Using Haar wavelet coefficients as the latent representation of a VAE, with L1 sparsity regularization, reduces blur in reconstructions compared with a Gaussian latent VAE in reported single-run experiments.
Bowman, Luke Vilnis, Oriol Vinyals, Andrew M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Wavelet-based Variational Autoencoders for High-Resolution Image Generation
Using Haar wavelet coefficients as the latent representation of a VAE, with L1 sparsity regularization, reduces blur in reconstructions compared with a Gaussian latent VAE in reported single-run experiments.