Thermal Face Image Generator

Abstract

This work addresses two image-to-image translation tasks. The first task is to convert a visible face image into a thermal face image (V2T) and the second task is to convert a thermal face image into another thermal face image with a given target temperature (T2T). We propose to use conditional generative adversarial networks to solve the two tasks. We train our models using Carl and SpeakingFaces Datasets, and use SSIM to measure the performance of our models. The SSIM of the generated thermal images reach 0.82 and 0.84 for the V2T and T2T tasks respectively.