{"id":"https://openalex.org/W4407424966","doi":"https://doi.org/10.1109/tvcg.2026.3688720","title":"VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation","display_name":"VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4407424966","doi":"https://doi.org/10.1109/tvcg.2026.3688720","pmid":"https://pubmed.ncbi.nlm.nih.gov/42060437"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3688720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3688720","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.07531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090851249","display_name":"Sixiao Zheng","orcid":"https://orcid.org/0000-0001-8324-1528"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixiao Zheng","raw_affiliation_strings":["School of Data Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8324-1528","affiliations":[{"raw_affiliation_string":"School of Data Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zimian Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zimian Peng","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102322717","display_name":"Yanpeng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanpeng Zhou","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031030335","display_name":"Yi Zhu","orcid":"https://orcid.org/0000-0002-5586-3773"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhu","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066768790","display_name":"Hang Xu","orcid":"https://orcid.org/0000-0003-4176-0738"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102707341","display_name":"Xiangru Huang","orcid":"https://orcid.org/0000-0002-9793-3071"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangru Huang","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9533-9546","affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["School of Data Science and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6595-6893","affiliations":[{"raw_affiliation_string":"School of Data Science and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00689769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"7","first_page":"6842","last_page":"6856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9606000185012817,"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":0.9606000185012817,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9315000176429749,"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"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.902999997138977,"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/computer-vision","display_name":"Computer vision","score":0.6442615985870361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.572747528553009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.565578281879425},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45478853583335876},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44168806076049805}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6442615985870361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.572747528553009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.565578281879425},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45478853583335876},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44168806076049805}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tvcg.2026.3688720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3688720","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:42060437","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42060437","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null},{"id":"pmh:oai:arXiv.org:2502.07531","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2502.07531","pdf_url":"https://arxiv.org/pdf/2502.07531","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.07531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.07531","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.07531","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2502.07531","pdf_url":"https://arxiv.org/pdf/2502.07531","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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":{"Controllable":[0],"image-to-video":[1],"(I2V)":[2],"generation":[3],"transforms":[4],"a":[5,9,69,159],"reference":[6],"image":[7],"into":[8,115],"coherent":[10],"video":[11],"guided":[12],"by":[13],"user-specified":[14],"control":[15,19,90,181],"signals.":[16],"While":[17],"precise":[18],"over":[20,91],"camera":[21,92,107],"motion,":[22,24,82,93,95],"object":[23,94,113,122],"and":[25,47,60,71,83,88,96,157,183],"lighting":[26,97,129,132,154],"is":[27],"essential":[28],"for":[29,105,134],"high-fidelity":[30],"creation,":[31],"existing":[32],"methods":[33],"often":[34],"treat":[35],"these":[36],"factors":[37],"independently.":[38],"This":[39],"overlooks":[40],"the":[41,139,147],"physical":[42],"coupling":[43],"among":[44,80],"viewpoint,":[45],"geometry,":[46,81],"illumination":[48],"in":[49,180],"dynamic":[50],"scenes,":[51],"leading":[52],"to":[53,119],"visual":[54,184],"inconsistencies":[55],"such":[56],"as":[57],"mismatched":[58],"shadows":[59],"perspective":[61],"drift":[62],"under":[63],"simultaneous":[64],"changes.":[65],"We":[66],"present":[67],"VidCRAFT3,":[68],"unified":[70],"flexible":[72],"I2V":[73],"framework":[74],"that":[75,164,175],"explicitly":[76],"models":[77],"cross-factor":[78],"interactions":[79],"illumination,":[84],"enabling":[85],"both":[86],"independent":[87],"joint":[89,170],"direction.":[98],"Image2Cloud":[99],"provides":[100],"explicit":[101],"3D":[102],"geometric":[103],"priors":[104],"accurate":[106,152],"motion":[108,117],"control.":[109],"ObjMotionNet":[110],"encodes":[111],"sparse":[112],"trajectories":[114],"multi-scale":[116],"features":[118],"guide":[120],"realistic":[121],"motion.":[123],"A":[124],"Spatial":[125],"Triple-Attention":[126],"Transformer":[127],"integrates":[128],"direction":[130,155],"through":[131],"cross-attention":[133],"consistent":[135],"relighting.":[136],"To":[137],"address":[138],"scarcity":[140],"of":[141],"jointly":[142],"annotated":[143],"data,":[144],"we":[145],"construct":[146],"VideoLightingDirection":[148],"(VLD)":[149],"dataset":[150],"with":[151],"per-frame":[153],"annotations,":[156],"introduce":[158],"three-stage":[160],"progressive":[161],"training":[162],"strategy":[163],"enables":[165],"robust":[166],"learning":[167],"without":[168],"fully":[169],"annotations.":[171],"Extensive":[172],"experiments":[173],"demonstrate":[174],"VidCRAFT3":[176],"achieves":[177],"state-of-the-art":[178],"performance":[179],"precision":[182],"coherence":[185],"across":[186],"diverse":[187],"scenarios.":[188]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}