{"id":"https://openalex.org/W4413144558","doi":"https://doi.org/10.1109/cvpr52734.2025.02130","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","display_name":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144558","doi":"https://doi.org/10.1109/cvpr52734.2025.02130"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009476152","display_name":"Sherwin Bahmani","orcid":"https://orcid.org/0009-0009-5724-3402"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sherwin Bahmani","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028188014","display_name":"Ivan Skorokhodov","orcid":"https://orcid.org/0000-0002-7611-9310"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Skorokhodov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032922702","display_name":"Guocheng Qian","orcid":"https://orcid.org/0000-0002-2935-8570"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guocheng Qian","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021757527","display_name":"Aliaksandr Siarohin","orcid":"https://orcid.org/0000-0001-9252-1775"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aliaksandr Siarohin","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052645912","display_name":"Willi Menapace","orcid":"https://orcid.org/0000-0002-0715-9300"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Willi Menapace","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037094498","display_name":"Andrea Tagliasacchi","orcid":"https://orcid.org/0000-0002-2209-7187"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrea Tagliasacchi","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004550709","display_name":"David B. Lindell","orcid":"https://orcid.org/0000-0002-6999-3958"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David B. Lindell","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058028206","display_name":"Sergey Tulyakov","orcid":"https://orcid.org/0000-0003-3465-1592"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Tulyakov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2359,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97078038,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"22875","last_page":"22889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9383999705314636,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6674699187278748},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5121800899505615},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5121498107910156},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49682024121284485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4126494228839874},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14680981636047363},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14515522122383118},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08695453405380249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674699187278748},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5121800899505615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5121498107910156},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49682024121284485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4126494228839874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14680981636047363},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14515522122383118},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08695453405380249}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.800000011920929,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319952","display_name":"Canada Foundation for Innovation","ror":"https://ror.org/000az4664"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"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":{"Numerous":[0],"works":[1],"have":[2],"recently":[3],"integrated":[4],"3D":[5,42,205],"camera":[6,15,30,43,56,101,116,126,164,185,219],"control":[7,16,165],"into":[8],"foundational":[9],"text-to-video":[10],"models,":[11],"but":[12],"the":[13,87,105,115,123,132,160,181,191,203,210],"resulting":[14],"is":[17,60],"often":[18],"imprecise,":[19],"and":[20,70,81,107,152,186,189],"video":[21,92,139,216],"generation":[22],"quality":[23],"suffers.":[24],"In":[25],"this":[26],"work,":[27],"we":[28,50,95,158],"analyze":[29],"motion":[31,53,82,188],"from":[32],"a":[33,109,129,143,168],"first":[34],"principles":[35],"perspective,":[36],"uncovering":[37],"insights":[38],"that":[39,52,97],"enable":[40],"precise":[41],"manipulation":[44],"without":[45],"compromising":[46],"synthesis":[47],"quality.":[48,83,156],"First,":[49],"determine":[51],"induced":[54],"by":[55,85],"movements":[57],"in":[58,62],"videos":[59,175],"low-frequency":[61],"nature.":[63],"This":[64,118,179],"motivates":[65],"us":[66,120],"to":[67,121,128,134,142,201],"adjust":[68],"train":[69],"test":[71],"pose":[72,102],"conditioning":[73,127],"schedules,":[74],"accelerating":[75],"training":[76,147,150],"convergence":[77],"while":[78],"improving":[79],"visual":[80,155],"Then,":[84],"probing":[86],"representations":[88],"of":[89,111,125,131,146,171,193],"an":[90],"unconditional":[91],"diffusion":[93],"transformer,":[94],"observe":[96],"they":[98],"implicitly":[99],"perform":[100],"estimation":[103],"under":[104],"hood,":[106],"only":[108],"sub-portion":[110],"their":[112],"layers":[113],"contain":[114],"information.":[117],"suggested":[119],"limit":[122],"injection":[124],"subset":[130],"architecture":[133],"prevent":[135],"interference":[136],"with":[137,167,176,218],"other":[138],"features,":[140],"leading":[141],"4\u00d7":[144],"reduction":[145],"parameters,":[148],"improved":[149],"speed,":[151],"10%":[153],"higher":[154],"Finally,":[157],"complement":[159],"typical":[161],"dataset":[162,170],"for":[163,214],"learning":[166],"curated":[169],"20K":[172],"diverse,":[173],"dynamic":[174],"stationary":[177],"cameras.":[178],"helps":[180],"model":[182,213],"distinguish":[183],"between":[184],"scene":[187],"improves":[190],"dynamics":[192],"generated":[194],"pose-conditioned":[195],"videos.":[196],"We":[197],"compound":[198],"these":[199],"findings":[200],"design":[202],"Advanced":[204],"Camera":[206],"Control":[207],"(AC3D)":[208],"architecture,":[209],"new":[211],"state-of-the-art":[212],"generative":[215],"modeling":[217],"control.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}