# Celeste: Variational inference for a generative model of astronomical images

arXiv: https://arxiv.org/abs/1506.01351 · HTML: https://mlsanity.com/paper/1506.01351/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2015.

## Built on by (most cited first, 7 of 7)

- [Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy](https://mlsanity.com/paper/2211.03796/) (2022)
- [Amortized Variational Inference: A Systematic Review](https://mlsanity.com/paper/2209.10888/) (2022)
- [A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science](https://mlsanity.com/paper/2403.12636/) (2024)
- [An Introduction to Variational Inference](https://mlsanity.com/paper/2108.13083/) (2021)
- [Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges](https://mlsanity.com/paper/2211.14732/) (2022)
- [Nested Diffusion Models Using Hierarchical Latent Priors](https://mlsanity.com/paper/2412.05984/) (2024)
- [Generative Principal Component Regression via Variational Inference](https://mlsanity.com/paper/2409.02327/) (2024)

## Abstract (arXiv)

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.