Skip to content

Learn a diffusion model prior on simulations to help real image deconvolution (JWST)

License

Notifications You must be signed in to change notification settings

astroinfo-hacks/2023-imgen-diffusion

Repository files navigation

Generative modeling of astro images with diffusion models

Rationale

The goal of this hack is to use Diffusion Models to build a simulations-driven prior that can be used to denoise and deconvolve galaxy images from JWST.

We would follow these steps:

  1. Gather simulated galaxy images from the Illustris TNG hydrodynamical simulations to act as a prior on what perfect observations would look like:
    image image

  2. Train a Score-Based Denoising Diffusion Model on these images. This is a type of generative models which can learn to generate images similar to the input training data. These diffusion models work by learning a mapping from pure noise to images in the training set: image

  3. Use the knownledge about galaxy morphology collected by the model to solve the inverse problem of reconstructing a high resolution, PSF-deconvolved, and noise-free image of observed JWST images similar to these: image

In more details, we will be using a forward model of the observed images, which takes into account the noise and and PSF properties of the image, and solve a Bayesian inverse problem with the Diffusion Model as our prior, to sample posterior images, compatible with the observations and still likely under the prior.

You can watch the hack presentation by Marc during the telecon.

Dataset

We will be using galaxy images from Illustris TNG, prepared with a radiative transfer code. The observations we will try to denoise and deconvolve are galaxy images from JWST.

References

About

Learn a diffusion model prior on simulations to help real image deconvolution (JWST)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published