{"id":"https://openalex.org/W4414902280","doi":"https://doi.org/10.1109/iccv51701.2025.01092","title":"MMAIF: Multi-Task and Multi-Degradation All-in-One for Image Fusion with Language Guidance","display_name":"MMAIF: Multi-Task and Multi-Degradation All-in-One for Image Fusion with Language Guidance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414902280","doi":"https://doi.org/10.1109/iccv51701.2025.01092"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.14944","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065512683","display_name":"Zihan Cao","orcid":"https://orcid.org/0000-0002-7532-2122"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Cao","raw_affiliation_strings":["University of Electronic Science and Technology of China (UESTC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China (UESTC)","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101180560","display_name":"Yu Zhong","orcid":"https://orcid.org/0009-0003-3106-1113"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhong","raw_affiliation_strings":["University of Electronic Science and Technology of China (UESTC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China (UESTC)","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438237","display_name":"Ziqi Wang","orcid":"https://orcid.org/0000-0002-2610-2158"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China (UESTC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China (UESTC)","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088224232","display_name":"Liang-Jian Deng","orcid":"https://orcid.org/0000-0003-3178-9772"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang-Jian Deng","raw_affiliation_strings":["University of Electronic Science and Technology of China (UESTC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China (UESTC)","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"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":"11744","last_page":"11754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9509999752044678,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12015","display_name":"Photoacoustic and Ultrasonic Imaging","score":0.9456999897956848,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/image-fusion","display_name":"Image fusion","score":0.5508000254631042},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5141000151634216},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.490200012922287},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45350000262260437},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4499000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.661899983882904},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6265000104904175},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5508000254631042},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45350000262260437},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4499000012874603},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3774000108242035},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2939000129699707},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2858000099658966},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.14944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14944","pdf_url":"https://arxiv.org/pdf/2503.14944","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.14944","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.14944","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.14944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14944","pdf_url":"https://arxiv.org/pdf/2503.14944","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2129173210","display_name":null,"funder_award_id":"12271083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3002070488","display_name":null,"funder_award_id":"2025YFNH0001","funder_id":"https://openalex.org/F4320322922","funder_display_name":"Department of Science and Technology of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322922","display_name":"Department of Science and Technology of Sichuan Province","ror":"https://ror.org/04323m874"},{"id":"https://openalex.org/F4320323292","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"fusion,":[1],"a":[2,14,77,94,123],"fundamental":[3],"low-level":[4],"vision":[5],"task,":[6],"aims":[7],"to":[8,107,141,146],"integrate":[9],"multiple":[10],"image":[11,43,85,101,125],"sequences":[12],"into":[13],"single":[15],"output":[16],"while":[17],"preserving":[18],"as":[19,22],"much":[20],"information":[21],"possible":[23],"from":[24],"the":[25,109,129,133,142,149,161,179],"input.":[26],"However,":[27],"existing":[28],"methods":[29],"face":[30],"several":[31],"significant":[32],"limitations:":[33],"1)":[34,93],"requiring":[35],"task-":[36],"or":[37],"dataset-specific":[38],"models;":[39],"2)":[40,111],"neglecting":[41],"real-world":[42,100],"degradations":[44,102],"(\\textit{e.g.},":[45],"noise),":[46],"which":[47,121],"causes":[48],"failure":[49],"when":[50],"processing":[51],"degraded":[52,130],"inputs;":[53],"3)":[54],"operating":[55,117],"in":[56,118],"pixel":[57],"space,":[58,120],"where":[59],"attention":[60],"mechanisms":[61],"are":[62,190],"computationally":[63],"expensive;":[64],"and":[65,83,103,132,164,170,182,186],"4)":[66],"lacking":[67],"user":[68],"interaction":[69],"capabilities.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75,137,156],"propose":[76],"unified":[78],"framework":[79,88],"for":[80],"multi-task,":[81],"multi-degradation,":[82],"language-guided":[84],"fusion.":[86],"Our":[87],"includes":[89],"two":[90,158],"key":[91],"components:":[92],"practical":[95],"degradation":[96],"pipeline":[97],"that":[98,174],"simulates":[99],"generates":[104],"interactive":[105],"prompts":[106],"guide":[108],"model;":[110],"an":[112],"all-in-one":[113,187],"Diffusion":[114],"Transformer":[115],"(DiT)":[116],"latent":[119],"fuses":[122],"clean":[124],"conditioned":[126],"on":[127,153],"both":[128],"inputs":[131],"generated":[134],"prompts.":[135],"Furthermore,":[136],"introduce":[138],"principled":[139],"modifications":[140],"original":[143],"DiT":[144],"architecture":[145],"better":[147],"suit":[148],"fusion":[150],"task.":[151],"Based":[152],"this":[154],"framework,":[155],"develop":[157],"versions":[159],"of":[160],"model:":[162],"Regression-based":[163],"Flow":[165],"Matching-based":[166],"variants.":[167],"Extensive":[168],"qualitative":[169],"quantitative":[171],"experiments":[172],"demonstrate":[173],"our":[175],"approach":[176],"effectively":[177],"addresses":[178],"aforementioned":[180],"limitations":[181],"outperforms":[183],"previous":[184],"restoration+fusion":[185],"pipelines.":[188],"Codes":[189],"available":[191],"at":[192],"https://github.com/294coder/MMAIF.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}