DeepAI
Log In Sign Up

Celeste: Variational inference for a generative model of astronomical images

06/03/2015
by   Jeffrey Regier, et al.
0

We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random variable, with a rate parameter dependent on latent properties of stars and galaxies. Key latent properties are themselves random, with scientific prior distributions constructed from large ancillary data sets. We check our approach on synthetic images. We also run it on images from a major sky survey, where it exceeds the performance of the current state-of-the-art method for locating celestial bodies and measuring their colors.

READ FULL TEXT

page 1

page 3

page 4

page 8

02/28/2018

Approximate Inference for Constructing Astronomical Catalogs from Images

We present a new, fully generative model for constructing astronomical c...
06/10/2022

PAVI: Plate-Amortized Variational Inference

Given some observed data and a probabilistic generative model, Bayesian ...
05/19/2017

Bayesian Nonparametric Poisson-Process Allocation for Time-Sequence Modeling

Analyzing the underlying structure of multiple time-sequences provides i...
02/27/2019

Training Variational Autoencoders with Buffered Stochastic Variational Inference

The recognition network in deep latent variable models such as variation...
06/21/2020

Isometric Gaussian Process Latent Variable Model for Dissimilarity Data

We propose a fully generative model where the latent variable respects b...
12/28/2020

Joint Intensity-Gradient Guided Generative Modeling for Colorization

This paper proposes an iterative generative model for solving the automa...
10/21/2008

Astronomical imaging: The theory of everything

We are developing automated systems to provide homogeneous calibration m...