{"id":"https://openalex.org/W7160337289","doi":"https://doi.org/10.1109/wacv61042.2026.00546","title":"F-ViTA: Foundation Model Guided Visible-to-Infrared Translation","display_name":"F-ViTA: Foundation Model Guided Visible-to-Infrared Translation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160337289","doi":"https://doi.org/10.1109/wacv61042.2026.00546"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135359984","display_name":"Jay Nitin Paranjape","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Nitin Paranjape","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066072868","display_name":"Celso M. de Melo","orcid":"https://orcid.org/0000-0003-2680-8334"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Celso M de Melo","raw_affiliation_strings":["DEVCOM Army Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135326487","display_name":"Vishal M. Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal M. Patel","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.7965,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98186603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5633","last_page":"5642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.04960000142455101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.04960000142455101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.026200000196695328,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.024000000208616257,"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/foundation","display_name":"Foundation (evidence)","score":0.461899995803833},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2793999910354614},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2506999969482422},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2409999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.545799970626831},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4580000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3596999943256378},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24410000443458557},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2409999966621399},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.22660000622272491}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1910108985","https://openalex.org/W2015148749","https://openalex.org/W2041981713","https://openalex.org/W2494592843","https://openalex.org/W2743341814","https://openalex.org/W2767014298","https://openalex.org/W2790896317","https://openalex.org/W2913527057","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2967090870","https://openalex.org/W3020634498","https://openalex.org/W3033020497","https://openalex.org/W3087893884","https://openalex.org/W3159018159","https://openalex.org/W3199191229","https://openalex.org/W4210393880","https://openalex.org/W4285111765","https://openalex.org/W4285267224","https://openalex.org/W4312933868","https://openalex.org/W4383109290","https://openalex.org/W4386076215","https://openalex.org/W4390874575","https://openalex.org/W4402352247","https://openalex.org/W4402916932","https://openalex.org/W4402917081","https://openalex.org/W4404612908","https://openalex.org/W4409262789","https://openalex.org/W4411050665"],"related_works":[],"abstract_inverted_index":{"Thermal":[0],"imaging":[1],"is":[2,18],"crucial":[3],"for":[4,28,110],"scene":[5,143],"understanding,":[6],"particularly":[7],"in":[8,102,149],"low-light":[9],"and":[10,20,76,123,131,145,174,183],"nighttime":[11],"conditions.":[12],"However,":[13],"collecting":[14],"large":[15],"thermal":[16,147],"datasets":[17,157],"costly":[19],"labor-intensive":[21],"due":[22],"to":[23,69,105,138,170],"the":[24,56,72,97,107,136,188],"specialized":[25],"equipment":[26],"required":[27],"infrared":[29,150],"image":[30,40],"capture.":[31],"To":[32],"address":[33],"this":[34,85],"challenge,":[35],"researchers":[36],"have":[37],"explored":[38],"visible-to-thermal":[39],"translation.":[41,112],"Most":[42],"existing":[43],"methods":[44],"rely":[45],"on":[46,154],"Generative":[47],"Adversarial":[48],"Networks":[49],"(GANs)":[50],"or":[51],"Diffusion":[52,118],"Models":[53],"(DMs),":[54],"treating":[55],"task":[57],"as":[58,129],"a":[59,64,90],"style":[60,92],"transfer":[61,93],"problem.":[62],"As":[63],"result,":[65],"these":[66],"approaches":[67],"attempt":[68],"learn":[70,139],"both":[71],"modality":[73],"distribution":[74],"shift":[75],"underlying":[77],"physical":[78],"principles":[79],"from":[80,125,187],"limited":[81],"training":[82],"data.":[83],"In":[84],"paper,":[86],"we":[87,114],"propose":[88],"F-ViTA,":[89],"novel":[91],"approach":[94],"that":[95,159],"leverages":[96],"general":[98],"world":[99],"knowledge":[100],"embedded":[101],"foundation":[103,126],"models":[104,127],"guide":[106],"diffusion":[108],"process":[109],"improved":[111],"Specifically,":[113],"condition":[115],"an":[116],"In-structPix2Pix":[117],"Model":[119],"with":[120],"zero-shot":[121],"masks":[122],"labels":[124],"such":[128],"SAM":[130],"Grounded":[132],"DINO.":[133],"This":[134],"allows":[135],"model":[137,167],"meaningful":[140],"correlations":[141],"between":[142],"objects":[144],"their":[146],"signatures":[148],"imagery.":[151],"Extensive":[152],"experiments":[153],"five":[155],"public":[156],"demonstrate":[158],"F-ViTA":[160],"outperforms":[161],"state-of-the-art":[162],"(SOTA)":[163],"methods.":[164],"Furthermore,":[165],"our":[166],"generalizes":[168],"well":[169],"out-of-distribution":[171],"(OOD)":[172],"scenarios":[173],"can":[175],"generate":[176],"Long-Wave":[177],"Infrared":[178,181],"(LWIR),":[179],"Mid-Wave":[180],"(MWIR),":[182],"Near-Infrared":[184],"(NIR)":[185],"translations":[186],"same":[189],"visible":[190],"image.":[191],"Code:":[192],"Released":[193],"post-review.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2026-05-06T00:00:00"}