{"id":"https://openalex.org/W4413145780","doi":"https://doi.org/10.1109/cvpr52734.2025.00692","title":"Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution","display_name":"Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145780","doi":"https://doi.org/10.1109/cvpr52734.2025.00692"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5058950651","display_name":"Shijun Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijun Shi","raw_affiliation_strings":["Jiangnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101829182","display_name":"Jing Xu","orcid":"https://orcid.org/0000-0002-3946-2056"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027728614","display_name":"Lijing Lu","orcid":"https://orcid.org/0000-0002-9039-0385"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijing Lu","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804803","display_name":"Zhihang Li","orcid":"https://orcid.org/0000-0002-9305-7924"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihang Li","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048675276","display_name":"Kai Hu","orcid":"https://orcid.org/0000-0001-7181-9935"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Hu","raw_affiliation_strings":["Jiangnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91204629,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7385","last_page":"7395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9972000122070312,"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":0.9972000122070312,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9794999957084656,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.6467186212539673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4822133779525757},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.47410091757774353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453653484582901},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34221553802490234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467186212539673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4822133779525757},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.47410091757774353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453653484582901},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34221553802490234}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Existing":[0],"diffusion-based":[1],"video":[2],"super-resolution":[3],"(VSR)":[4],"methods":[5],"are":[6],"susceptible":[7],"to":[8,19,103,124],"introducing":[9],"complex":[10],"degradations":[11],"and":[12,37,99,158],"noticeable":[13],"artifacts":[14,84],"into":[15,39],"high-resolution":[16],"videos":[17,121],"due":[18],"their":[20],"inherent":[21],"randomness.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,51,88],"propose":[27],"a":[28,57,68,90,111,117],"noise-robust":[29],"real-world":[30,146],"VSR":[31,126,137,147],"framework":[32],"by":[33],"incorporating":[34],"self-supervised":[35,91],"learning":[36,102],"Mamba":[38,135],"pre-trained":[40],"latent":[41],"diffusion":[42,54],"models.":[43],"To":[44,81],"ensure":[45],"content":[46],"consistency":[47],"across":[48],"adjacent":[49],"frames,":[50],"enhance":[52],"the":[53,63,151,154],"model":[55,156],"with":[56,67,132],"global":[58],"spatio-temporal":[59],"attention":[60],"mechanism":[61],"using":[62],"Video":[64],"State-Space":[65],"block":[66],"3D":[69],"Selective":[70],"Scan":[71],"module,":[72],"which":[73],"reinforces":[74],"coherence":[75],"at":[76],"an":[77],"affordable":[78],"computational":[79],"cost.":[80],"further":[82],"reduce":[83],"in":[85],"generated":[86],"details,":[87],"introduce":[89],"ControlNet":[92,131],"that":[93],"leverages":[94],"HR":[95],"features":[96,106],"as":[97],"guidance":[98],"employs":[100],"contrastive":[101],"extract":[104],"degradation-insensitive":[105],"from":[107],"LR":[108],"videos.":[109],"Finally,":[110],"three-stage":[112],"training":[113,159],"strategy":[114],"based":[115,136],"on":[116,145],"mixture":[118],"of":[119,153],"HR-LR":[120],"is":[122],"proposed":[123,129,155],"stabilize":[125],"training.":[127],"The":[128],"Self-supervised":[130],"Spatio-Temporal":[133],"Continuous":[134],"algorithm":[138],"achieves":[139],"superior":[140],"perceptual":[141],"quality":[142],"than":[143],"state-of-the-arts":[144],"benchmark":[148],"datasets,":[149],"validating":[150],"effectiveness":[152],"design":[157],"strategies.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}