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

Simple item page
dc.contributor.authorZhang, Lingen_US
dc.contributor.authorXie, Wenyangen_US
dc.contributor.authorXiao, Chunxiaen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:08:04Z
dc.date.available2024-10-13T18:08:04Z
dc.date.issued2024
dc.description.abstractExisting 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.en_US
dc.description.number7
dc.description.sectionheadersImage and Video Enhancement II
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15220
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15220
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15220
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Shadow removal; Facial image; Feature fusion; Frequency-aware
dc.subjectComputing methodologies → Shadow removal
dc.subjectFacial image
dc.subjectFeature fusion
dc.subjectFrequency
dc.subjectaware
dc.titleFrequency-Aware Facial Image Shadow Removal through Skin Color and Texture Learningen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
cgf15220.pdf
Size:
11.26 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 7