TechRxiv
41463294_File000000_1013984268.pdf (11.67 MB)
Download file

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

Download (11.67 MB)
preprint
posted on 19.04.2021, 15:20 by NAND YADAVNAND YADAV
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

nandkmyadav@gmail.com

Submitting Author's Institution

Indian Institute Of information Technology

Submitting Author's Country

India

Usage metrics

Licence

Exports