{"id":"https://openalex.org/W4417265481","doi":"https://doi.org/10.48550/arxiv.2507.19138","title":"RealisVSR: Detail-enhanced Diffusion for Real-World 4K Video Super-Resolution","display_name":"RealisVSR: Detail-enhanced Diffusion for Real-World 4K Video Super-Resolution","publication_year":2025,"publication_date":"2025-07-25","ids":{"openalex":"https://openalex.org/W4417265481","doi":"https://doi.org/10.48550/arxiv.2507.19138"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.19138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19138","pdf_url":"https://arxiv.org/pdf/2507.19138","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.19138","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014417853","display_name":"Weisong Zhao","orcid":"https://orcid.org/0000-0003-3957-8590","observed_orcids":["https://orcid.org/0000-0003-3957-8590"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Weisong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110673609","display_name":"Jingkai Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405281272","display_name":"Alibaba DAMO Academy (China)","ror":"https://ror.org/0448px924","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405281272","https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Jingkai","raw_affiliation_strings":["DAMO Academy Ours RealisVSR RealisVSR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy Ours RealisVSR RealisVSR","institution_ids":["https://openalex.org/I4405281272"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632822","display_name":"Xiangyu Zhu","orcid":"https://orcid.org/0000-0002-4636-9677","observed_orcids":["https://orcid.org/0000-0002-4636-9677"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Zhu, Xiangyu","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences ,","State Key Laboratory of Multimodal Artificial Intelligence Systems , Institute of Automation , Chinese Academy of Science ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences ,","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems , Institute of Automation , Chinese Academy of Science ,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625507","display_name":"Weihua Chen","orcid":"https://orcid.org/0000-0002-0548-330X","observed_orcids":["https://orcid.org/0000-0002-0548-330X"]},"institutions":[{"id":"https://openalex.org/I4405281272","display_name":"Alibaba DAMO Academy (China)","ror":"https://ror.org/0448px924","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405281272","https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Weihua","raw_affiliation_strings":["DAMO Academy Ours RealisVSR RealisVSR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy Ours RealisVSR RealisVSR","institution_ids":["https://openalex.org/I4405281272"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419434","display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0000-0003-1630-6058","observed_orcids":["https://orcid.org/0000-0003-1630-6058","https://orcid.org/0009-0000-8886-509X"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Zhang, Xiao-Yu","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences ,","School of Cyber Security , University of Chinese Academy of Sciences ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences ,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences ,","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109299788","display_name":"Zhen Lei","orcid":"https://orcid.org/0000-0002-0791-189X","observed_orcids":["https://orcid.org/0000-0002-0791-189X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602033","display_name":"Fan Wang","orcid":"https://orcid.org/0000-0002-0757-0861","observed_orcids":["https://orcid.org/0000-0002-0757-0861"]},"institutions":[{"id":"https://openalex.org/I4405281272","display_name":"Alibaba DAMO Academy (China)","ror":"https://ror.org/0448px924","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405281272","https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Fan","raw_affiliation_strings":["DAMO Academy Ours RealisVSR RealisVSR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy Ours RealisVSR RealisVSR","institution_ids":["https://openalex.org/I4405281272"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9980000257492065,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9980000257492065,"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":0.0010000000474974513,"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/T11019","display_name":"Image Enhancement Techniques","score":0.00019999999494757503,"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/video-super-resolution","display_name":"video super-resolution","score":0.9959999918937683},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/high-frequency-detail-enhancement","display_name":"high-frequency detail enhancement","score":0.8500000238418579},{"id":"https://openalex.org/keywords/controlnet","display_name":"ControlNet","score":0.6309999823570251},{"id":"https://openalex.org/keywords/temporal-dynamics-modeling","display_name":"temporal dynamics modeling","score":0.6430000066757202},{"id":"https://openalex.org/keywords/wavelet-decomposition","display_name":"wavelet decomposition","score":0.902999997138977},{"id":"https://openalex.org/keywords/histogram-of-oriented-gradients","display_name":"histogram of oriented gradients","score":0.8899999856948853},{"id":"https://openalex.org/keywords/texture-restoration","display_name":"texture restoration","score":0.9309999942779541},{"id":"https://openalex.org/keywords/artifact-removal","display_name":"artifact removal","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796000003814697},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6525999903678894},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.635200023651123},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5827000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550599992275238},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4821999967098236},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.19138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19138","pdf_url":"https://arxiv.org/pdf/2507.19138","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.19138","doi":"https://doi.org/10.48550/arxiv.2507.19138","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.19138","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.19138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19138","pdf_url":"https://arxiv.org/pdf/2507.19138","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417265481.pdf","grobid_xml":"https://content.openalex.org/works/W4417265481.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4407794264"],"related_works":["https://openalex.org/W4390523408","https://openalex.org/W4406354408","https://openalex.org/W4415539348","https://openalex.org/W4415251844","https://openalex.org/W7160080807","https://openalex.org/W6979294374","https://openalex.org/W7084071185","https://openalex.org/W4416922899","https://openalex.org/W7143530024","https://openalex.org/W4417536267"],"abstract_inverted_index":{"Video":[0],"Super-Resolution":[1],"(VSR)":[2],"has":[3],"achieved":[4],"significant":[5],"progress":[6],"through":[7],"diffusion":[8,79,96],"models,":[9],"effectively":[10],"addressing":[11],"the":[12,93,99,125,137,149],"over-smoothing":[13],"issues":[14],"inherent":[15],"in":[16,26,35,172],"GAN-based":[17],"methods.":[18],"Despite":[19],"recent":[20],"advances,":[21],"three":[22,82],"critical":[23],"challenges":[24],"persist":[25],"VSR":[27,129,160],"community:":[28],"1)":[29,85],"Inconsistent":[30],"modeling":[31],"of":[32,51,141,148],"temporal":[33],"dynamics":[34],"foundational":[36],"models;":[37],"2)":[38,107],"limited":[39],"high-frequency":[40,76],"detail":[41,52],"recovery":[42],"under":[43],"complex":[44,102],"real-world":[45],"degradations;":[46],"and":[47,54,101,104,116],"3)":[48,123],"insufficient":[49],"evaluation":[50],"enhancement":[53],"4K":[55,128],"super-resolution,":[56],"as":[57],"current":[58],"methods":[59],"primarily":[60],"rely":[61],"on":[62,159],"720P":[63],"datasets":[64],"with":[65,81,92],"inadequate":[66],"details.":[67],"To":[68],"address":[69],"these":[70],"challenges,":[71],"we":[72],"propose":[73],"RealisVSR,":[74],"a":[75],"detail-enhanced":[77],"video":[78,95],"model":[80,98],"core":[83],"innovations:":[84],"Consistency":[86],"Preserved":[87],"ControlNet":[88],"(CPC)":[89],"architecture":[90],"integrated":[91],"Wan2.1":[94],"to":[97,154],"smooth":[100],"motions":[103],"suppress":[105],"artifacts;":[106],"High-Frequency":[108],"Rectified":[109],"Diffusion":[110],"Loss":[111],"(HR-Loss)":[112],"combining":[113],"wavelet":[114],"decomposition":[115],"HOG":[117],"feature":[118],"constraints":[119],"for":[120],"texture":[121],"restoration;":[122],"RealisVideo-4K,":[124],"first":[126],"public":[127],"benchmark":[130],"containing":[131],"1,000":[132],"high-definition":[133],"video-text":[134],"pairs.":[135],"Leveraging":[136],"advanced":[138],"spatio-temporal":[139],"guidance":[140],"Wan2.1,":[142],"our":[143,169],"method":[144],"requires":[145],"only":[146],"5-25%":[147],"training":[150],"data":[151],"volume":[152],"compared":[153],"existing":[155],"approaches.":[156],"Extensive":[157],"experiments":[158],"benchmarks":[161],"(REDS,":[162],"SPMCS,":[163],"UDM10,":[164],"YouTube-HQ,":[165],"VideoLQ,":[166],"RealisVideo-720P)":[167],"demonstrate":[168],"superiority,":[170],"particularly":[171],"ultra-high-resolution":[173],"scenarios.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}