![\"\"](\"https:\/\/cmu.box.com\/shared\/static\/266ys4iinp2ddq3bgz6fcrb8jq46gddi.gif\")
Second, feature scarcity<\/strong> the lack of rich texture and contrast in thermal images impedes reliable cross view correspondence and alignment.<\/p>\n\n\n\n Third, coverage gaps and drift<\/strong> arise when stitching multiple drone passes, yielding holes and misregistrations that degrade global consistency, as seen in Figure 2. <\/p>\n\n\n\n Finally, dynamic thermal phenomena<\/strong>, such as spreading fire fronts or moving heat sources, violate static scene assumptions and introduce temporal artifacts in na\u00efve reconstructions.<\/p>\n\n\n\n To overcome these obstacles, we propose a 3D Gaussian Splatting Thermal Reconstruction Pipeline, a unified, real\u2011time pipeline for 3D thermal scene reconstruction. Our framework comprises three key modules:<\/p>\n\n\n\n By investigating and integrating these components, we aim to transform disjoint 2D thermal video into coherent volumetric heat maps enabling precise, real\u2011time 3D thermal reconstructions even in feature poor and dynamic environments.<\/p>\n","protected":false},"excerpt":{"rendered":" Thermal infrared (TIR) imaging from unmanned aerial vehicles (UAVs) offers an all weather, none contact modality essential for applications such as wildfire monitoring, industrial safety inspections, and nighttime search and rescue operations. Unlike visible light imagery whose reconstruction pipelines falter under low illumination, haze, or fog, TIR data remains robust across diverse environmental conditions. Yet, … <\/p>\n![\"\"](\"https:\/\/cmu.box.com\/shared\/static\/obxbcatnj7f3s0n2faggttqzp00vl7de.gif\")
\n