English

PSRFlow: Probabilistic Super Resolution with Flow-Based Models for Scientific Data

Image and Video Processing 2023-08-10 v1 Computer Vision and Pattern Recognition Graphics Machine Learning

Abstract

Although many deep-learning-based super-resolution approaches have been proposed in recent years, because no ground truth is available in the inference stage, few can quantify the errors and uncertainties of the super-resolved results. For scientific visualization applications, however, conveying uncertainties of the results to scientists is crucial to avoid generating misleading or incorrect information. In this paper, we propose PSRFlow, a novel normalizing flow-based generative model for scientific data super-resolution that incorporates uncertainty quantification into the super-resolution process. PSRFlow learns the conditional distribution of the high-resolution data based on the low-resolution counterpart. By sampling from a Gaussian latent space that captures the missing information in the high-resolution data, one can generate different plausible super-resolution outputs. The efficient sampling in the Gaussian latent space allows our model to perform uncertainty quantification for the super-resolved results. During model training, we augment the training data with samples across various scales to make the model adaptable to data of different scales, achieving flexible super-resolution for a given input. Our results demonstrate superior performance and robust uncertainty quantification compared with existing methods such as interpolation and GAN-based super-resolution networks.

Keywords

Cite

@article{arxiv.2308.04605,
  title  = {PSRFlow: Probabilistic Super Resolution with Flow-Based Models for Scientific Data},
  author = {Jingyi Shen and Han-Wei Shen},
  journal= {arXiv preprint arXiv:2308.04605},
  year   = {2023}
}

Comments

To be published in Proc. IEEE VIS 2023

R2 v1 2026-06-28T11:51:24.250Z