{"id":"https://openalex.org/W7169165493","doi":"https://doi.org/10.1145/3799902.3811224","title":"ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation","display_name":"ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7169165493","doi":"https://doi.org/10.1145/3799902.3811224"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811224","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811224","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141022561","display_name":"Omar El Khalifi","orcid":"https://orcid.org/0009-0000-1116-4148"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar El Khalifi","raw_affiliation_strings":["Kinetix, Paris, France"],"raw_orcid":"https://orcid.org/0009-0000-1116-4148","affiliations":[{"raw_affiliation_string":"Kinetix, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140969889","display_name":"Thomas Rossi","orcid":"https://orcid.org/0009-0009-9650-4783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Rossi","raw_affiliation_strings":["Kinetix, Paris, France"],"raw_orcid":"https://orcid.org/0009-0009-9650-4783","affiliations":[{"raw_affiliation_string":"Kinetix, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120525330","display_name":"Oscar Fossey","orcid":"https://orcid.org/0009-0008-7426-8604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oscar Fossey","raw_affiliation_strings":["Kinetix, Paris, France"],"raw_orcid":"https://orcid.org/0009-0008-7426-8604","affiliations":[{"raw_affiliation_string":"Kinetix, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140998136","display_name":"Thibault Fouque","orcid":"https://orcid.org/0009-0003-5296-9366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thibault Fouque","raw_affiliation_strings":["Kinetix, Paris, France"],"raw_orcid":"https://orcid.org/0009-0003-5296-9366","affiliations":[{"raw_affiliation_string":"Kinetix, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099464035","display_name":"Ulysse Mizrahi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulysse Mizrahi","raw_affiliation_strings":["Kinetix, Paris, France"],"raw_orcid":"https://orcid.org/0009-0005-2795-2321","affiliations":[{"raw_affiliation_string":"Kinetix, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133952568","display_name":"Philip Torr","orcid":null},"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, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-0259-5732","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ivan Laptev","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-7072-3325","affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078065160","display_name":"Fabio Pizzati","orcid":"https://orcid.org/0000-0002-6249-5649"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fabio Pizzati","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-6249-5649","affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026169292","display_name":"Baptiste Bellot-Gurlet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baptiste Bellot-Gurlet","raw_affiliation_strings":["Kinetix, Paris, France"],"raw_orcid":"https://orcid.org/0009-0005-7062-6783","affiliations":[{"raw_affiliation_string":"Kinetix, Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5838000178337097},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5519000291824341},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/camera-auto-calibration","display_name":"Camera auto-calibration","score":0.42250001430511475},{"id":"https://openalex.org/keywords/video-camera","display_name":"Video camera","score":0.4187999963760376},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.37529999017715454},{"id":"https://openalex.org/keywords/stereo-camera","display_name":"Stereo camera","score":0.3450999855995178},{"id":"https://openalex.org/keywords/video-denoising","display_name":"Video denoising","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8273000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8026000261306763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659000158309937},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C94816000","wikidata":"https://www.wikidata.org/wiki/Q5026006","display_name":"Camera auto-calibration","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C2778852477","wikidata":"https://www.wikidata.org/wiki/Q313614","display_name":"Video camera","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C185078393","wikidata":"https://www.wikidata.org/wiki/Q313783","display_name":"Stereo camera","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.34360000491142273},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811224","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811224","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2045181334","https://openalex.org/W2128019145","https://openalex.org/W4386075924","https://openalex.org/W4390873054","https://openalex.org/W4400580599","https://openalex.org/W4402660110","https://openalex.org/W4402702984","https://openalex.org/W4402704510","https://openalex.org/W4409365923","https://openalex.org/W4413144558","https://openalex.org/W4413144792","https://openalex.org/W4413145386","https://openalex.org/W4413145529","https://openalex.org/W4413146013","https://openalex.org/W4413146118","https://openalex.org/W4413146321","https://openalex.org/W4413147048","https://openalex.org/W4413156376","https://openalex.org/W4415796819","https://openalex.org/W4415798286","https://openalex.org/W4415798521","https://openalex.org/W4415798699","https://openalex.org/W7160042079","https://openalex.org/W7160149202"],"related_works":[],"abstract_inverted_index":{"For":[0],"artistic":[1],"applications,":[2],"video":[3,27,38,76],"generation":[4,28],"requires":[5],"fine-grained":[6],"control":[7,47,159,198],"over":[8],"both":[9,115],"performance":[10],"and":[11,16,43,50,70,81,89,117,129,149,160,168,171,188,196],"cinematography\u2014i.e.,":[12],"the":[13,17,137],"actor\u2019s":[14],"motion":[15,34,169,197],"camera":[18,52,84,166,195],"trajectory.":[19],"We":[20,98,139,153],"present":[21],"ActCam,":[22],"a":[23,36,40,74,78,82,101,106],"zero-shot":[24],"method":[25],"for":[26],"that":[29,62,92,184],"jointly":[30],"(i)":[31],"transfers":[32],"character":[33,71,80,147],"from":[35],"driving":[37],"into":[39],"new":[41],"scene":[42,68,122],"(ii)":[44],"enables":[45],"per-frame":[46],"of":[48,67],"intrinsic":[49],"extrinsic":[51],"parameters.":[53],"ActCam":[54,86,141,164],"builds":[55],"on":[56,114,142],"any":[57],"pretrained":[58],"image-to-video":[59],"diffusion":[60],"model":[61],"accepts":[63],"conditioning":[64,108,187],"in":[65,174],"terms":[66],"depth":[69,90,119,126],"pose.":[72],"Given":[73],"source":[75],"with":[77,105],"moving":[79],"target":[83],"motion,":[85],"generates":[87],"pose":[88,116],"conditions":[91],"remain":[93],"geometrically":[94],"consistent":[95],"across":[96],"frames.":[97],"then":[99],"run":[100],"single":[102],"sampling":[103],"process":[104],"two-phase":[107],"schedule:":[109],"early":[110],"denoising":[111],"steps":[112],"condition":[113],"sparse":[118],"to":[120,157],"enforce":[121],"structure,":[123],"after":[124],"which":[125],"is":[127,172],"dropped":[128],"pose-only":[130,158],"guidance":[131,190],"refines":[132],"high-frequency":[133],"details":[134],"without":[135,199],"over-constraining":[136],"generation.":[138],"evaluate":[140],"multiple":[143],"benchmarks":[144],"spanning":[145],"diverse":[146],"motions":[148],"challenging":[150],"viewpoint":[151,179],"changes.":[152,180],"find":[154],"that,":[155],"compared":[156],"other":[161],"pose+camera":[162],"methods,":[163],"improves":[165],"adherence":[167],"fidelity,":[170],"preferred":[173],"human":[175],"evaluations\u2014especially":[176],"under":[177],"large":[178],"Our":[181],"results":[182],"highlight":[183],"careful":[185],"camera-consistent":[186],"staged":[189],"can":[191],"enable":[192],"strong":[193],"joint":[194],"training.":[200],"Project":[201],"page:":[202],"https://elkhomar.github.io/actcam/.":[203]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-07-17T00:00:00"}
