Category-based Galaxy Image Generation via Diffusion Models

TL;DR

This paper introduces GalCatDiff, a diffusion model-based framework that generates realistic galaxy images by incorporating astrophysical features and category embeddings, improving diversity and physical consistency.

Contribution

GalCatDiff is the first to integrate galaxy features and astrophysical properties into diffusion models for category-specific galaxy image generation.

Findings

GalCatDiff outperforms existing methods in sample color and size distribution consistency.

Generated galaxies are visually realistic and physically consistent.

The framework enhances galaxy simulation reliability and aids in data augmentation.

Abstract

Conventional galaxy generation methods rely on semi-analytical models and hydrodynamic simulations, which are highly dependent on physical assumptions and parameter tuning. In contrast, data-driven generative models do not have explicit physical parameters pre-determined, and instead learn them efficiently from observational data, making them alternative solutions to galaxy generation. Among these, diffusion models outperform Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) in quality and diversity. Leveraging physical prior knowledge to these models can further enhance their capabilities. In this work, we present GalCatDiff, the first framework in astronomy to leverage both galaxy image features and astrophysical properties in the network design of diffusion models. GalCatDiff incorporates an enhanced U-Net and a novel block entitled Astro-RAB (Residual Attention Block), which dynamically combines attention mechanisms with convolution operations to ensure global consistency and local feature fidelity. Moreover, GalCatDiff uses category embeddings for class-specific galaxy generation, avoiding the high computational costs of training separate models for each category. Our experimental results demonstrate that GalCatDiff significantly outperforms existing methods in terms of the consistency of sample color and size distributions, and the generated galaxies are both visually realistic and physically consistent. This framework will enhance the reliability of galaxy simulations and can potentially serve as a data augmentor to support future galaxy classification algorithm development.