TechRxiv
TVA_GAN (3).pdf (11.84 MB)

TVA-GAN: Attention Guided Generative Adversarial Network For Thermal To Visible Image Transformations

Download (11.84 MB)
preprint
posted on 2022-01-28, 21:08 authored by NAND YADAVNAND YADAV, Satish Kumar Singh, Shiv Ram Dubey
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.

History

Email Address of Submitting Author

pis2016004@iiita.ac.in

Submitting Author's Institution

Indian Institute of Information Technology Allahabad

Submitting Author's Country

  • India