Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention

TL;DR

This paper introduces PearlGAN, a novel GAN-based method with top-down attention and gradient alignment to improve thermal infrared image colorization for nighttime driving scenes, enhancing semantic and geometric consistency.

Contribution

The paper proposes PearlGAN, which incorporates top-down guided attention and structured gradient alignment loss to address semantic entanglement and geometric distortion in infrared image colorization.

Findings

PearlGAN outperforms existing methods in semantic preservation.

The structured gradient alignment loss improves edge consistency.

The new metric effectively evaluates geometric fidelity.

Abstract

Benefitting from insensitivity to light and high penetration of foggy environments, infrared cameras are widely used for sensing in nighttime traffic scenes. However, the low contrast and lack of chromaticity of thermal infrared (TIR) images hinder the human interpretation and portability of high-level computer vision algorithms. Colorization to translate a nighttime TIR image into a daytime color (NTIR2DC) image may be a promising way to facilitate nighttime scene perception. Despite recent impressive advances in image translation, semantic encoding entanglement and geometric distortion in the NTIR2DC task remain under-addressed. Hence, we propose a toP-down attEntion And gRadient aLignment based GAN, referred to as PearlGAN. A top-down guided attention module and an elaborate attentional loss are first designed to reduce the semantic encoding ambiguity during translation. Then, a structured gradient alignment loss is introduced to encourage edge consistency between the translated and input images. In addition, pixel-level annotation is carried out on a subset of FLIR and KAIST datasets to evaluate the semantic preservation performance of multiple translation methods. Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process. Extensive experiments demonstrate the superiority of the proposed PearlGAN over other image translation methods for the NTIR2DC task. The source code and labeled segmentation masks will be available at \url{https://github.com/FuyaLuo/PearlGAN/}.