DeepAI AI Chat
Log In Sign Up

SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination

by   Chih-Chung Hsu, et al.
National Institute of Informatics
National Tsing Hua University
1, Shuefu Road, Neipu, Pingtung 91201, TAIWAN

Despite generative adversarial networks (GANs) can hallucinate photo-realistic high-resolution (HR) faces from low-resolution (LR) faces, they cannot guarantee preserving the identities of hallucinated HR faces, making the HR faces poorly recognizable. To address this problem, we propose a Siamese GAN (SiGAN) to reconstruct HR faces that visually resemble their corresponding identities. On top of a Siamese network, the proposed SiGAN consists of a pair of two identical generators and one discriminator. We incorporate reconstruction error and identity label information in the loss function of SiGAN in a pairwise manner. By iteratively optimizing the loss functions of the generator pair and discriminator of SiGAN, we cannot only achieve photo-realistic face reconstruction, but also ensures the reconstructed information is useful for identity recognition. Experimental results demonstrate that SiGAN significantly outperforms existing face hallucination GANs in objective face verification performance, while achieving photo-realistic reconstruction. Moreover, for input LR faces from unknown identities who are not included in training, SiGAN can still do a good job.


page 1

page 8

page 9

page 10


Generate Identity-Preserving Faces by Generative Adversarial Networks

Generating identity-preserving faces aims to generate various face image...

Semantically Decomposing the Latent Spaces of Generative Adversarial Networks

We propose a new algorithm for training generative adversarial networks ...

WarpGAN: Automatic Caricature Generation

We propose, WarpGAN, a fully automatic network that can generate caricat...

SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis

Advances in face rotation, along with other face-based generative tasks,...

Face Morphing: Fooling a Face Recognition System Is Simple!

State-of-the-art face recognition (FR) approaches have shown remarkable ...

PROVES: Establishing Image Provenance using Semantic Signatures

Modern AI tools, such as generative adversarial networks, have transform...

Learning Robust 3D Face Reconstruction and Discriminative Identity Representation

3D face reconstruction from a single 2D image is a very important topic ...