Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
This addresses a practical issue in surveillance systems where thermal images are low-resolution, enabling better face verification for security applications, though it is incremental as it builds on existing GAN and transformer techniques.
The paper tackles the problem of thermal-to-visible face verification from low-resolution thermal images in long-range surveillance, proposing Axial-GAN to synthesize high-resolution visible images, resulting in significant improvements in image quality and verification performance compared to state-of-the-art methods.
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution. This is unlikely in real-world long-range surveillance systems, since humans are distant from the cameras. To address this issue, we introduce the task of thermal-to-visible face verification from low-resolution thermal images. Furthermore, we propose Axial-Generative Adversarial Network (Axial-GAN) to synthesize high-resolution visible images for matching. In the proposed approach we augment the GAN framework with axial-attention layers which leverage the recent advances in transformers for modelling long-range dependencies. We demonstrate the effectiveness of the proposed method by evaluating on two different thermal-visible face datasets. When compared to related state-of-the-art works, our results show significant improvements in both image quality and face verification performance, and are also much more efficient.