Bayesian imaging inverse problem with scattering transform

TL;DR

This paper presents a Bayesian imaging inverse problem approach using Scattering Transform statistics to enable effective inference and reconstruction in low-data astrophysical and cosmological settings without relying on external priors.

Contribution

It introduces a novel Bayesian method leveraging Scattering Transform features for inverse problems, allowing inference in low-data regimes with complex forward models.

Findings

Accurate statistical inference demonstrated on large-scale structure data.

Deterministic signal reconstruction from a single contaminated image.

Effective handling of non-Gaussian signals without external priors.

Abstract

Bayesian imaging inverse problems in astrophysics and cosmology remain challenging, particularly in low-data regimes, due to complex forward operators and the frequent lack of well-motivated priors for non-Gaussian signals. In this paper, we introduce a Bayesian approach that addresses these difficulties by relying on a low-dimensional representation of physical fields built from Scattering Transform statistics. This representation enables inference to be performed in a compact model space, where we recover a posterior distribution over signal models that are consistent with the observed data. We propose an iterative adaptive algorithm to efficiently approximate this posterior distribution. We apply our method to a large-scale structure column density field from the Quijote simulations, using a realistic instrumental forward operator. We demonstrate both accurate statistical inference and deterministic signal reconstruction from a single contaminated image, without relying on any external prior distribution for the field of interest. These results demonstrate that Scattering Transform statistics provide an effective representation for solving complex imaging inverse problems in challenging low-data regimes. Our approach opens the way to new applications for non-Gaussian astrophysical and cosmological signals for which little or no prior modeling is available.