La revue comme échec

Letawe, Céline; Provenzano, François

doi:10.4000/grm.968

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deconvolution has long been known as an "ill-posed" inverse problem because there is often no unique solution if one follows the signal processing approach of backwards modelling (Magain et al 1998Letawe et al 2007Letawe et al , 2008Cantale et al 2016). Another standard practice in tackling inverse problems like these is integrating priors using domain knowledge in forward modelling.…”

Section: Introductionmentioning

confidence: 99%

Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limit

Schawinski

Zhang

et al. 2017

Monthly Notices of the Royal Astronomical Society: Letters

215

138

View full text Add to dashboard Cite

Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional deconvolution techniques are limited in their ability to recover features in imaging data by the Shannon-Nyquist sampling theorem. Here we train a generative adversarial network (GAN) on a sample of 4, 550 images of nearby galaxies at 0.01 < z < 0.02 from the Sloan Digital Sky Survey and conduct 10× cross validation to evaluate the results. We present a method using a GAN trained on galaxy images that can recover features from artificially degraded images with worse seeing and higher noise than the original with a performance which far exceeds simple deconvolution. The ability to better recover detailed features such as galaxy morphology from low-signal-to-noise and low angular resolution imaging data significantly increases our ability to study existing data sets of astrophysical objects as well as future observations with observatories such as the Large Synoptic Sky Telescope (LSST) and the Hubble and James Webb space telescopes.

show abstract

Section: Introductionmentioning

confidence: 99%