{"id":"https://openalex.org/W4408351875","doi":"https://doi.org/10.1109/icassp49660.2025.10887583","title":"DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance","display_name":"DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351875","doi":"https://doi.org/10.1109/icassp49660.2025.10887583"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887583","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":"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/A5100390494","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0002-6068-0103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Sun Yat-Sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091310860","display_name":"Jiaxi Gu","orcid":"https://orcid.org/0000-0002-6201-9503"},"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":"Jiaxi Gu","raw_affiliation_strings":["Huawei,Noah’ark Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,Noah’ark Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043898209","display_name":"Panwen Hu","orcid":"https://orcid.org/0000-0001-6183-6598"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panwen Hu","raw_affiliation_strings":["The Chinese University of Hong Kong at Shenzhen,School of Science and Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong at Shenzhen,School of Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021895690","display_name":"Yuanfan Guo","orcid":"https://orcid.org/0000-0002-5835-8545"},"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":"Yuanfan Guo","raw_affiliation_strings":["Huawei,Noah’ark Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,Noah’ark Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961088","display_name":"Xiao Dong","orcid":"https://orcid.org/0000-0001-9519-612X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Dong","raw_affiliation_strings":["Sun Yat-Sen University at Zhuhai,School of Intelligent Engineering,Zhuhai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University at Zhuhai,School of Intelligent Engineering,Zhuhai,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102619815","display_name":"Hang Xu","orcid":"https://orcid.org/0009-0006-0421-0576"},"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’ark Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei,Noah’ark Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Sun Yat-Sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9930999875068665,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9930999875068665,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9868000149726868,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9746999740600586,"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":0.724153995513916},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.527032196521759},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.511405885219574},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.497090607881546},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47157755494117737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4505057632923126},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.41877004504203796},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32395026087760925},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08527502417564392},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08223491907119751}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724153995513916},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.527032196521759},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.511405885219574},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.497090607881546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47157755494117737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4505057632923126},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.41877004504203796},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32395026087760925},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08527502417564392},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08223491907119751},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887583","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2425121537","https://openalex.org/W2963524571","https://openalex.org/W3031246127","https://openalex.org/W4385259380","https://openalex.org/W4386065764","https://openalex.org/W4386076215","https://openalex.org/W4386076323","https://openalex.org/W4403021266","https://openalex.org/W6640963894","https://openalex.org/W6766759079"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W4224231624","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Image-to-video":[0],"generation,":[1],"which":[2,30],"aims":[3],"to":[4,33,100],"generate":[5,115],"a":[6,10,48,55,61],"video":[7,63],"starting":[8],"from":[9,24],"given":[11],"reference":[12,72,95],"image,":[13],"has":[14],"drawn":[15],"great":[16],"attention.":[17],"Existing":[18],"methods":[19],"frequently":[20],"integrate":[21],"semantic":[22],"information":[23],"images":[25],"or":[26],"simply":[27],"concatenate":[28],"images,":[29],"often":[31],"leads":[32],"low":[34],"fidelity":[35],"and":[36,77,134,137],"flickering":[37],"in":[38],"the":[39,71,79,82,91,94,101,108,131,145],"generated":[40],"videos.":[41],"To":[42],"tackle":[43],"these":[44],"problems,":[45],"we":[46],"propose":[47],"high-fidelity":[49],"image-to-video":[50],"generation":[51],"method":[52,143],"by":[53,106,121],"devising":[54],"frame":[56],"retention":[57],"branch":[58],"based":[59],"on":[60,130],"pre-trained":[62],"diffusion":[64],"model,":[65],"named":[66],"DreamVideo.":[67],"Our":[68],"DreamVideo":[69,113],"perceives":[70],"image":[73,96],"via":[74],"convolution":[75],"layers":[76],"concatenates":[78],"features":[80],"with":[81],"noisy":[83],"latents":[84],"as":[85],"model":[86],"input.":[87],"By":[88],"this":[89],"means,":[90],"details":[92],"of":[93,118],"can":[97,114],"be":[98],"preserved":[99],"greatest":[102],"extent.":[103],"In":[104],"addition,":[105],"incorporating":[107],"designed":[109],"double-condition":[110],"classifier-free":[111],"guidance,":[112],"high-quality":[116],"videos":[117],"different":[119],"actions":[120],"providing":[122],"varying":[123],"prompt":[124],"texts.":[125],"We":[126],"conduct":[127],"comprehensive":[128],"experiments":[129],"public":[132],"datasets,":[133],"both":[135],"quantitative":[136],"qualitative":[138],"results":[139],"indicate":[140],"that":[141],"our":[142],"outperforms":[144],"state-of-the-art":[146],"method.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}