论文标题
扩散概率模型可以产生逼真的天体物理领域吗？
Can denoising diffusion probabilistic models generate realistic astrophysical fields?
论文作者
论文摘要
基于得分的生成模型已成为生成对抗网络（GAN）的替代品，并将涉及学习和从复杂图像分布进行抽样的任务进行标准化。在这项工作中，我们研究了这些模型在两个天体物理环境中生成场的能力：来自宇宙学模拟和星际尘埃图像的暗物质质量密度场。我们使用三个不同的指标研究了采样宇宙学领域相对于真实领域的忠诚度，并确定要解决的潜在问题。我们证明了对尘埃训练的模型的概念验证应用，以降级灰尘图像。据我们所知，这是这类模型在星际介质中的第一个应用。
Score-based generative models have emerged as alternatives to generative adversarial networks (GANs) and normalizing flows for tasks involving learning and sampling from complex image distributions. In this work we investigate the ability of these models to generate fields in two astrophysical contexts: dark matter mass density fields from cosmological simulations and images of interstellar dust. We examine the fidelity of the sampled cosmological fields relative to the true fields using three different metrics, and identify potential issues to address. We demonstrate a proof-of-concept application of the model trained on dust in denoising dust images. To our knowledge, this is the first application of this class of models to the interstellar medium.
