Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
This work addresses the problem of feature distortion in face super-resolution for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles face super-resolution by proposing a wavelet-based feature enhancement network that reduces feature distortion through lossless decomposition and a full domain Transformer for efficient feature extraction, achieving a balance between performance, model size, and speed.
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.