{"id":"https://openalex.org/W4416032641","doi":"https://doi.org/10.1109/iccv51701.2025.01241","title":"I2V3D: Controllable Image-to-Video Generation with 3D Guidance","display_name":"I2V3D: Controllable Image-to-Video Generation with 3D Guidance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416032641","doi":"https://doi.org/10.1109/iccv51701.2025.01241"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.09733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100403357","display_name":"Zhiyuan Zhang","orcid":"https://orcid.org/0000-0003-3845-7420"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhang","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037612985","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-1819-8778"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft GenAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft GenAI","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013972536","display_name":"Jing Liao","orcid":"https://orcid.org/0000-0001-7014-5377"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Liao","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8556955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13360","last_page":"13371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6111999750137329,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6111999750137329,"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/T12290","display_name":"Human Motion and Animation","score":0.14910000562667847,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.12929999828338623,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/process","display_name":"Process (computing)","score":0.555400013923645},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.5295000076293945},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5110999941825867},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43720000982284546},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3822000026702881},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5972999930381775},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5940999984741211},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3790999948978424},{"id":"https://openalex.org/C66629338","wikidata":"https://www.wikidata.org/wiki/Q189177","display_name":"3D computer graphics","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.29490000009536743},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.2865000069141388},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.09733","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09733","pdf_url":"https://arxiv.org/pdf/2503.09733","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.09733","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.09733","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":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:2503.09733","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09733","pdf_url":"https://arxiv.org/pdf/2503.09733","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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"I2V3D,":[2],"a":[3,35,81,94,112],"novel":[4],"framework":[5,133,154],"for":[6,152],"animating":[7],"static":[8],"images":[9,142],"into":[10],"dynamic":[11],"videos":[12,63],"with":[13,53,71,147],"precise":[14],"3D":[15,22,87,145],"control,":[16],"leveraging":[17],"the":[18,32,54,129],"strengths":[19],"of":[20,34,57,131],"both":[21],"geometry":[23,146],"guidance":[24],"and":[25,50,76,105,107],"advanced":[26],"generative":[27,58,148],"models.":[28,149],"Our":[29],"approach":[30,114],"combines":[31],"precision":[33],"computer":[36],"graphics":[37],"pipeline,":[38],"enabling":[39],"accurate":[40],"control":[41],"over":[42],"elements":[43],"such":[44],"as":[45],"camera":[46],"movement,":[47],"object":[48],"rotation,":[49],"character":[51],"animation,":[52],"visual":[55],"fidelity":[56],"AI":[59],"to":[60,102],"produce":[61],"high-quality":[62,118,137],"from":[64,139],"coarsely":[65],"rendered":[66,100],"inputs.":[67],"To":[68],"support":[69],"animations":[70,138],"any":[72],"initial":[73],"start":[74],"point":[75],"extended":[77],"sequences,":[78],"we":[79],"adopt":[80],"two-stage":[82],"generation":[83],"process":[84],"guided":[85],"by":[86,143],"geometry:":[88],"1)":[89],"3D-Guided":[90,109],"Keyframe":[91],"Generation,":[92],"where":[93],"customized":[95],"image":[96],"diffusion":[97],"model":[98],"refines":[99],"keyframes":[101,122],"ensure":[103],"consistency":[104],"quality,":[106],"2)":[108],"Video":[110],"Interpolation,":[111],"training-free":[113],"that":[115],"generates":[116],"smooth,":[117],"video":[119],"frames":[120],"between":[121],"using":[123],"bidirectional":[124],"guidance.":[125],"Experimental":[126],"results":[127],"highlight":[128],"effectiveness":[130],"our":[132,153],"in":[134],"producing":[135],"controllable,":[136],"single":[140],"input":[141],"harmonizing":[144],"The":[150],"code":[151],"will":[155],"be":[156],"publicly":[157],"released.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}