Accelerating Black Hole Image Generation via Latent Space Diffusion Models

TL;DR

This paper introduces a physics-conditioned diffusion model operating in a latent space to generate accurate black hole images efficiently, reducing computational costs and enabling real-time modeling for black hole observations.

Contribution

The authors develop a novel latent space diffusion approach conditioned on physical parameters, significantly improving speed and fidelity over traditional radiative transfer methods.

Findings

Over fourfold reduction in inference time per image

High fidelity reproduction of key observational features

Improved parameter estimation accuracy

Abstract

Interpreting horizon-scale black hole images currently relies on computationally intensive General Relativistic Ray Tracing (GRRT) simulations, which pose a significant bottleneck for rapid parameter exploration and high-precision tests of strong-field gravity. We demonstrate that physically accurate black hole images, synthesized from magnetized accretion flows, inherently reside on a low-dimensional manifold-encoding the essential features of spacetime geometry, plasma distribution, and relativistic emission. Leveraging this structure, we introduce a physics-conditioned diffusion model that operates in a compact latent space to generate high-fidelity black hole imagery directly from physical parameters. The model accurately reproduces critical observational signatures from full GRRT simulations-such as shadow diameter, photon-ring structure, and relativistic brightness asymmetry-while achieving over a fourfold reduction in computational expense. Compared with the previous generation of denoising diffusion models, the proposed approach achieves significant improvements in image quality, reconstruction fidelity, and parameter estimation accuracy, while reducing the average inference time per black hole image from 5.25 seconds to 1.15 seconds. Our work establishes diffusion-based latent models as efficient and scalable substitutes for traditional radiative transfer solvers, offering a practical framework toward real-time modeling and inference for next-generation black hole imaging.