FADPNet processes low- and high-frequency facial content with separate Mamba and CNN branches and reports the best PSNR/SSIM among compared x8 face super-resolution methods on CelebA and Helen.
Survey on deep face restoration: From non-blind to blind and beyond
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2verdicts
CONDITIONAL 2representative citing papers
T-PMambaSR, a hybrid Transformer-Mamba architecture with progressive receptive-field expansion, achieves competitive lightweight super-resolution performance with reduced parameters.
citing papers explorer
-
FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution
FADPNet processes low- and high-frequency facial content with separate Mamba and CNN branches and reports the best PSNR/SSIM among compared x8 face super-resolution methods on CelebA and Helen.
-
Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution
T-PMambaSR, a hybrid Transformer-Mamba architecture with progressive receptive-field expansion, achieves competitive lightweight super-resolution performance with reduced parameters.