Frequency-Aware Facial Image Shadow Removal through Skin Color and Texture Learning

Zhang, Ling; Xie, Wenyang; Xiao, Chunxia

Frequency-Aware Facial Image Shadow Removal through Skin Color and Texture Learning

Files

cgf15220.pdf (11.26 MB)

Date

2024

Authors

Zhang, Ling
Xie, Wenyang
Xiao, Chunxia

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

Existing facial image shadow removal methods predominantly rely on pre-extracted facial features. However, these methods often fail to capitalize on the full potential of these features, resorting to simplified utilization. Furthermore, they tend to overlook the importance of low-frequency information during the extraction of prior features, which can be easily compromised by noises. In our work, we propose a frequency-aware shadow removal network (FSRNet) for facial image shadow removal, which utilizes the skin color and texture information in the face to help recover illumination in shadow regions. Our FSRNet uses a frequencydomain image decomposition network to extract the low-frequency skin color map and high-frequency texture map from the face images, and applies a color-texture guided shadow removal network to produce final shadow removal result. Concretely, the designed fourier sparse attention block (FSABlock) can transform images from the spatial domain to the frequency domain and help the network focus on the key information. We also introduce a skin color fusion module (CFModule) and a texture fusion module (TFModule) to enhance the understanding and utilization of color and texture features, promoting high-quality result without color distortion and detail blurring. Extensive experiments demonstrate the superiority of the proposed method. The code is available at https://github.com/laoxie521/FSRNet.

CCS Concepts: Computing methodologies → Shadow removal; Facial image; Feature fusion; Frequency-aware

        @article{10.1111:cgf.15220
,
journal = {Computer Graphics Forum},
title = {{Frequency-Aware Facial Image Shadow Removal through Skin Color and Texture Learning
}},
author = {Zhang, Ling and 
Xie, Wenyang and 
Xiao, Chunxia
},
year = {2024
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.15220
}
}