Papers

Strong-Lensing Source Reconstruction with Denoising Diffusion Restoration Models

K Karchev, NA Montel, A Coogan… - arXiv preprint arXiv …, 2022 - arxiv.org
Astrophysics paper astro-ph.IM Suggest

… We expect the denoising diffusion approach to source reconstruction to prove instrumental in generating constrained training examples for simulation-based inference of dark matter …

Cited by Link to paper

BibTeX

@article{2211.04365v1,
Author        = {Konstantin Karchev and Noemi Anau Montel and Adam Coogan and Christoph Weniger},
Title         = {Strong-Lensing Source Reconstruction with Denoising Diffusion
  Restoration Models},
Eprint        = {2211.04365v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {astro-ph.IM},
Abstract      = {Analysis of galaxy--galaxy strong lensing systems is strongly dependent on
any prior assumptions made about the appearance of the source. Here we present
a method of imposing a data-driven prior / regularisation for source galaxies
based on denoising diffusion probabilistic models (DDPMs). We use a pre-trained
model for galaxy images, AstroDDPM, and a chain of conditional reconstruction
steps called denoising diffusion reconstruction model (DDRM) to obtain samples
consistent both with the noisy observation and with the distribution of
training data for AstroDDPM. We show that these samples have the qualitative
properties associated with the posterior for the source model: in a
low-to-medium noise scenario they closely resemble the observation, while
reconstructions from uncertain data show greater variability, consistent with
the distribution encoded in the generative model used as prior.},
Year          = {2022},
Month         = {Nov},
Url           = {http://arxiv.org/abs/2211.04365v1},
File          = {2211.04365v1.pdf}
}

Share