Saved in:
Bibliographic Details
Main Authors: Li, Wenjie, Guo, Heng, Liu, Xuannan, Liang, Kongming, Hu, Jiani, Ma, Zhanyu, Guo, Jun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.19768
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911971836690432
author Li, Wenjie
Guo, Heng
Liu, Xuannan
Liang, Kongming
Hu, Jiani
Ma, Zhanyu
Guo, Jun
author_facet Li, Wenjie
Guo, Heng
Liu, Xuannan
Liang, Kongming
Hu, Jiani
Ma, Zhanyu
Guo, Jun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19768
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
Li, Wenjie
Guo, Heng
Liu, Xuannan
Liang, Kongming
Hu, Jiani
Ma, Zhanyu
Guo, Jun
Computer Vision and Pattern Recognition
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.
title Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.19768