# Cascaded Generation of High-quality Color Visible Face Images from Thermal Captures

arXiv: https://arxiv.org/abs/1910.09524 · HTML: https://mlsanity.com/paper/1910.09524/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2019.

## Built on by (most cited first, 3 of 3)

- [Biometrics in the Era of COVID-19: Challenges and Opportunities](https://mlsanity.com/paper/2102.09258/) (2021)
- [I2V-GAN: Unpaired Infrared-to-Visible Video Translation](https://mlsanity.com/paper/2108.00913/) (2021)
- [When Visible-to-Thermal Facial GAN Beats Conditional Diffusion](https://mlsanity.com/paper/2302.09395/) (2023)

## Abstract (arXiv)

Generating visible-like face images from thermal images is essential to perform manual and automatic cross-spectrum face recognition. We successfully propose a solution based on cascaded refinement network that, unlike previous works, produces high quality generated color images without the need for face alignment, large databases, data augmentation, polarimetric sensors, computationally-intense training, or unrealistic restriction on the generated resolution. The training of our solution is based on the contextual loss, making it inherently scale (face area) and rotation invariant. We present generated image samples of unknown individuals under different poses and occlusion conditions.We also prove the high similarity in image quality between ground-truth images and generated ones by comparing seven quality metrics. We compare our results with two state-of-the-art approaches proving the superiority of our proposed approach.