Our algorithm is few-shot: Given about a dozen images restored by the model, it can significantly improve the perceptual quality and/or the MSE of the model for newly restored images without further training.

The Gaussianity assumption has been consistently criticized as a main limitation of the V ariational Autoencoder (V AE) despite its efficiency in computational modeling. In this paper, we propose a new approach that expands the model capacity (i.e., expressive power of distributional family) without sacrificing the computational advantages of the V AE framework. Our V AE model's decoder is composed of an infinite mixture of asymmetric Laplace distribution, which possesses general

We revisit this scenario as an experimental case study in Section 6.

Both challenges involve modeling long-term dependencies.