Structured Uncertainty Prediction Networks

02/20/2018
by   Garoe Dorta, et al.
0

This paper is the first work to propose a network to predict a structured uncertainty distribution for a reconstructed image. Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation. We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset