SMFD-UNet deblurs faces by generating semantic component masks from blurry inputs and fusing them via multi-stage UNet with residual dense blocks and attention, reporting higher PSNR and SSIM on CelebA than prior models.
Maskgan: Towards diverse and interactive facial image manipulation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SMFD-UNet: Semantic Face Mask Is The Only Thing You Need To Deblur Faces
SMFD-UNet deblurs faces by generating semantic component masks from blurry inputs and fusing them via multi-stage UNet with residual dense blocks and attention, reporting higher PSNR and SSIM on CelebA than prior models.