{"id":8,"date":"2025-05-07T17:37:57","date_gmt":"2025-05-07T17:37:57","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/?page_id=8"},"modified":"2025-12-13T02:20:09","modified_gmt":"2025-12-13T02:20:09","slug":"results","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/","title":{"rendered":"Results"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\"><strong>1. Qualitative Result<\/strong><\/h3>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cmu.box.com\/shared\/static\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif\" alt=\"\" \/><figcaption class=\"wp-element-caption\" style=\"text-align: center\"><strong>Figure 7:<\/strong> Comparison rendering output between 3DGS (Left) and our method (Right)\n    <a href=\"https:\/\/cmu.box.com\/s\/hebx5kh4mzazu2ivhpxtfdrp783dw6dw\" target=\"_blank\" rel=\"noopener noreferrer\">\n      [Click for High Res Video]\n    <\/a>\n<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cmu.box.com\/shared\/static\/w1zpwh8p10fnwrt0tbwtee18jzm6mv63.gif\" alt=\"\" \/><figcaption class=\"wp-element-caption\" style=\"text-align: center\"><strong>Figure 8:<\/strong> Comparison rendering output between 3DGS (Left) and our method (Right)\n    <a href=\"https:\/\/cmu.box.com\/s\/p9nxr97pdl23tgqpne410fj2u6usf99n\" target=\"_blank\" rel=\"noopener noreferrer\">\n      [Click for High Res Video]\n    <\/a>\n<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cmu.box.com\/shared\/static\/lxwyp188jrjmlcciu4rnzugmtg6dzqhn.gif\" alt=\"\" \/><figcaption class=\"wp-element-caption\" style=\"text-align: center\"><strong>Figure 9:<\/strong> Comparison rendering output between 3DGS (Left) and our method (Right)\n    <a href=\"https:\/\/cmu.box.com\/s\/xhb6xi5b6gy2aaqlps3actvsbibkjnlp\" target=\"_blank\" rel=\"noopener noreferrer\">\n      [Click for High Res Video]\n    <\/a>\n<\/figcaption><\/figure>\n\n\n\n<p style=\"font-size:16px;margin-bottom:12px\">\n  <strong>Ground Truth.<\/strong> Reference thermal sequences for the scenes shown above.\n<\/p>\n\n<div style=\"gap:16px;flex-wrap:wrap;align-items:flex-start\">\n  <figure style=\"margin:0;flex:1;min-width:260px\">\n    <img decoding=\"async\" src=\"https:\/\/cmu.box.com\/shared\/static\/veiocl8so5aztnn1o10i4gu7umnnkys1.gif\" alt=\"Ground Truth (GT)\" style=\"width:100%;height:auto;border-radius:10px\">\n    <figcaption style=\"margin-top:8px;font-size:14px;text-align:center\">GT<\/figcaption>\n  <\/figure>\n\n\n  <figure style=\"margin:0;flex:1;min-width:260px\">\n    <img decoding=\"async\" src=\"https:\/\/cmu.box.com\/shared\/static\/18ximguou15x3wv4m385dr9x7765jrdi.gif\" alt=\"Ground Truth (GT)\" style=\"width:100%;height:auto;border-radius:10px\">\n    <figcaption style=\"margin-top:8px;font-size:14px;text-align:center\">GT<\/figcaption>\n  <\/figure>\n\n\n\n  <figure style=\"margin:0;flex:1;min-width:260px\">\n    <img decoding=\"async\" src=\"https:\/\/cmu.box.com\/shared\/static\/0regotcrv9copwh227lgpaxgd0bzqafq.gif\" alt=\"Ground Truth (GT)\" style=\"width:100%;height:auto;border-radius:10px\">\n    <figcaption style=\"margin-top:8px;font-size:14px;text-align:center\">GT<\/figcaption>\n  <\/figure>\n<\/div>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>2. <\/strong><span><strong style=\"font-weight: bold\">Dataset<\/strong><\/span><\/h3>\n\n\n\n\n\n<p style=\"text-align: justify\">\nDue to the limited availability of large-scale dynamic thermal datasets, we conduct our experiments using a combination of publicly available benchmarks, including <strong>NTR-Gaussian<\/strong> and <strong>TI-NSD<\/strong>. NTR-Gaussian is designed for nighttime dynamic thermal reconstruction and contains aerial thermal infrared (TIR) imagery from four outdoor scenes (two urban, two suburban), captured at multiple time intervals using a DJI Matrice 300 RTK equipped with a DJI H20T thermal camera. The data is collected at an altitude of 250 meters with a resolution of <strong>640 \u00d7 512<\/strong> pixels and covers diverse environments such as buildings, roads, farmlands, and water bodies. The dataset provides calibrated camera poses and paired synthetic RGB images, enabling multi view and time varying thermal scene modeling. While TI-NSD further complements this data as a larger benchmark, comprising 20 real thermal infrared video scenes spanning indoor, outdoor, and UAV scenarios for evaluating thermal novel view reconstruction techniques.\n<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>3. Quantitive Results <\/strong><\/h3>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"248\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-9.14.53-PM-1024x248.png\" alt=\"\" class=\"wp-image-258\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-9.14.53-PM-1024x248.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-9.14.53-PM-300x73.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-9.14.53-PM-768x186.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-9.14.53-PM.png 1336w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"772\" height=\"604\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-8.54.54-PM.png\" alt=\"\" class=\"wp-image-254\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-8.54.54-PM.png 772w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-8.54.54-PM-300x235.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-content\/uploads\/sites\/139\/2025\/12\/Screenshot-2025-12-12-at-8.54.54-PM-768x601.png 768w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>\u00a04. Future Directions<\/strong><\/h3>\n\n\n\n<p style=\"text-align: justify\">We plan to expand our evaluation beyond visual quality by introducing targeted experiments that test whether predicted temperature evolution is consistent with observed thermal trends in real scenes. This includes validating relative temperature changes on fixed surfaces across repeated UAV passes, measuring temporal consistency under partial observations, and comparing against simpler baselines to identify when dynamic modeling provides clear benefits. We also aim to explore lightweight validation signals and controlled scenarios that help assess physical plausibility without requiring dense ground truth temperature measurements. Together, these steps will clarify the practical scope of 4D thermal reconstruction and guide its use in applications where spatiotemporal modeling is most informative.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>1. Qualitative Result Figure 7: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Figure 8: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Figure 9: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Ground &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Results&#8221;<\/span><\/a><\/p>\n","protected":false},"author":261,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-8","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Results - End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Results - End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction\" \/>\n<meta property=\"og:description\" content=\"1. Qualitative Result Figure 7: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Figure 8: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Figure 9: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Ground &hellip; Continue reading &quot;Results&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/\" \/>\n<meta property=\"og:site_name\" content=\"End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-13T02:20:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cmu.box.com\/shared\/static\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/\",\"name\":\"Results - End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/cmu.box.com\\\/shared\\\/static\\\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif\",\"datePublished\":\"2025-05-07T17:37:57+00:00\",\"dateModified\":\"2025-12-13T02:20:09+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/#primaryimage\",\"url\":\"https:\\\/\\\/cmu.box.com\\\/shared\\\/static\\\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif\",\"contentUrl\":\"https:\\\/\\\/cmu.box.com\\\/shared\\\/static\\\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/results\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Results\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/\",\"name\":\"End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction\",\"description\":\"By: Lamia Alsalloom | Advised By: Prof. Sebastian Scherer\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-2\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Results - End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/","og_locale":"en_US","og_type":"article","og_title":"Results - End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction","og_description":"1. Qualitative Result Figure 7: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Figure 8: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Figure 9: Comparison rendering output between 3DGS (Left) and our method (Right) [Click for High Res Video] Ground &hellip; Continue reading \"Results\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/","og_site_name":"End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction","article_modified_time":"2025-12-13T02:20:09+00:00","og_image":[{"url":"https:\/\/cmu.box.com\/shared\/static\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/","name":"Results - End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/#primaryimage"},"thumbnailUrl":"https:\/\/cmu.box.com\/shared\/static\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif","datePublished":"2025-05-07T17:37:57+00:00","dateModified":"2025-12-13T02:20:09+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/#primaryimage","url":"https:\/\/cmu.box.com\/shared\/static\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif","contentUrl":"https:\/\/cmu.box.com\/shared\/static\/d2dc1vrjs5pv5sasohwwa1952d7gbk59.gif"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/results\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/"},{"@type":"ListItem","position":2,"name":"Results"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/","name":"End-to-End Infrared UAV Mapping: An Integrated Framework for Thermal Scene Reconstruction","description":"By: Lamia Alsalloom | Advised By: Prof. Sebastian Scherer","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/pages\/8","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/users\/261"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/comments?post=8"}],"version-history":[{"count":33,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/pages\/8\/revisions"}],"predecessor-version":[{"id":264,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/pages\/8\/revisions\/264"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-2\/wp-json\/wp\/v2\/media?parent=8"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}