{"id":"https://openalex.org/W7161167482","doi":"https://doi.org/10.48550/arxiv.2605.13258","title":"X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge","display_name":"X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161167482","doi":"https://doi.org/10.48550/arxiv.2605.13258"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13258","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":null,"license_id":null,"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.2605.13258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136120199","display_name":"Youwei Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Youwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013728469","display_name":"Leilei Cao","orcid":"https://orcid.org/0000-0003-0336-9295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Leilei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136128326","display_name":"Yingfang Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yingfang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136185880","display_name":"Fengjie Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Fengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"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/T11019","display_name":"Image Enhancement Techniques","score":0.7839999794960022,"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/T11019","display_name":"Image Enhancement Techniques","score":0.7839999794960022,"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":0.10109999775886536,"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":0.023600000888109207,"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/key","display_name":"Key (lock)","score":0.6007000207901001},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5460000038146973},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5228000283241272},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.5110999941825867},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4104999899864197},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4034000039100647},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3865000009536743},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163000106811523},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612000226974487},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.5110999941825867},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5098999738693237},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13258","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.13258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13258","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":null,"license_id":null,"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":0.6344994306564331,"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":{"In":[0,70,116],"this":[1],"work,":[2],"we":[3,156],"present":[4],"our":[5,244],"winning":[6],"solution":[7],"for":[8],"the":[9,27,53,71,88,117,125,169,207,226,251],"8th":[10],"UG2+":[11],"Challenge":[12],"(CVPR":[13],"2026)":[14],"Track":[15],"1:":[16],"Image":[17],"Restoration":[18],"under":[19],"All-weather":[20],"Conditions.":[21],"Our":[22],"method":[23,246],"is":[24,76,122,189],"built":[25],"upon":[26],"X-Restormer":[28],"baseline,":[29],"which":[30,164],"captures":[31],"both":[32],"channel-wise":[33],"global":[34],"dependencies":[35],"and":[36,48,107,114,129,185,193],"spatially-local":[37],"structural":[38,152],"information":[39],"through":[40],"its":[41,234],"dual-attention":[42],"design":[43],"(Multi-DConv":[44],"Head":[45],"Transposed":[46],"Attention":[47],"Overlapping":[49],"Cross-Attention),":[50],"augmented":[51],"with":[52,66,144],"spatially-adaptive":[54],"input":[55],"scaling":[56],"mechanism":[57],"from":[58,78,87,206,238],"Restormer-Plus.":[59],"We":[60],"adopt":[61],"a":[62,81,145,158,174,198,213],"two-stage":[63],"training":[64,90,200],"strategy":[65],"dual-model":[67],"ensemble":[68],"inference.":[69],"first":[72],"stage,":[73,119],"Model":[74,120,133,231],"B":[75,232],"trained":[77],"scratch":[79],"on":[80,124],"large-scale":[82,239],"diverse":[83],"dataset":[84,127],"randomly":[85],"sampled":[86],"FoundIR":[89],"set":[91],"(approximately":[92],"800":[93],"GB":[94],"out":[95,216],"of":[96],"4.84":[97],"TB),":[98],"covering":[99],"five":[100],"degradation":[101],"types:":[102],"blur,":[103],"haze,":[104],"rain,":[105],"snow,":[106],"composite":[108],"conditions":[109],"such":[110],"as":[111,137],"co-occurring":[112],"rain":[113],"haze.":[115],"second":[118],"A":[121],"fine-tuned":[123],"WeatherStream":[126],"(rain":[128],"snow":[130],"splits)":[131],"using":[132],"B's":[134],"final":[135],"checkpoint":[136],"pretrained":[138],"initialization,":[139],"enabling":[140],"efficient":[141],"domain":[142],"adaptation":[143],"substantially":[146],"smaller":[147],"dataset.":[148],"To":[149],"better":[150],"preserve":[151],"details":[153],"during":[154],"training,":[155],"propose":[157],"novel":[159],"Gradient-Guided":[160],"Edge-Aware":[161],"(GGEA)":[162],"Loss,":[163],"applies":[165],"Sobel":[166],"operators":[167],"to":[168,172,183,230],"ground-truth":[170],"image":[171],"construct":[173],"spatially":[175],"adaptive":[176],"weight":[177,228],"map":[178],"that":[179],"assigns":[180],"higher":[181,227],"supervision":[182],"edge":[184],"high-frequency":[186],"regions.":[187],"This":[188],"incorporated":[190],"alongside":[191],"L1":[192],"Multi-Scale":[194],"SSIM":[195],"losses":[196],"in":[197,250],"unified":[199],"objective.":[201],"At":[202],"inference":[203],"time,":[204],"predictions":[205],"two":[208],"models":[209],"are":[210],"fused":[211],"via":[212],"weighted":[214],"average,":[215],"=":[217],"0.4":[218],"x":[219,223],"outA":[220],"+":[221],"0.6":[222],"outB,":[224],"where":[225],"assigned":[229],"reflects":[233],"stronger":[235],"generalization":[236],"ability":[237],"pretraining.":[240],"With":[241],"these":[242],"strategies,":[243],"proposed":[245],"successfully":[247],"ranks":[248],"1st":[249],"challenge.":[252]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-15T00:00:00"}