{"id":"https://openalex.org/W4408354596","doi":"https://doi.org/10.1109/icassp49660.2025.10890226","title":"DreamHA: Towards High-Quality Human Animation with Image-to-Video Diffusion Models","display_name":"DreamHA: Towards High-Quality Human Animation with Image-to-Video Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354596","doi":"https://doi.org/10.1109/icassp49660.2025.10890226"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5089703326","display_name":"L. G. Shao","orcid":"https://orcid.org/0009-0007-9950-8443"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longran Shao","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047775656","display_name":"Bonan Li","orcid":"https://orcid.org/0009-0004-1496-4166"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bonan Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046469888","display_name":"Congying Han","orcid":"https://orcid.org/0000-0002-3445-4620"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congying Han","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085927257","display_name":"Wenzhao Liu","orcid":"https://orcid.org/0000-0001-7506-0663"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhao Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059320585","display_name":"Tiande Guo","orcid":"https://orcid.org/0000-0002-3804-9163"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiande Guo","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068062033","display_name":"T. Y. Xing","orcid":"https://orcid.org/0009-0005-2294-1068"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchi Xing","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035749919","display_name":"Xinmin Qiu","orcid":"https://orcid.org/0009-0007-8820-5797"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinmin Qiu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072007173","display_name":"Zicheng Zhang","orcid":"https://orcid.org/0000-0003-0665-5270"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5089703326"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0431916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9979000091552734,"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":0.9979000091552734,"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":0.9968000054359436,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582288980484009},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6940250396728516},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.6828501224517822},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5330551862716675},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5020427703857422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4447352886199951},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.41552478075027466},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41203773021698},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3615954518318176},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35760563611984253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582288980484009},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6940250396728516},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.6828501224517822},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5330551862716675},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5020427703857422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447352886199951},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.41552478075027466},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41203773021698},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3615954518318176},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35760563611984253},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2884460600","https://openalex.org/W2962785568","https://openalex.org/W2963092440","https://openalex.org/W2963917969","https://openalex.org/W3178284600","https://openalex.org/W3180355996","https://openalex.org/W4312400623","https://openalex.org/W4312473638","https://openalex.org/W4312933868","https://openalex.org/W4388190237","https://openalex.org/W4390874168","https://openalex.org/W4402704510","https://openalex.org/W4402716255","https://openalex.org/W4402727180","https://openalex.org/W4404719810","https://openalex.org/W4409367615","https://openalex.org/W6726983635","https://openalex.org/W6765779288","https://openalex.org/W6767264202","https://openalex.org/W6768910476","https://openalex.org/W6779810587","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6791353385","https://openalex.org/W6838639034","https://openalex.org/W6843180743","https://openalex.org/W6851800889","https://openalex.org/W6853059638","https://openalex.org/W6855459923","https://openalex.org/W6858340613","https://openalex.org/W6858529799","https://openalex.org/W6861400146","https://openalex.org/W6869023397","https://openalex.org/W6872817574","https://openalex.org/W6873371640"],"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/W2103375294","https://openalex.org/W1823321090","https://openalex.org/W2378792725"],"abstract_inverted_index":{"Recent":[0],"diffusion":[1,90,114],"models":[2,24,91,115],"have":[3],"made":[4],"significant":[5],"advancements":[6],"in":[7,36,116],"generating":[8],"lifelike":[9],"videos":[10],"from":[11,43,56],"driving":[12,54],"signals,":[13],"including":[14],"a":[15,19,97],"reference":[16],"character":[17,37],"and":[18,41,72,81,132,149],"skeleton":[20],"sequence.":[21],"Nevertheless,":[22],"these":[23],"often":[25],"struggle":[26],"with":[27,92],"maintaining":[28],"fidelity,":[29],"as":[30],"the":[31,44,51,57,61,66,104,111],"generated":[32],"results":[33,138],"frequently":[34],"deviate":[35],"features,":[38],"e.g.,":[39],"appearance":[40,119],"identity":[42,134],"reference.":[45],"We":[46],"attribute":[47],"this":[48,86],"issue":[49],"to":[50,76,84,102,127],"use":[52],"of":[53,107,113],"signals":[55],"same":[58],"individual":[59],"during":[60],"training":[62,108],"process,":[63],"which":[64],"biases":[65],"model":[67],"towards":[68],"skeleton-based":[69],"shape":[70,105],"features":[71],"limits":[73],"its":[74],"capacity":[75],"fully":[77],"exploit":[78],"character-specific":[79],"information,":[80],"propose":[82],"DreamHA":[83,88],"address":[85],"issue.":[87],"incorporates":[89],"Rigid":[93],"Transformation":[94],"Augmentation":[95],"(RTAug),":[96],"simple":[98],"yet":[99],"effective":[100],"technique":[101],"perturb":[103],"characteristics":[106],"data,":[109],"improving":[110],"capability":[112],"capturing":[117],"basic":[118],"features.":[120],"Additionally,":[121],"we":[122],"introduce":[123],"Identity":[124],"Keeper":[125],"(IK)":[126],"provide":[128],"fine-grained":[129],"facial":[130],"control":[131],"enhance":[133],"consistency.":[135],"Extensive":[136],"experimental":[137],"demonstrate":[139],"that":[140],"our":[141],"method":[142],"outperforms":[143],"state-of-the-art":[144],"approaches,":[145],"producing":[146],"more":[147],"faithful":[148],"consistent":[150],"animations.":[151]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
