{"id":"https://openalex.org/W4409961710","doi":"https://doi.org/10.48550/arxiv.2504.02312","title":"OmniCam: Unified Multimodal Video Generation via Camera Control","display_name":"OmniCam: Unified Multimodal Video Generation via Camera Control","publication_year":2025,"publication_date":"2025-04-03","ids":{"openalex":"https://openalex.org/W4409961710","doi":"https://doi.org/10.48550/arxiv.2504.02312"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.02312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02312","pdf_url":"https://arxiv.org/pdf/2504.02312","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.02312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078055210","display_name":"Xiaoda Yang","orcid":"https://orcid.org/0000-0003-2282-6594"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Xiaoda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102197227","display_name":"Jie-Hong Xu","orcid":"https://orcid.org/0000-0002-1468-4285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jiayang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032822057","display_name":"Kaixuan Luan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luan, Kaixuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112476602","display_name":"Xinyu Zhan","orcid":"https://orcid.org/0009-0006-9120-9708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Xinyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101218526","display_name":"Hongshun Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Hongshun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058950651","display_name":"Shijun Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Shijun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348588","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-4019-3420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016058377","display_name":"Shuai Yang","orcid":"https://orcid.org/0000-0002-3577-5565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425671","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0002-9386-8938"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102777718","display_name":"Chansu Yu","orcid":"https://orcid.org/0000-0002-3318-9087"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Checheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010726528","display_name":"Cewu Lu","orcid":"https://orcid.org/0009-0003-7254-9318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Cewu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109632470","display_name":"Lixin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Lixin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5078055210"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9693999886512756,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9693999886512756,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9265000224113464,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9210000038146973,"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/computer-science","display_name":"Computer science","score":0.6171659231185913},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.543109655380249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44939878582954407},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.412203848361969},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.40534162521362305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6171659231185913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.543109655380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44939878582954407},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.412203848361969},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.40534162521362305}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.02312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02312","pdf_url":"https://arxiv.org/pdf/2504.02312","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.02312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.02312","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.02312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02312","pdf_url":"https://arxiv.org/pdf/2504.02312","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409961710.pdf","grobid_xml":"https://content.openalex.org/works/W4409961710.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Camera":[0],"control,":[1],"which":[2,101],"achieves":[3,120],"diverse":[4],"visual":[5],"effects":[6],"by":[7],"changing":[8],"camera":[9,40,74,88],"position":[10],"and":[11,26,47,77,111],"pose,":[12],"has":[13],"attracted":[14],"widespread":[15],"attention.":[16],"However,":[17],"existing":[18],"methods":[19],"face":[20],"challenges":[21],"such":[22],"as":[23,73,81],"complex":[24],"interaction":[25],"limited":[27],"control":[28,41,86],"capabilities.":[29],"To":[30,90],"address":[31],"these":[32],"issues,":[33],"we":[34,96],"present":[35],"OmniCam,":[36,95],"a":[37,103],"unified":[38],"multimodal":[39],"framework.":[42],"Leveraging":[43],"large":[44,104],"language":[45],"models":[46],"video":[48,69,80,126],"diffusion":[49],"models,":[50],"OmniCam":[51],"generates":[52],"spatio-temporally":[53],"consistent":[54],"videos.":[55],"It":[56],"supports":[57],"various":[58,129],"combinations":[59],"of":[60,94,106],"input":[61],"modalities:":[62],"the":[63,92,98],"user":[64],"can":[65],"provide":[66],"text":[67],"or":[68,79],"with":[70],"expected":[71],"trajectory":[72],"path":[75],"guidance,":[76],"image":[78],"content":[82],"reference,":[83],"enabling":[84],"precise":[85],"over":[87],"motion.":[89],"facilitate":[91],"training":[93],"introduce":[97],"OmniTr":[99],"dataset,":[100],"contains":[102],"collection":[105],"high-quality":[107,124],"long-sequence":[108],"trajectories,":[109],"videos,":[110],"corresponding":[112],"descriptions.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"that":[117],"our":[118],"model":[119],"state-of-the-art":[121],"performance":[122],"in":[123],"camera-controlled":[125],"generation":[127],"across":[128],"metrics.":[130]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
