{"id":"https://openalex.org/W7204182779","doi":"https://doi.org/10.48550/arxiv.2608.21786","title":"UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion","display_name":"UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204182779","doi":"https://doi.org/10.48550/arxiv.2608.21786"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21786","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21786","pdf_url":"https://arxiv.org/pdf/2608.21786","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21786","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013097958","display_name":"Xingxin Xu","orcid":"https://orcid.org/0000-0001-8968-9331","observed_orcids":["https://orcid.org/0000-0001-8968-9331"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Xingxin","raw_affiliation_strings":["School of New Media and Communication , Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of New Media and Communication , Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612775","display_name":"Siqi Zhao","orcid":"https://orcid.org/0009-0001-6477-5679","observed_orcids":["https://orcid.org/0009-0001-6477-5679"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Siqi","raw_affiliation_strings":["School of Artificial Intelligence , Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148089677","display_name":"Xin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["BD","CN"],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":["School of Automation , Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation , Southeast University","institution_ids":["https://openalex.org/I4210090971","https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136407914","display_name":"Xinjie Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao, Xinjie","raw_affiliation_strings":["School of Artificial Intelligence , Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125759498","display_name":"Yiming Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["BD","CN"],"is_corresponding":false,"raw_author_name":"Sun, Yiming","raw_affiliation_strings":["School of Automation , Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation , Southeast University","institution_ids":["https://openalex.org/I4210090971","https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130760165","display_name":"Pengfei Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/image-fusion","display_name":"image fusion","score":0.9559999704360962},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8980000019073486},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/infrared-and-visible-image-fusion","display_name":"infrared and visible image fusion","score":0.8610000014305115},{"id":"https://openalex.org/keywords/multi-exposure-image-fusion","display_name":"multi-exposure image fusion","score":0.9670000076293945},{"id":"https://openalex.org/keywords/prompt-routing","display_name":"prompt routing","score":0.6850000023841858},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.6650000214576721},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.953000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634000182151794},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4758000075817108},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.39910000562667847},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21786","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21786","pdf_url":"https://arxiv.org/pdf/2608.21786","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21786","doi":"https://doi.org/10.48550/arxiv.2608.21786","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21786","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.21786","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21786","pdf_url":"https://arxiv.org/pdf/2608.21786","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204182779.pdf","grobid_xml":"https://content.openalex.org/works/W7204182779.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4405703354"],"related_works":["https://openalex.org/W7154118506","https://openalex.org/W4414902280","https://openalex.org/W7203678499","https://openalex.org/W7138203269","https://openalex.org/W4416445946","https://openalex.org/W4414229180","https://openalex.org/W7163704388","https://openalex.org/W4405303762","https://openalex.org/W4394687776","https://openalex.org/W7202225501"],"abstract_inverted_index":{"General":[0],"image":[1,44,176],"fusion":[2,61,65,95,141,156,177,183,214],"aims":[3],"to":[4,22,57,74,86,93,103,122,154],"integrate":[5],"complementary":[6],"information":[7],"from":[8],"multiple":[9],"source":[10,111],"images,":[11],"but":[12],"existing":[13],"methods":[14],"often":[15],"rely":[16],"on":[17,171],"task-specific":[18],"models":[19],"and":[20,42,70,97,108,134,142,160,174,185,190,199,215],"struggle":[21],"maintain":[23],"robust":[24],"performance":[25],"under":[26,187],"diverse":[27],"degradation":[28,100],"conditions.":[29,192],"In":[30],"this":[31],"paper,":[32],"we":[33,81],"propose":[34],"UniDiffFusion,":[35],"a":[36,53,59,99,151,207],"unified":[37,208],"diffusion":[38,55,91,209],"framework":[39,147,210],"for":[40,127,211],"multi-task":[41],"degradation-robust":[43],"fusion.":[45,114],"UniDiffFusion":[46,180,194],"leverages":[47],"the":[48,89,139],"strong":[49],"generative":[50],"prior":[51],"of":[52],"pretrained":[54],"model":[56],"establish":[58],"shared":[60,90,140],"backbone":[62],"across":[63],"heterogeneous":[64,167],"tasks,":[66],"while":[67],"introducing":[68],"task-":[69],"degradation-aware":[71,106,158],"conditional":[72],"adaptation":[73],"accommodate":[75],"their":[76],"distinct":[77],"information-selection":[78],"requirements.":[79],"Specifically,":[80],"employ":[82],"task":[83],"prompt":[84,101,118],"modulation":[85],"progressively":[87],"adapt":[88],"representations":[92],"different":[94],"objectives,":[96],"develop":[98],"router":[102],"dynamically":[104],"retrieve":[105],"priors":[107],"restore":[109],"corrupted":[110],"features":[112],"before":[113],"Furthermore,":[115],"an":[116],"application":[117],"bank":[119],"is":[120,148],"introduced":[121],"incorporate":[123],"task-oriented":[124,216],"semantic":[125,135,200],"guidance":[126],"downstream":[128,197],"applications,":[129],"such":[130],"as":[131,206],"object":[132],"detection":[133,198],"segmentation,":[136],"without":[137],"altering":[138],"restoration":[143],"pathways.":[144],"The":[145],"proposed":[146],"trained":[149],"in":[150],"progressive":[152],"manner":[153],"decouple":[155],"learning,":[157],"restoration,":[159],"application-specific":[161],"adaptation,":[162],"thereby":[163],"reducing":[164],"interference":[165],"among":[166],"objectives.":[168],"Extensive":[169],"experiments":[170],"visible-infrared,":[172],"multi-exposure,":[173],"multi-focus":[175],"demonstrate":[178],"that":[179],"achieves":[181],"superior":[182],"quality":[184],"robustness":[186],"both":[188,212],"clean":[189],"degraded":[191],"Moreover,":[193],"consistently":[195],"improves":[196],"segmentation":[201],"performance,":[202],"demonstrating":[203],"its":[204],"effectiveness":[205],"perceptual":[213],"vision.":[217]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}