Efficient Posterior Sampling for Diverse Super-Resolution with Hierarchical VAE Prior

Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis

2024

Abstract

We investigate the problem of producing diverse solutions to an image super-resolution problem. From a probabilistic perspective, this can be done by sampling from the posterior distribution of an inverse problem, which requires the definition of a prior distribution on the high-resolution images. In this work, we propose to use a pretrained hierarchical variational autoencoder (HVAE) as a prior. We train a lightweight stochastic encoder to encode low-resolution images in the latent space of a pretrained HVAE. At inference, we combine the low-resolution encoder and the pretrained generative model to super-resolve an image. We demonstrate on the task of face super-resolution that our method provides an advantageous trade-off between the computational efficiency of conditional normalizing flows techniques and the sample quality of diffusion based methods.

Paper Citation

in Harvard Style

Prost J., Houdard A., Almansa A. and Papadakis N. (2024). Efficient Posterior Sampling for Diverse Super-Resolution with Hierarchical VAE Prior. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 393-400. DOI: 10.5220/0012352800003660

in Bibtex Style

@conference{visapp24,
author={Jean Prost and Antoine Houdard and Andrés Almansa and Nicolas Papadakis},
title={Efficient Posterior Sampling for Diverse Super-Resolution with Hierarchical VAE Prior},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={393-400},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012352800003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Efficient Posterior Sampling for Diverse Super-Resolution with Hierarchical VAE Prior
SN - 978-989-758-679-8
AU - Prost J.
AU - Houdard A.
AU - Almansa A.
AU - Papadakis N.
PY - 2024
SP - 393
EP - 400
DO - 10.5220/0012352800003660
PB - SciTePress