{"id":881361,"date":"2022-09-27T18:49:15","date_gmt":"2022-09-28T01:49:15","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/"},"modified":"2022-09-27T18:49:15","modified_gmt":"2022-09-28T01:49:15","slug":"location-aware-super-resolution-for-satellite-data-fusion","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/location-aware-super-resolution-for-satellite-data-fusion\/","title":{"rendered":"Location Aware Super-Resolution for Satellite Data Fusion"},"content":{"rendered":"<p><span dir=\"ltr\" role=\"presentation\">Satellite data fusion involves images with different spatial, temporal, <\/span><span dir=\"ltr\" role=\"presentation\">and spectral resolution.<\/span> <span dir=\"ltr\" role=\"presentation\">These images are taken <\/span><span dir=\"ltr\" role=\"presentation\">under different illumination conditions, with different sensors <\/span><span dir=\"ltr\" role=\"presentation\">and atmospheric noise. We use classic super-resolution algo<\/span><span dir=\"ltr\" role=\"presentation\">rithms to synthesize commercial satellite images <\/span><span dir=\"ltr\" role=\"presentation\">from a public satellite source (Sentinel-2).<\/span> <span dir=\"ltr\" role=\"presentation\">Each super-resolution <\/span><span dir=\"ltr\" role=\"presentation\">resolution method is then further improved by adaptive sharp<\/span><span dir=\"ltr\" role=\"presentation\">ening to the location by use of matrix completion (regression <\/span><span dir=\"ltr\" role=\"presentation\">with missing pixels). Finally, we consider ensemble systems <\/span><span dir=\"ltr\" role=\"presentation\">and a residual channel attention dual network with stochastic <\/span><span dir=\"ltr\" role=\"presentation\">dropout.<\/span> <span dir=\"ltr\" role=\"presentation\">The resulting systems are visibly less blurry with <\/span><span dir=\"ltr\" role=\"presentation\">higher fidelity and yield improved performance<\/span><\/p>\n<div id=\"attachment_881364\" style=\"width: 310px\" class=\"wp-caption alignnone\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-881364\" class=\"size-medium wp-image-881364\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/collage-300x186.jpg\" alt=\"Location Aware Super Resolution\" width=\"300\" height=\"186\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/collage-300x186.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/collage-768x477.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/collage-240x149.jpg 240w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/collage.jpg 856w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><p id=\"caption-attachment-881364\" class=\"wp-caption-text\">Example of several super-resolution methods from 6 locations. The standard super-resolution methods are notably blurrier compared to the ground truth in column 1. The ensembles combine the 3 preceding columns using SRCNN.<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Satellite data fusion involves images with different spatial, temporal, and spectral resolution. These images are taken under different illumination conditions, with different sensors and atmospheric noise. We use classic super-resolution algorithms to synthesize commercial satellite images from a public satellite source (Sentinel-2). Each super-resolution resolution method is then further improved by adaptive sharpening to the [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[263152],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-881361","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us"],"msr_publishername":"IEEE","msr_edition":"","msr_affiliation":"","msr_published_date":"2022-7-21","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"IEEE","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/IEEE_IGARSS__Satellite_Super_Resolution-8.pdf","id":"881373","title":"_ieee_igarss__satellite_super_resolution-8","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":881373,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/IEEE_IGARSS__Satellite_Super_Resolution-8.pdf"},{"id":881370,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/09\/collage.pdf"}],"msr-author-ordering":[{"type":"text","value":"Olaoluwa Adigun","user_id":0,"rest_url":false},{"type":"guest","value":"peder-olsen","user_id":718918,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=peder-olsen"},{"type":"user_nicename","value":"Ranveer Chandra","user_id":33344,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ranveer Chandra"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[],"msr_group":[714067],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/881361"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/881361\/revisions"}],"predecessor-version":[{"id":881376,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/881361\/revisions\/881376"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=881361"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=881361"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=881361"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=881361"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=881361"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=881361"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=881361"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=881361"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=881361"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=881361"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=881361"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=881361"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=881361"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=881361"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=881361"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=881361"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}