{"id":"https://openalex.org/W7139055189","doi":"https://doi.org/10.48550/arxiv.2603.16482","title":"DST-Net: A Dual-Stream Transformer with Illumination-Independent Feature Guidance and Multi-Scale Spatial Convolution for Low-Light Image Enhancement","display_name":"DST-Net: A Dual-Stream Transformer with Illumination-Independent Feature Guidance and Multi-Scale Spatial Convolution for Low-Light Image Enhancement","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7139055189","doi":"https://doi.org/10.48550/arxiv.2603.16482"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16482","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16482","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.2603.16482","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101474225","display_name":"Y.Q. Shi","orcid":"https://orcid.org/0009-0001-6813-0309"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shi, Yicui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129935206","display_name":"Yuhan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019776679","display_name":"Xiangfei Huang","orcid":"https://orcid.org/0000-0001-5782-5212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiangfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123768724","display_name":"Zhenguo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhenguo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123636152","display_name":"Wenxuan Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Wenxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129807632","display_name":"Ying Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Ying","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101474225"],"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":0.9836999773979187,"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":0.9836999773979187,"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":0.00989999994635582,"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":0.0010999999940395355,"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/feature-extraction","display_name":"Feature extraction","score":0.48590001463890076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.3905999958515167},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.3871999979019165},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.36039999127388},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3594000041484833},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.3571999967098236},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3522999882698059},{"id":"https://openalex.org/keywords/luminance","display_name":"Luminance","score":0.35030001401901245}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7214000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797000169754028},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5787000060081482},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3871999979019165},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C73313986","wikidata":"https://www.wikidata.org/wiki/Q355386","display_name":"Luminance","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16482","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16482","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.2603.16482","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16482","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.808643102645874}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Low-light":[0],"image":[1,36],"enhancement":[2,115,150],"aims":[3],"to":[4,34,71,111,136,156,163,190],"restore":[5],"the":[6,73,114,130,133,139,144,158,231,237],"visibility":[7],"of":[8,45,75,92,143,160,227],"images":[9],"captured":[10],"by":[11,17],"visual":[12,216],"sensors":[13],"in":[14,214],"dim":[15],"environments":[16],"addressing":[18],"their":[19],"inherent":[20],"signal":[21,47,63,77,109,141],"degradations,":[22],"such":[23],"as":[24,108],"luminance":[25],"attenuation":[26],"and":[27,66,99,167,179,205,218],"structural":[28],"corruption.":[29],"Although":[30],"numerous":[31],"algorithms":[32],"attempt":[33],"improve":[35],"quality,":[37],"existing":[38,161],"methods":[39,162],"often":[40],"cause":[41],"a":[42,55,84,120,126,171,225],"severe":[43],"loss":[44,74],"intrinsic":[46],"priors.":[48],"To":[49],"overcome":[50,157],"these":[51],"challenges,":[52],"we":[53,82,118,169],"propose":[54,170],"Dual-Stream":[56],"Transformer":[57],"Network":[58],"(DST-Net)":[59],"based":[60],"on":[61,230,236],"illumination-agnostic":[62,106],"prior":[64],"guidance":[65],"multi-scale":[67,200],"spatial":[68,197,201],"convolutions.":[69,183,202],"First,":[70],"address":[72],"critical":[76],"features":[78,107],"under":[79],"low-light":[80],"conditions,":[81],"design":[83],"feature":[85],"extraction":[86],"module.":[87],"This":[88,184],"module":[89,185],"integrates":[90,186],"Difference":[91],"Gaussians":[93],"(DoG),":[94],"LAB":[95],"color":[96],"space":[97],"transformations,":[98],"VGG-16":[100],"for":[101],"texture":[102],"extraction,":[103],"utilizing":[104],"decoupled":[105],"priors":[110,135],"continuously":[112],"guide":[113],"process.":[116],"Second,":[117],"construct":[119],"dual-stream":[121],"interaction":[122],"architecture.":[123],"By":[124],"employing":[125],"cross-modal":[127],"attention":[128],"mechanism,":[129],"network":[131],"leverages":[132],"extracted":[134],"dynamically":[137],"rectify":[138],"deteriorated":[140],"representation":[142],"enhanced":[145],"image,":[146],"ultimately":[147],"achieving":[148],"iterative":[149],"through":[151],"differentiable":[152],"curve":[153],"estimation.":[154],"Furthermore,":[155],"inability":[159],"preserve":[164],"fine":[165],"structures":[166],"textures,":[168],"Multi-Scale":[172],"Spatial":[173],"Fusion":[174],"Block":[175],"(MSFB)":[176],"featuring":[177],"pseudo-3D":[178],"3D":[180],"gradient":[181,188],"operator":[182],"explicit":[187],"operators":[189],"recover":[191],"high-frequency":[192],"edges":[193],"while":[194],"capturing":[195],"inter-channel":[196],"correlations":[198],"via":[199],"Extensive":[203],"evaluations":[204],"ablation":[206],"studies":[207],"demonstrate":[208],"that":[209],"DST-Net":[210],"achieves":[211,224],"superior":[212],"performance":[213],"subjective":[215],"quality":[217],"objective":[219],"metrics.":[220],"Specifically,":[221],"our":[222],"method":[223],"PSNR":[226],"25.64":[228],"dB":[229],"LOL":[232],"dataset.":[233],"Subsequent":[234],"validation":[235],"LSRW":[238],"dataset":[239],"further":[240],"confirms":[241],"its":[242],"robust":[243],"cross-scene":[244],"generalization.":[245]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}