Thermal Infrared Guided Color Image Dehazing

Abstract

Owing to the superior wavelength properties in penetrating haze, the thermal infrared images maintain high contrast and sharp edge even in the presence of dense haze, holding significant potential for improving color image dehazing. Thus, we propose a thermal infrared guided color image dehazing algorithm. Rather than direct fusion, an optimization framework is established, in which the regional contrast information of the thermal infrared guides contrast enhancement of color image, and the edge information is used to transmission map refinement and edge preservation. In conjunction with a color fidelity constraint, the optimization framework is solved with gradient descent. Additionally, we propose the Thermal infrared/Visible Images in Haze dataset (TVIH), which consists of registered high-resolution image pairs in outdoor dense haze and mist scenarios. Our method outperforms single image dehazing and image fusion methods on our dataset regarding subjective quality and objective metrics.