TeX-NeRF: Neural Radiance Fields for Novel HADAR View Synthesis

Abstract

Most existing NeRF methods rely on RGB images, making them unsuitable for scenarios with darkness, low light, or adverse weather conditions. To address this limitation, we propose TeX-NeRF, a NeRF framework based on heat sensing, designed for a new task: novel HADAR view synthesis. Our approach leverages Pseudo-TeX Vision to effectively transform heat sensing images through a structured mapping process. We introduce a loss function tailored to the transformed representation and incorporate temperature gradient embedding to enhance the capture of thermal information. Additionally, we construct 3D-TeX, a high-quality heat sensing dataset, to validate our method. Extensive experiments demonstrate that TeX-NeRF significantly improves pose estimation success rates for heat sensing images and outperforms existing approaches in novel HADAR view synthesis.