Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling

2026-05-17

AI Summary

This work proposes an efficient method for generating realistic galaxy images conditioned on redshift to support studies of morphological evolution in cosmology. By integrating diffusion models—including DDPM, DDIM, and DPM++2M—with the single-step generative model pixel-MeanFlow, the study presents the first systematic validation of single-step generation for redshift-conditioned image synthesis. Experimental results demonstrate that pixel-MeanFlow accurately preserves key morphological statistics such as ellipticity, semi-major axis length, and Sérsic index. Although it exhibits slightly reduced fidelity in fine structural details compared to multi-step diffusion models, it achieves computational speedups of several orders of magnitude, making it highly suitable for large-scale survey simulations.

Abstract

Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. In this work, we study efficient redshift-conditioned generative modeling for astrophysical image synthesis using diffusion models and pixel-MeanFlow. We first review the connections between score-based diffusion models, Flow Matching, one-step generative models, and modern diffusion samplers. We then evaluate DDPM, DDIM, DEIS-AB2, DPM++2M, and one-step pixel-MeanFlow on the GalaxiesML-64 dataset using morphology-based metrics, including ellipticity, semi-major axis, Sérsic index, and isophotal area. Our results show a clear accuracy-efficiency trade-off: standard DDPM sampling achieves the best distributional fidelity but requires high computational cost, while second-order samplers substantially improve efficiency over DDIM. Pixel-MeanFlow enables single-step generation and achieves competitive performance on several morphology statistics, though it remains weaker than many-step DDPM for fine-grained structure. Our results demonstrate that one-step generative models can recover key galaxy morphology statistics at orders-of-magnitude lower computational cost, opening a path toward efficient conditional simulators for large cosmological surveys and simulation-based scientific inference.

Problem

• redshift-conditioned
• galaxy image synthesis
• generative modeling
• morphology evolution
• computational efficiency

Innovation

• one-step generative modeling
• pixel-MeanFlow
• redshift-conditioned synthesis
• diffusion models
• galaxy morphology