Diffusion Models for Probabilistic Deconvolution of Galaxy Images
Diffusion Models for Probabilistic Deconvolution of Galaxy Images
复制标题
DOI：
10.48550/arxiv.2307.11122
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Zhiwei Xue;Yuhang Li;Yash J. Patel;J. Regier
中科院分区：
文献类型：
--
作者：
Zhiwei Xue;Yuhang Li;Yash J. Patel;J. Regier
望远镜用特定的点扩散函数（PSF）捕捉图像。推断图像在更清晰的PSF下看起来会是什么样子，这是一个称为PSF反卷积的问题，是不适定的，因为PSF卷积不是可逆变换。深度生成模型对PSF反卷积很有吸引力，因为它们可以推断候选图像的后验分布，如果与PSF卷积，则可以生成观察结果。然而，经典的深度生成模型（如VAE和GAN）通常提供的样本多样性不足。作为一种替代方案，我们提出了一个无分类器的条件扩散模型的PSF反卷积的星系图像。我们证明，这种扩散模型捕获更大的多样性可能的去卷积相比，条件VAE。
Telescopes capture images with a particular point spread function (PSF). Inferring what an image would have looked like with a much sharper PSF, a problem known as PSF deconvolution, is ill-posed because PSF convolution is not an invertible transformation. Deep generative models are appealing for PSF deconvolution because they can infer a posterior distribution over candidate images that, if convolved with the PSF, could have generated the observation. However, classical deep generative models such as VAEs and GANs often provide inadequate sample diversity. As an alternative, we propose a classifier-free conditional diffusion model for PSF deconvolution of galaxy images. We demonstrate that this diffusion model captures a greater diversity of possible deconvolutions compared to a conditional VAE.