论文标题
基于得分的非偶性高斯噪声模型的deno降解扩散
Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
论文作者
论文摘要
基于转化扩散技术的生成模型导致图像的质量和多样性始终提高，现在可以通过神经生成模型来创建。但是，大多数当代的最先进方法均来自标准的各向同性高斯公式。在这项工作中，我们研究了使用非异向高斯分布的情况。我们介绍了使用潜在的非异型高斯噪声模型创建非授予扩散模型的关键数学推导。我们还使用CIFAR-10数据集提供初始实验，以帮助经验验证这种更通用的建模方法也可以产生高质量的样本。
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural generative models. However, most contemporary state-of-the-art methods are derived from a standard isotropic Gaussian formulation. In this work we examine the situation where non-isotropic Gaussian distributions are used. We present the key mathematical derivations for creating denoising diffusion models using an underlying non-isotropic Gaussian noise model. We also provide initial experiments with the CIFAR-10 dataset to help verify empirically that this more general modeling approach can also yield high-quality samples.
