A practical generative adversarial network architecture for restoring damaged character photographs
Neurocomputing（2021）
Abstract
•We collect real world DCPs, unpaired CCPs, and dirty masks and proposed a residual U-Net GAN.•We put forward a residual U-Net conditional GAN to restore real DCPs.•We adopt a weighted multi-features loss to improve the quality of generated photographs.
MoreTranslated text
Key words
Damaged photographs restoration,Deep learning,GAN
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined