{"id":"https://openalex.org/W4415708193","doi":"https://doi.org/10.1109/icme59968.2025.11209876","title":"VividPose: Vividly 3D-driven Stable Pose Diffusion of High Facial Fidelity","display_name":"VividPose: Vividly 3D-driven Stable Pose Diffusion of High Facial Fidelity","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708193","doi":"https://doi.org/10.1109/icme59968.2025.11209876"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081181176","display_name":"Qilin Wang","orcid":null},"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":"Qilin Wang","raw_affiliation_strings":["Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101637347","display_name":"Zhengkai Jiang","orcid":"https://orcid.org/0000-0003-4064-994X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengkai Jiang","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102678899","display_name":"Chengming Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengming Xu","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381558","display_name":"Xinyi Zhang","orcid":"https://orcid.org/0000-0002-9307-1654"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101411638","display_name":"Yun Cao","orcid":"https://orcid.org/0009-0003-0618-4015"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Cao","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008990100","display_name":"Weijian Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijian Cao","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengjie Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009597034","display_name":"Zhanxiong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanxiong Wang","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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":["Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"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":"6"},"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":0.483599990606308,"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":0.483599990606308,"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/T11448","display_name":"Face recognition and analysis","score":0.44769999384880066,"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":0.025599999353289604,"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/rendering","display_name":"Rendering (computer graphics)","score":0.5830000042915344},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5156000256538391},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5134000182151794},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.43209999799728394},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.430400013923645},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42179998755455017},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.38600000739097595},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7649000287055969},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7638999819755554},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5830000042915344},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.43209999799728394},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.29809999465942383},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.2581000030040741},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W2966421984","https://openalex.org/W2969985801","https://openalex.org/W2978956737","https://openalex.org/W3175471114","https://openalex.org/W3178284600","https://openalex.org/W4312473638","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4390190334","https://openalex.org/W4390872896","https://openalex.org/W4390874168","https://openalex.org/W4402704510","https://openalex.org/W4402754210","https://openalex.org/W4402979707","https://openalex.org/W4402982288","https://openalex.org/W4404719810"],"related_works":[],"abstract_inverted_index":{"Human":[0],"image":[1,11],"animation":[2],"aims":[3],"to":[4,32],"generate":[5],"a":[6,9,14,22,100],"video":[7],"from":[8],"static":[10],"by":[12],"following":[13],"specified":[15],"pose":[16,102],"sequence.":[17],"Existing":[18],"methods":[19],"typically":[20],"adopt":[21],"multi-stage":[23],"pipeline":[24,48],"that":[25,55,73,104,124],"separately":[26],"learns":[27],"appearance":[28,33,71,81],"and":[29,35,87,95,109,114,120],"motion,":[30],"leading":[31],"degradation":[34],"temporal":[36,58],"inconsistencies.":[37],"To":[38,60,89],"address":[39],"these":[40],"issues,":[41],"we":[42,67,98],"propose":[43,68],"VividPose,":[44],"an":[45,69],"innovative":[46],"end-to-end":[47],"based":[49],"on":[50,117,136],"Stable":[51],"Video":[52],"Diffusion":[53],"(SVD)":[54],"ensures":[56],"superior":[57,133],"stability.":[59],"enhance":[61],"the":[62,118],"retention":[63],"of":[64],"human":[65,92],"identity,":[66],"identity-aware":[70],"controller":[72,103],"integrates":[74],"additional":[75],"facial":[76],"information":[77],"without":[78],"compromising":[79],"other":[80],"details":[82],"such":[83],"as":[84],"clothing":[85],"texture":[86],"background.":[88],"accommodate":[90],"diverse":[91],"body":[93],"shapes":[94],"hand":[96],"movements,":[97],"introduce":[99],"geometry-aware":[101],"utilizes":[105],"both":[106],"rendering":[107],"maps":[108],"skeleton":[110],"maps.":[111],"Extensive":[112],"qualitative":[113],"quantitative":[115],"experiments":[116],"UBCFashion":[119],"TikTok":[121],"benchmarks":[122],"demonstrate":[123],"our":[125,137],"method":[126],"achieves":[127],"state-of-the-art":[128],"performance.":[129],"Furthermore,":[130],"VividPose":[131],"exhibits":[132],"generalization":[134],"capabilities":[135],"proposed":[138],"in-the-wild":[139],"dataset.":[140],"Our":[141],"project":[142],"page":[143],"is":[144],"available":[145],"at":[146],"https://kelu007.github.io/vivid-pose.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}
