],"maintains":[76],"self-refreshing":[78],"periodically":[83],"updated":[84],"online":[85],"model's":[88],"own":[89,134],"outputs:":[90],"we":[91],"estimate":[92],"depth":[93],"recently":[97],"generated":[98,135,193],"unproject":[100],"3D,":[102],"reproject":[104],"into":[105],"target":[107],"view":[108],"produce":[110],"point":[111],"reprojections":[112],"as":[113],"subsequent":[117],"synthesis.":[118],"By":[119],"same":[121],"principle,":[122],"seen":[125],"during":[126],"training":[127],"also":[129],"rendered":[130],"student's":[133],"frames,":[136],"yielding":[137],"fully":[139],"on-policy":[140],"distillation":[141],"naturally":[143],"aligns":[144],"train":[146],"inference":[148],"distributions.":[150],"Unlike":[151],"prior":[152],"work":[153],"uses":[155],"off-policy":[156],"condition":[157],"noising,":[158],"our":[159,201],"approach":[160,202],"trains":[161],"model":[163],"against":[164],"exact":[166],"error":[167],"distribution":[168],"it":[169],"encounters":[170],"at":[171],"inference,":[172],"mitigating":[173],"both":[174],"standard":[175],"drift":[177],"second-order":[180],"feedback":[182],"loop":[183],"arises":[185],"when":[186],"itself":[189],"derived":[191],"outputs.":[194],"Quantitative":[195],"qualitative":[197],"results":[198],"show":[199],"substantially":[203],"controllability.":[206]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-17T00:00:00"}