Blind deconvolution is solved by alternating gradient descent in the latent spaces of pretrained image and blur-kernel generators, with a slack variant that relaxes the image constraint.
Modeling the performance of image restora- tion from motion blur
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Blind Image Deconvolution using Pretrained Generative Priors
Blind deconvolution is solved by alternating gradient descent in the latent spaces of pretrained image and blur-kernel generators, with a slack variant that relaxes the image constraint.