{"id":"https://openalex.org/W4406272370","doi":"https://doi.org/10.1109/iccv51701.2025.01334","title":"Perception-as-Control: Fine-Grained Controllable Image Animation with 3D-Aware Motion Representation","display_name":"Perception-as-Control: Fine-Grained Controllable Image Animation with 3D-Aware Motion Representation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406272370","doi":"https://doi.org/10.1109/iccv51701.2025.01334"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01334","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.05020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101769380","display_name":"Yingjie Chen","orcid":"https://orcid.org/0000-0003-2361-3291"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingjie Chen","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036805135","display_name":"Yifang Men","orcid":"https://orcid.org/0000-0003-2495-2869"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifang Men","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103072099","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0002-3616-2496"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Yao","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564882","display_name":"Miaomiao Cui","orcid":"https://orcid.org/0000-0001-5546-3967"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaomiao Cui","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085032007","display_name":"Liefeng Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liefeng Bo","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101769380"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00880932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14380","last_page":"14389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9878000020980835,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9822999835014343,"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/representation","display_name":"Representation (politics)","score":0.787050187587738},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7593898773193359},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.734490692615509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6066927909851074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.570254921913147},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5554514527320862},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5550951361656189},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5292341709136963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019469261169434},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45250874757766724},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19791319966316223},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.05840221047401428}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.787050187587738},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7593898773193359},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.734490692615509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6066927909851074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.570254921913147},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5554514527320862},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5550951361656189},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5292341709136963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019469261169434},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45250874757766724},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19791319966316223},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.05840221047401428},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01334","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:2501.05020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05020","pdf_url":"https://arxiv.org/pdf/2501.05020","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.2501.05020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.05020","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:2501.05020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05020","pdf_url":"https://arxiv.org/pdf/2501.05020","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310844315","https://openalex.org/W2532377291","https://openalex.org/W2000013817","https://openalex.org/W4296190881","https://openalex.org/W2366362996","https://openalex.org/W2517624617","https://openalex.org/W2378422373","https://openalex.org/W2129566390","https://openalex.org/W2360905385","https://openalex.org/W2215755978"],"abstract_inverted_index":{"Motion-controllable":[0],"image":[1,56],"animation":[2,57],"is":[3],"a":[4,8,74,126],"fundamental":[5],"task":[6],"with":[7,41],"wide":[9],"range":[10],"of":[11,135],"potential":[12],"applications.":[13],"Recent":[14],"works":[15],"have":[16],"made":[17],"progress":[18],"in":[19,125],"controlling":[20],"camera":[21,36,93],"or":[22],"object":[23,38,95],"motion":[24,27,39,51,65,71,113],"via":[25],"various":[26,120],"representations,":[28],"while":[29],"they":[30],"still":[31],"struggle":[32],"to":[33,61,118,147],"support":[34,119],"collaborative":[35,64],"and":[37,53,84,94,101,128,142],"control":[40,43,114],"adaptive":[42],"granularity.":[44],"To":[45],"this":[46,91],"end,":[47],"we":[48,68],"introduce":[49],"3D-aware":[50,70],"representation":[52,72],"propose":[54],"an":[55],"framework,":[58],"called":[59],"Perception-as-Control,":[60],"achieve":[62],"fine-grained":[63],"control.":[66],"Specifically,":[67],"construct":[69],"from":[73,87],"reference":[75],"image,":[76],"manipulate":[77],"it":[78,86,117],"based":[79],"on":[80],"interpreted":[81],"user":[82],"instructions,":[83],"perceive":[85],"different":[88],"viewpoints.":[89],"In":[90],"way,":[92],"motions":[96],"are":[97],"transformed":[98],"into":[99],"intuitive":[100],"consistent":[102],"visual":[103],"changes.":[104],"Then,":[105],"our":[106,148],"framework":[107],"leverages":[108],"the":[109,133,136],"perception":[110],"results":[111],"as":[112],"signals,":[115],"enabling":[116],"motion-related":[121],"video":[122],"synthesis":[123],"tasks":[124],"unified":[127],"flexible":[129],"way.":[130],"Experiments":[131],"demonstrate":[132],"superiority":[134],"proposed":[137],"approach.":[138],"For":[139],"more":[140],"details":[141],"qualitative":[143],"results,":[144],"please":[145],"refer":[146],"anonymous":[149],"project":[150],"webpage:":[151],"https://chen-yingjie.github.io/projects/Perception-as-Control.":[152]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
