Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network

TL;DR

This paper introduces SEGA-FURN, a novel face super-resolution network guided by semantic encoding and adversarial training, achieving superior results in ultra-resolving tiny low-resolution face images to high-resolution images.

Contribution

The paper presents a new semantic encoder, a hierarchical generator with RIDB, and a joint discriminator with RaLS loss, advancing face super-resolution techniques.

Findings

Outperforms state-of-the-art methods in qualitative assessments.

Achieves higher quantitative metrics on large face datasets.

Effectively handles multiple ultra-upscaling factors like 4x and 8x.

Abstract

Face super-resolution is a domain-specific image super-resolution, which aims to generate High-Resolution (HR) face images from their Low-Resolution (LR) counterparts. In this paper, we propose a novel face super-resolution method, namely Semantic Encoder guided Generative Adversarial Face Ultra-Resolution Network (SEGA-FURN) to ultra-resolve an unaligned tiny LR face image to its HR counterpart with multiple ultra-upscaling factors (e.g., 4x and 8x). The proposed network is composed of a novel semantic encoder that has the ability to capture the embedded semantics to guide adversarial learning and a novel generator that uses a hierarchical architecture named Residual in Internal Dense Block (RIDB). Moreover, we propose a joint discriminator which discriminates both image data and embedded semantics. The joint discriminator learns the joint probability distribution of the image space and latent space. We also use a Relativistic average Least Squares loss (RaLS) as the adversarial loss to alleviate the gradient vanishing problem and enhance the stability of the training procedure. Extensive experiments on large face datasets have proved that the proposed method can achieve superior super-resolution results and significantly outperform other state-of-the-art methods in both qualitative and quantitative comparisons.