The technique of turning infrared (IR) radiation (heat) into visual images is known as thermal
infrared. Semantic segmentation aims to divide an input image based on information that is …

Cross-modality images that combine visible-infrared spectra can provide complementary
information for object detection. In particular, they are well-suited for autonomous vehicle …

Robust imaging under challenging conditions, such as starlit nights, has broadened the
adoption of thermal infrared (TIR) cameras for nighttime driving scenes. Given that TIR …

Nighttime Thermal InfraRed (NTIR) image colorization, also known as the translation of NTIR
images into Daytime Color Visible (DCV) images, can facilitate human and intelligent system …

Semantic segmentation of thermal infrared (ThIR) images is challenging because the
images considered in this task are highly complex. The discrimination of image regions is …

Stable imaging in adverse environments (eg, total darkness) makes thermal infrared (TIR)
cameras a prevalent option for night scene perception. However, the low contrast and lack of …

Nighttime thermal infrared (NTIR) image colorization, also known as translation of NTIR
images into daytime color images (NTIR2DC), is a promising research direction to facilitate …

Existing infrared colorization methods based on image-to-image translation in a GAN
framework require paired image data for network learning and are limited by data quality …

Image inpainting has achieved fundamental advances with deep learning. However, almost
all existing inpainting methods aim to process natural images, while few target Thermal …

Color images offer more information and are more detail-specific compared to typical
grayscale images. The frequency level of the images captured by the near-infrared (NIR) …