{"id":"https://openalex.org/W4402816945","doi":"https://doi.org/10.1109/cvpr52733.2024.00272","title":"Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios","display_name":"Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402816945","doi":"https://doi.org/10.1109/cvpr52733.2024.00272"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5016150995","display_name":"Shiyan Chen","orcid":"https://orcid.org/0000-0001-9853-1181"},"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":true,"raw_author_name":"Shiyan Chen","raw_affiliation_strings":["School of Computer Science, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691292","display_name":"Jiyuan Zhang","orcid":"https://orcid.org/0000-0003-4081-5231"},"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":"Jiyuan Zhang","raw_affiliation_strings":["School of Computer Science, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048087489","display_name":"Zhaofei Yu","orcid":"https://orcid.org/0000-0002-6913-7553"},"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":"Zhaofei Yu","raw_affiliation_strings":["School of Computer Science, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111925815","display_name":"Tiejun Huang","orcid":null},"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":"Tiejun Huang","raw_affiliation_strings":["School of Computer Science, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016150995"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.7362,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91729663,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2814","last_page":"2823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9740999937057495,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9740999937057495,"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/blind-spot","display_name":"Blind spot","score":0.7947336435317993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6418497562408447},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5920321345329285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.493852436542511},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3332124352455139}],"concepts":[{"id":"https://openalex.org/C64731932","wikidata":"https://www.wikidata.org/wiki/Q371090","display_name":"Blind spot","level":2,"score":0.7947336435317993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6418497562408447},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5920321345329285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.493852436542511},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3332124352455139}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G4375190006","display_name":null,"funder_award_id":"62176003,62088102,62306015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5782943403","display_name":null,"funder_award_id":"20230484362","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Self-supervised":[0],"denoising":[1,51,111],"has":[2],"attracted":[3],"widespread":[4],"at-tention":[5],"due":[6,64],"to":[7,10,34,41,57,65,102,114,192,214],"its":[8],"ability":[9],"train":[11,115],"without":[12],"clean":[13],"images.":[14],"How-ever,":[15],"noise":[16,33,43,151],"in":[17,108,218],"real-world":[18,109],"scenarios":[19],"is":[20,113,212],"often":[21],"spatially":[22],"cor-related,":[23],"which":[24],"causes":[25],"many":[26],"self-supervised":[27,110,216],"algorithms":[28,217],"that":[29,99,206],"assume":[30],"pixel-wise":[31],"independent":[32],"perform":[35],"poorly.":[36],"Re-cent":[37],"works":[38],"have":[39],"attempted":[40],"break":[42],"correlation":[44,152],"with":[45,77],"downsampling":[46],"or":[47,81],"neighborhood":[48,72],"masking.":[49],"However,":[50],"on":[52,131,202],"downsampled":[53],"subgraphs":[54],"can":[55,144],"lead":[56],"aliasing":[58],"effects":[59],"and":[60,105,122,128,154,161,211,223],"loss":[61],"of":[62,93,175,220],"details":[63],"a":[66,171,186,194],"lower":[67],"sampling":[68,181],"rate.":[69],"Further-more,":[70],"the":[71,91,100,117,141,167],"masking":[73],"methods":[74],"either":[75],"come":[76],"high":[78],"computational":[79,221],"complexity":[80],"do":[82],"not":[83],"consider":[84],"local":[85,156],"spatial":[86,157],"preservation":[87],"during":[88,126,159],"inference.":[89,129,162],"Through":[90],"analy-sis":[92],"existing":[94],"methods,":[95],"we":[96,133,165],"point":[97],"out":[98],"key":[101],"obtaining":[103],"high-quality":[104],"texture-rich":[106],"results":[107,201],"tasks":[112],"at":[116],"original":[118],"input":[119],"resolution":[120],"structure":[121],"use":[123],"asymmetric":[124],"operations":[125],"training":[127,160],"Based":[130],"this,":[132],"propose":[134,185],"Asymmet-ric":[135],"Tunable":[136],"Blind-Spot":[137],"Network":[138],"(AT-BSN),":[139],"where":[140],"blind-spot":[142,187],"size":[143],"be":[145],"freely":[146],"adjusted,":[147],"thus":[148],"better":[149],"balancing":[150],"suppression":[153],"image":[155],"destruction":[158],"In":[163],"addition,":[164],"regard":[166],"pre-trained":[168],"AT-BSN":[169],"as":[170],"meta-teacher":[172],"network":[173],"capable":[174],"generating":[176],"various":[177],"teacher":[178],"networks":[179],"by":[180],"different":[182],"blind-spots.":[183],"We":[184],"based":[188],"multi-teacher":[189],"distillation":[190],"strategy":[191],"distill":[193],"lightweight":[195],"network,":[196],"signif-icantly":[197],"improving":[198],"performance.":[199],"Experimental":[200],"multiple":[203],"datasets":[204],"prove":[205],"our":[207],"method":[208],"achieves":[209],"state-of-the-art,":[210],"superior":[213],"other":[215],"terms":[219],"overhead":[222],"visual":[224],"effects.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}