Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces

TL;DR

This paper introduces a GAN-based method for synthesizing realistic visible face images from polarimetric thermal images, improving cross-domain face recognition by joint optimization and semantic guidance.

Contribution

The paper proposes a novel GAN framework with a guidance sub-network and combined loss functions for more photo-realistic and discriminative visible face synthesis from thermal images.

Findings

Achieves state-of-the-art performance in visible face synthesis

Outperforms previous two-step methods in realism and recognition accuracy

Demonstrates robustness across different experimental protocols

Abstract

The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domain makes cross-domain face recognition quite a challenging problem for both human-examiners and computer vision algorithms. Previous approaches utilize a two-step procedure (visible feature estimation and visible image reconstruction) to synthesize the visible image given the corresponding polarimetric thermal image. However, these are regarded as two disjoint steps and hence may hinder the performance of visible face reconstruction. We argue that joint optimization would be a better way to reconstruct more photo-realistic images for both computer vision algorithms and human-examiners to examine. To this end, this paper proposes a Generative Adversarial Network-based Visible Face Synthesis (GAN-VFS) method to synthesize more photo-realistic visible face images from their corresponding polarimetric images. To ensure that the encoded visible-features contain more semantically meaningful information in reconstructing the visible face image, a guidance sub-network is involved into the training procedure. To achieve photo realistic property while preserving discriminative characteristics for the reconstructed outputs, an identity loss combined with the perceptual loss are optimized in the framework. Multiple experiments evaluated on different experimental protocols demonstrate that the proposed method achieves state-of-the-art performance.