RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark.
Zhuo DengYuanhao CaiLu ChenZheng GongQiqi BaoXue YaoDong FangShaochong ZhangLan MaPublished in: CoRR (2022)
Keyphrases
- image restoration
- total variation
- edge preserving
- regularization parameter
- image processing
- markov random field
- image deblurring
- regularization method
- super resolution
- iterative image restoration
- total least squares
- markov random field models
- gaussian noise
- wiener filter
- adaptive neighborhood
- image deconvolution
- blurred images
- kernel estimation
- restoration algorithm
- blur identification
- gauss markov
- modified hopfield neural network
- neural network
- blind image restoration
- image prior
- motion blur