# Matching Thermal to Visible Face Images Using a Semantic-Guided Generative Adversarial Network

arXiv: https://arxiv.org/abs/1903.00963 · HTML: https://mlsanity.com/paper/1903.00963/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [Beyond the Visible: A Survey on Cross-spectral Face Recognition](https://mlsanity.com/paper/2201.04435/) (2022)
- [When Visible-to-Thermal Facial GAN Beats Conditional Diffusion](https://mlsanity.com/paper/2302.09395/) (2023)
- [Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels](https://mlsanity.com/paper/2106.08091/) (2021)
- [Vista-Morph: Unsupervised Image Registration of Visible-Thermal Facial Pairs](https://mlsanity.com/paper/2306.06505/) (2023)
- [Multi-Domain Biometric Recognition using Body Embeddings](https://mlsanity.com/paper/2503.10931/) (2025)
- [Sustainable Face Recognition on Low-Power Devices with VQ-VAE Embeddings](https://mlsanity.com/paper/2606.15355/) (2026)

## Abstract (arXiv)

Designing face recognition systems that are capable of matching face images obtained in the thermal spectrum with those obtained in the visible spectrum is a challenging problem. In this work, we propose the use of semantic-guided generative adversarial network (SG-GAN) to automatically synthesize visible face images from their thermal counterparts. Specifically, semantic labels, extracted by a face parsing network, are used to compute a semantic loss function to regularize the adversarial network during training. These semantic cues denote high-level facial component information associated with each pixel. Further, an identity extraction network is leveraged to generate multi-scale features to compute an identity loss function. To achieve photo-realistic results, a perceptual loss function is introduced during network training to ensure that the synthesized visible face is perceptually similar to the target visible face image. We extensively evaluate the benefits of individual loss functions, and combine them effectively to learn the mapping from thermal to visible face images. Experiments involving two multispectral face datasets show that the proposed method achieves promising results in both face synthesis and cross-spectral face matching.