Conditional Image Generation by Conditioning Variational Auto-Encoders
William Harvey, Saeid Naderiparizi, Frank Wood
Abstract
We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE. To train the conditional VAE, we only need to train an artifact to perform amortized inference over the unconditional VAE's latent variables given a conditioning input. We demonstrate our approach on tasks including image inpainting, for which it outperforms state-of-the-art GAN-based approaches at faithfully representing the inherent uncertainty. We conclude by describing a possible application of our inpainting model, in which it is used to perform Bayesian experimental design for the purpose of guiding a sensor.
BibTeX
@inproceedings{
harvey2022conditional,
title={Conditional Image Generation by Conditioning Variational Auto-Encoders},
author={William Harvey and Saeid Naderiparizi and Frank Wood},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=7MV6uLzOChW}
}