A zero-shot neural optimization, using a Deep Image Prior network for the sharp image and a fully connected Softmax network for the blur kernel, achieves competitive state-of-the-art blind deconvolution on benchmarks.
Title resolution pending
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
-
Neural Blind Deconvolution Using Deep Priors
A zero-shot neural optimization, using a Deep Image Prior network for the sharp image and a fully connected Softmax network for the blur kernel, achieves competitive state-of-the-art blind deconvolution on benchmarks.