# Realistic galaxy image simulation via score-based generative models

arXiv: https://arxiv.org/abs/2111.01713 · HTML: https://mlsanity.com/paper/2111.01713/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 0 of its 9 references that are in the map.
- First posted on arXiv 2 Nov 2021.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Built on by (most cited first, 24 of 24)

- [SoK: Privacy-Preserving Data Synthesis](https://mlsanity.com/paper/2307.02106/) (2023)
- [Posterior samples of source galaxies in strong gravitational lenses with score-based priors](https://mlsanity.com/paper/2211.03812/) (2022)
- [Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy](https://mlsanity.com/paper/2211.03796/) (2022)
- [Can denoising diffusion probabilistic models generate realistic astrophysical fields?](https://mlsanity.com/paper/2211.12444/) (2022)
- [Multiscale Flow for Robust and Optimal Cosmological Analysis](https://mlsanity.com/paper/2306.04689/) (2023)
- [AstroPT: Scaling Large Observation Models for Astronomy](https://mlsanity.com/paper/2405.14930/) (2024)
- [The Platonic Universe: Do Foundation Models See the Same Sky?](https://mlsanity.com/paper/2509.19453/) (2025)
- [Tackling the Problem of Distributional Shifts: Correcting Misspecified, High-Dimensional Data-Driven Priors for Inverse Problems](https://mlsanity.com/paper/2407.17667/) (2024)
- [Denoising Diffusion Probabilistic Models to Predict the Density of Molecular Clouds](https://mlsanity.com/paper/2304.01670/) (2023)
- [Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models](https://mlsanity.com/paper/2411.18440/) (2024)
- [Bayesian Imaging for Radio Interferometry with Score-Based Priors](https://mlsanity.com/paper/2311.18012/) (2023)
- [Predicting the Radiation Field of Molecular Clouds using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2309.05811/) (2023)
- [Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-Based Likelihoods and Priors](https://mlsanity.com/paper/2311.18002/) (2023)
- [Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models](https://mlsanity.com/paper/2408.02693/) (2024)
- [Nested Diffusion Models Using Hierarchical Latent Priors](https://mlsanity.com/paper/2412.05984/) (2024)
- [Learning to Kindle the Starlight](https://mlsanity.com/paper/2211.09206/) (2022)
- [Category-based Galaxy Image Generation via Diffusion Models](https://mlsanity.com/paper/2506.16255/) (2025)
- [Deep Learning Segmentation of Spiral Arms and Bars](https://mlsanity.com/paper/2312.02908/) (2023)
- [ρ-Diffusion: A diffusion-based density estimation framework for computational physics](https://mlsanity.com/paper/2312.08153/) (2023)
- [Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep Learning](https://mlsanity.com/paper/2501.15149/) (2025)
- [Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation](https://mlsanity.com/paper/2506.16233/) (2025)
- [Neural Posterior Estimation for Cataloging Astronomical Images from the Legacy Survey of Space and Time](https://mlsanity.com/paper/2510.15315/) (2025)
- [Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling](https://mlsanity.com/paper/2605.17546/) (2026)
- [High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology](https://mlsanity.com/paper/2606.24817/) (2026)

## Abstract (arXiv)

We show that a Denoising Diffusion Probabalistic Model (DDPM), a class of score-based generative model, can be used to produce realistic mock images that mimic observations of galaxies. Our method is tested with Dark Energy Spectroscopic Instrument (DESI) grz imaging of galaxies from the Photometry and Rotation curve OBservations from Extragalactic Surveys (PROBES) sample and galaxies selected from the Sloan Digital Sky Survey. Subjectively, the generated galaxies are highly realistic when compared with samples from the real dataset. We quantify the similarity by borrowing from the deep generative learning literature, using the `Fr'echet Inception Distance' to test for subjective and morphological similarity. We also introduce the `Synthetic Galaxy Distance' metric to compare the emergent physical properties (such as total magnitude, colour and half light radius) of a ground truth parent and synthesised child dataset. We argue that the DDPM approach produces sharper and more realistic images than other generative methods such as Adversarial Networks (with the downside of more costly inference), and could be used to produce large samples of synthetic observations tailored to a specific imaging survey. We demonstrate two potential uses of the DDPM: (1) accurate in-painting of occluded data, such as satellite trails, and (2) domain transfer, where new input images can be processed to mimic the properties of the DDPM training set. Here we `DESI-fy' cartoon images as a proof of concept for domain transfer. Finally, we suggest potential applications for score-based approaches that could motivate further research on this topic within the astronomical community.