loading page

TVA-GAN: Attention Guided Generative Adversarial Network For Thermal To Visible Image Transformations
  • NAND YADAV ,
  • Satish Kumar Singh ,
  • Shiv Ram Dubey
NAND YADAV
Indian Institute Of information Technology, Indian Institute of Information Technology Allahabad
Author Profile
Satish Kumar Singh
Author Profile
Shiv Ram Dubey
Author Profile

Abstract

In the recent advancement of machine learning methods for realistic image generation and image translation, Generative Adversarial Networks (GANs) play a vital role. GAN generates novel samples that look indistinguishable from the real images. The image translation using a generative adversarial network refers to unsupervised learning. In this paper, we translate the thermal images into visible images. Thermal to Visible image translation is challenging due to the non-availability of accurate semantic information and smooth textures. The thermal images contain only single-channel, holding only the images’ luminance with less feature. We develop a new Cyclic Attention-based Generative Adversarial Network for Thermal to Visible Face transformation (TVA-GAN) by incorporating a new attention-based network. We use attention guidance with a recurrent block through an Inception module to reduce the learning space towards the optimum solution.
Sep 2023Published in Neural Computing and Applications volume 35 issue 27 on pages 19729-19749. 10.1007/s00521-023-08724-5