W-Net: A Facial Feature-Guided Face Super-Resolution Network

TL;DR

W-Net is a novel face super-resolution network that leverages facial priors and a W-shaped architecture to improve reconstruction quality, efficiency, and downstream task performance.

Contribution

The paper introduces W-Net, a new architecture that effectively utilizes facial parsing maps and a W-shaped structure for enhanced face super-resolution.

Findings

Outperforms existing methods in quantitative metrics

Improves visual quality of reconstructed faces

Enhances downstream facial recognition and keypoint detection

Abstract

Face Super-Resolution (FSR) aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Despite the progress made by convolutional neural networks in FSR, the results of existing approaches are not ideal due to their low reconstruction efficiency and insufficient utilization of prior information. Considering that faces are highly structured objects, effectively leveraging facial priors to improve FSR results is a worthwhile endeavor. This paper proposes a novel network architecture called W-Net to address this challenge. W-Net leverages meticulously designed Parsing Block to fully exploit the resolution potential of LR image. We use this parsing map as an attention prior, effectively integrating information from both the parsing map and LR images. Simultaneously, we perform multiple fusions in various dimensions through the W-shaped network structure combined with the LPF(LR-Parsing Map Fusion Module). Additionally, we utilize a facial parsing graph as a mask, assigning different weights and loss functions to key facial areas to balance the performance of our reconstructed facial images between perceptual quality and pixel accuracy. We conducted extensive comparative experiments, not only limited to conventional facial super-resolution metrics but also extending to downstream tasks such as facial recognition and facial keypoint detection. The experiments demonstrate that W-Net exhibits outstanding performance in quantitative metrics, visual quality, and downstream tasks.