Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network

TL;DR

This paper introduces a wavelet-based feature enhancement network for face super-resolution that reduces distortion and improves efficiency by decomposing features into frequency components and using a Transformer for enhanced feature extraction.

Contribution

It presents a novel wavelet-based approach combined with a Transformer to improve face super-resolution efficiency and accuracy without increasing model complexity.

Findings

Outperforms previous methods in balancing performance and efficiency.

Effectively reduces high-frequency feature distortion.

Achieves superior results with fewer modules.

Abstract

Face super-resolution aims to reconstruct a high-resolution face image from a low-resolution face image. Previous methods typically employ an encoder-decoder structure to extract facial structural features, where the direct downsampling inevitably introduces distortions, especially to high-frequency features such as edges. To address this issue, we propose a wavelet-based feature enhancement network, which mitigates feature distortion by losslessly decomposing the input feature into high and low-frequency components using the wavelet transform and processing them separately. To improve the efficiency of facial feature extraction, a full domain Transformer is further proposed to enhance local, regional, and global facial features. Such designs allow our method to perform better without stacking many modules as previous methods did. Experiments show that our method effectively balances performance, model size, and speed. Code link: https://github.com/PRIS-CV/WFEN.