# Approximate Inference for Constructing Astronomical Catalogs from Images

arXiv: https://arxiv.org/abs/1803.00113 · HTML: https://mlsanity.com/paper/1803.00113/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2018.

## Built on by (most cited first, 4 of 4)

- [Variational Inference for Deblending Crowded Starfields](https://mlsanity.com/paper/2102.02409/) (2021)
- [Scalable Bayesian Inference for Detection and Deblending in Astronomical Images](https://mlsanity.com/paper/2207.05642/) (2022)
- [Neural Posterior Estimation with Autoregressive Tiling for Detecting Objects in Astronomical Images](https://mlsanity.com/paper/2510.03074/) (2025)
- [Bayesian In Vivo Tracking of Synapses using Joint Poisson Deconvolution and Diffeomorphic Registration](https://mlsanity.com/paper/2605.13455/) (2026)

## Abstract (arXiv)

We present a new, fully generative model for constructing astronomical catalogs from optical telescope image sets. Each pixel intensity is treated as a random variable with parameters that depend on the latent properties of stars and galaxies. These latent properties are themselves modeled as random. We compare two procedures for posterior inference. One procedure is based on Markov chain Monte Carlo (MCMC) while the other is based on variational inference (VI). The MCMC procedure excels at quantifying uncertainty, while the VI procedure is 1000 times faster. On a supercomputer, the VI procedure efficiently uses 665,000 CPU cores to construct an astronomical catalog from 50 terabytes of images in 14.6 minutes, demonstrating the scaling characteristics necessary to construct catalogs for upcoming astronomical surveys.