{"id":"https://openalex.org/W7154424864","doi":"https://doi.org/10.48550/arxiv.2604.11468","title":"Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising","display_name":"Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154424864","doi":"https://doi.org/10.48550/arxiv.2604.11468"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.11468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.11468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133618567","display_name":"Gengjia Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chang, Gengjia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133582953","display_name":"Xining Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Xining","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102781181","display_name":"Weijun Yuan","orcid":"https://orcid.org/0009-0003-3215-4848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Weijun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133619480","display_name":"Zhan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Song, Qiurong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Qiurong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076561018","display_name":"Luen Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Luen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133601212","display_name":"Shuhong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shuhong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5133618567"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9046000242233276,"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":0.9046000242233276,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.02239999920129776,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.018799999728798866,"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/noise-reduction","display_name":"Noise reduction","score":0.6525999903678894},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5697000026702881},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5360999703407288},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5105000138282776},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5016999840736389},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.4311000108718872},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4120999872684479}],"concepts":[{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6525999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6412000060081482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388999819755554},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5697000026702881},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5016999840736389},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.4311000108718872},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.3407000005245209},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.33000001311302185},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C101453961","wikidata":"https://www.wikidata.org/wiki/Q7048948","display_name":"Non-local means","level":4,"score":0.2766000032424927},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.11468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.11468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.40924012660980225,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,124],"solution":[4],"to":[5,88,110,144],"the":[6,31,35,54,61,117,136,152,157,162],"NTIRE":[7],"2026":[8],"Image":[9],"Denoising":[10],"Challenge":[11],"(Gaussian":[12],"color":[13],"image":[14,72],"denoising":[15],"at":[16],"fixed":[17],"noise":[18],"level":[19],"$\u03c3=":[20],"50$).":[21],"Rather":[22],"than":[23],"proposing":[24],"a":[25],"new":[26],"restoration":[27],"backbone,":[28],"we":[29,59,82],"revisit":[30],"performance":[32],"boundary":[33],"of":[34,121],"mature":[36],"Restormer":[37,56,138],"architecture":[38],"from":[39,53,156],"two":[40,78],"complementary":[41],"directions:":[42],"stronger":[43],"data-centric":[44],"training":[45,64,159],"and":[46,68,74,131,161,166],"more":[47,69],"complete":[48],"Test-Time":[49],"capability":[50],"release.":[51],"Starting":[52],"public":[55,71,137],"$\u03c3\\!=\\!50$":[57,139],"baseline,":[58],"expand":[60],"standard":[62],"multi-dataset":[63],"recipe":[65],"with":[66],"larger":[67],"diverse":[70],"corpora":[73],"organize":[75],"optimization":[76,164],"into":[77],"stages.":[79],"At":[80],"inference,":[81],"apply":[83],"$\\times":[84],"8$":[85],"geometric":[86],"self-ensemble":[87,167],"further":[89],"release":[90],"model":[91],"capacity.":[92],"A":[93],"TLC-style":[94],"local":[95],"inference":[96],"wrapper":[97],"is":[98],"retained":[99],"for":[100],"implementation":[101],"consistency;":[102],"however,":[103],"systematic":[104],"ablation":[105],"reveals":[106],"its":[107],"quantitative":[108],"contribution":[109],"be":[111],"negligible":[112],"in":[113],"this":[114],"setting.":[115],"On":[116],"challenge":[118],"validation":[119],"set":[120],"100":[122],"images,":[123],"final":[125],"submission":[126],"achieves":[127],"30.762":[128],"dB":[129,146],"PSNR":[130],"0.861":[132],"SSIM,":[133],"improving":[134],"over":[135],"pretrained":[140],"baseline":[141],"by":[142],"up":[143],"3.366":[145],"PSNR.":[147],"Ablation":[148],"studies":[149],"show":[150],"that":[151],"dominant":[153],"gain":[154],"originates":[155],"expanded":[158],"corpus":[160],"two-stage":[163],"schedule,":[165],"provides":[168],"marginal":[169],"but":[170],"consistent":[171],"improvement.":[172]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-15T00:00:00"}