A trained noise-prior predictor converts iterative latent search in GAN inpainting into a single feed-forward pass, and a recurrent grouped-prior model enables unsupervised sequence inpainting.
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
-
The Angel is in the Priors: Improving GAN based Image and Sequence Inpainting with Better Noise and Structural Priors
A trained noise-prior predictor converts iterative latent search in GAN inpainting into a single feed-forward pass, and a recurrent grouped-prior model enables unsupervised sequence inpainting.