Identity-Aware Deep Face Hallucination via Adversarial Face Verification

TL;DR

This paper introduces a multi-scale GAN architecture for face hallucination that emphasizes identity preservation and perceptual quality, outperforming existing methods on standard datasets.

Contribution

The work presents a novel multi-scale generator and a discriminator with identity verification, enhancing face hallucination with identity preservation and perceptual loss.

Findings

Outperforms state-of-the-art methods on LFW and CelebA datasets.

Effectively preserves identity features in high-resolution face images.

Achieves high-quality face hallucination at 8x upscaling.

Abstract

In this paper, we address the problem of face hallucination by proposing a novel multi-scale generative adversarial network (GAN) architecture optimized for face verification. First, we propose a multi-scale generator architecture for face hallucination with a high up-scaling ratio factor, which has multiple intermediate outputs at different resolutions. The intermediate outputs have the growing goal of synthesizing small to large images. Second, we incorporate a face verifier with the original GAN discriminator and propose a novel discriminator which learns to discriminate different identities while distinguishing fake generated HR face images from their ground truth images. In particular, the learned generator cares for not only the visual quality of hallucinated face images but also preserving the discriminative features in the hallucination process. In addition, to capture perceptually relevant differences we employ a perceptual similarity loss, instead of similarity in pixel space. We perform a quantitative and qualitative evaluation of our framework on the LFW and CelebA datasets. The experimental results show the advantages of our proposed method against the state-of-the-art methods on the 8x downsampled testing dataset.