Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraint

TL;DR

This paper introduces a novel GAN-based face hallucination method that incorporates frequency awareness and semantic structural constraints to improve the quality of high-resolution face images from low-resolution inputs.

Contribution

The work proposes a progressive face hallucination network with explicit high frequency component encoding and 3D structural constraints, advancing beyond existing 2D prior-based methods.

Findings

Outperforms state-of-the-art face hallucination methods

Effectively preserves local features and structural details

Enhances depth information in generated images

Abstract

In this paper, we address the issue of face hallucination. Most current face hallucination methods rely on two-dimensional facial priors to generate high resolution face images from low resolution face images. These methods are only capable of assimilating global information into the generated image. Still there exist some inherent problems in these methods; such as, local features, subtle structural details and missing depth information in final output image. Present work proposes a Generative Adversarial Network (GAN) based novel progressive Face Hallucination (FH) network to address these issues present among current methods. The generator of the proposed model comprises of FH network and two sub-networks, assisting FH network to generate high resolution images. The first sub-network leverages on explicitly adding high frequency components into the model. To explicitly encode the high frequency components, an auto encoder is proposed to generate high resolution coefficients of Discrete Cosine Transform (DCT). To add three dimensional parametric information into the network, second sub-network is proposed. This network uses a shape model of 3D Morphable Models (3DMM) to add structural constraint to the FH network. Extensive experimentation results in the paper shows that the proposed model outperforms the state-of-the-art methods.