FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Siyu, Li, Wenjie, Gao, Guangwei, Yang, Jian, Qi, Guo-Jun, Lin, Chia-Wen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917412400529408
author Xu, Siyu
Li, Wenjie
Gao, Guangwei
Yang, Jian
Qi, Guo-Jun
Lin, Chia-Wen
author_facet Xu, Siyu
Li, Wenjie
Gao, Guangwei
Yang, Jian
Qi, Guo-Jun
Lin, Chia-Wen
contents Face super-resolution (FSR) under limited computational budgets remains challenging. Existing methods often treat all facial pixels equally, leading to suboptimal resource allocation and degraded performance. CNNs are sensitive to high-frequency facial features such as contours and outlines, while Mamba excels at capturing low-frequency attributes like facial color and texture with lower complexity than Transformers. Motivated by this, we propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components for dedicated processing. The low-frequency branch employs a Mamba-based Low-Frequency Enhancement Block (LFEB) that integrates state-space attention with squeeze-and-excitation to restore global interactions and emphasize informative channels. The high-frequency branch uses a CNN-based Deep Position-Aware Attention (DPA) module to refine structural details, followed by a lightweight High-Frequency Refinement (HFR) module for further frequency-specific refinement. These designs enable FADPNet to achieve a strong balance between FSR quality and efficiency, outperforming existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14121
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution
Xu, Siyu
Li, Wenjie
Gao, Guangwei
Yang, Jian
Qi, Guo-Jun
Lin, Chia-Wen
Computer Vision and Pattern Recognition
Face super-resolution (FSR) under limited computational budgets remains challenging. Existing methods often treat all facial pixels equally, leading to suboptimal resource allocation and degraded performance. CNNs are sensitive to high-frequency facial features such as contours and outlines, while Mamba excels at capturing low-frequency attributes like facial color and texture with lower complexity than Transformers. Motivated by this, we propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components for dedicated processing. The low-frequency branch employs a Mamba-based Low-Frequency Enhancement Block (LFEB) that integrates state-space attention with squeeze-and-excitation to restore global interactions and emphasize informative channels. The high-frequency branch uses a CNN-based Deep Position-Aware Attention (DPA) module to refine structural details, followed by a lightweight High-Frequency Refinement (HFR) module for further frequency-specific refinement. These designs enable FADPNet to achieve a strong balance between FSR quality and efficiency, outperforming existing methods.
title FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14121