{"id":"https://openalex.org/W4415540184","doi":"https://doi.org/10.1145/3746027.3754776","title":"Enhanced Motion-aware Latent Diffusion Models for Video Frame Interpolation","display_name":"Enhanced Motion-aware Latent Diffusion Models for Video Frame Interpolation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540184","doi":"https://doi.org/10.1145/3746027.3754776"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5101113352","display_name":"Zhilin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhilin Huang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034643682","display_name":"Chujun Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chujun Qin","raw_affiliation_strings":["China Southern Power Grid Co., Ltd., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"China Southern Power Grid Co., Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I74872605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045346394","display_name":"Yifei Xing","orcid":"https://orcid.org/0000-0002-5206-9515"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Xing","raw_affiliation_strings":["University of Chinese Academy of Sciences, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026184280","display_name":"Wenming Yang","orcid":"https://orcid.org/0000-0002-2506-1286"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101113352"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30708236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2811","last_page":"2820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9990000128746033,"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":0.9965000152587891,"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/prior-probability","display_name":"Prior probability","score":0.6506999731063843},{"id":"https://openalex.org/keywords/motion-interpolation","display_name":"Motion interpolation","score":0.6438000202178955},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4336000084877014},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42289999127388},{"id":"https://openalex.org/keywords/inter-frame","display_name":"Inter frame","score":0.41670000553131104},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.36410000920295715},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.3619999885559082}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7616999745368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7382000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863999962806702},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6506999731063843},{"id":"https://openalex.org/C72560505","wikidata":"https://www.wikidata.org/wiki/Q204510","display_name":"Motion interpolation","level":5,"score":0.6438000202178955},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5246000289916992},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.41670000553131104},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.2712000012397766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.2581999897956848},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":12,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2147253850","https://openalex.org/W2769654144","https://openalex.org/W2904275768","https://openalex.org/W2964156315","https://openalex.org/W3004970274","https://openalex.org/W3013522332","https://openalex.org/W3096831136","https://openalex.org/W4285604424","https://openalex.org/W4382240059","https://openalex.org/W4386071957","https://openalex.org/W4386072096"],"related_works":[],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,113],"video":[3,11,102],"frame":[4,103,126],"interpolation":[5],"(VFI)":[6],"methods":[7,32,47],"is":[8,72],"to":[9,53,59,64,77,83,118,143],"enhance":[10,60],"fluency":[12],"and":[13,134,149,161,178,182],"visual":[14],"quality":[15],"by":[16],"generating":[17,79],"intermediate":[18],"frames":[19,23],"between":[20,68,146],"consecutive":[21],"original":[22],"based":[24],"on":[25,167],"the":[26,61,84,111,120,139,147],"source":[27],"video.":[28],"Recently,":[29],"diffusion-based":[30],"VFI":[31,75],"have":[33,48],"made":[34],"promising":[35],"progresses,":[36],"with":[37],"generated":[38],"results":[39,81],"performing":[40],"well":[41],"in":[42,141],"perceptual":[43],"quality.":[44],"However,":[45],"these":[46],"not":[49],"fully":[50],"explored":[51],"how":[52],"effectively":[54,154],"leverage":[55],"external":[56],"motion":[57,66,85,108,144,156,159],"priors":[58,109,145],"model's":[62],"ability":[63],"estimate":[65],"information":[67,121],"adjacent":[69],"frames,":[70],"which":[71],"crucial":[73],"for":[74,101],"models":[76],"avoid":[78],"blurry":[80],"due":[82],"ambiguity.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90,106,129],"propose":[91,130],"an":[92],"Enhanced":[93],"Motion-Aware":[94],"latent":[95],"Diffusion":[96],"model":[97],"(":[98],"EMADiff":[99,153,171],")":[100],"interpolation.":[104],"Specifically,":[105],"integrate":[107],"into":[110],"decoder":[112],"vector-quantized":[114],"enhanced":[115,131],"motion-aware":[116,132],"GAN":[117],"guide":[119],"propagation":[122],"during":[123],"RGB":[124],"interpolated":[125],"reconstruction.":[127],"Furthermore,":[128],"noising":[133],"de-noising":[135],"procedures.":[136],"By":[137],"reducing":[138],"discrepancy":[140],"attention":[142],"forward":[148],"reverse":[150],"processes,":[151],"our":[152],"utilizes":[155],"priors,":[157],"alleviates":[158],"ambiguity,":[160],"generates":[162],"realistic":[163],"content.":[164],"Comprehensive":[165],"experiments":[166],"benchmark":[168],"datasets":[169],"show":[170],"achieves":[172],"state-of-the-art":[173],"performance,":[174],"surpassing":[175],"existing":[176],"approaches":[177],"producing":[179],"visually":[180],"plausible":[181],"content-clear":[183],"results.":[184]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}