Can denoising diffusion probabilistic models generate realistic astrophysical fields? by Nayantara Mudur et al. on Thursday 24 November

Score-based generative models have emerged as alternatives to generative

adversarial networks (GANs) and normalizing flows for tasks involving learning

and sampling from complex image distributions. In this work we investigate the

ability of these models to generate fields in two astrophysical contexts: dark

matter mass density fields from cosmological simulations and images of

interstellar dust. We examine the fidelity of the sampled cosmological fields

relative to the true fields using three different metrics, and identify

potential issues to address. We demonstrate a proof-of-concept application of

the model trained on dust in denoising dust images. To our knowledge, this is

the first application of this class of models to the interstellar medium.

arXiv: http://arxiv.org/abs/http://arxiv.org/abs/2211.12444v1