Search Results for author:
Found 3 papers, 1 papers with code
Canonical normalizing flows for manifold learning
Alternatively, if a locally orthogonal and/or sparse basis is to be learned, here coined canonical intrinsic basis, it can serve in learning a more compact latent space representation.
Explicitly Minimizing the Blur Error of Variational Autoencoders
Variational autoencoders (VAEs) are powerful generative modelling methods, however they suffer from blurry generated samples and reconstructions compared to the images they have been trained on.
Gradient flow encoding with distance optimization adaptive step size
In this work, we investigate a decoder-only method that uses gradient flow to encode data samples in the latent space.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
