DeepAI
Log In Sign Up

Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models

10/21/2022
by   Vikram Voleti, et al.
0

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 to help verify empirically that this more general modelling approach can also yield high-quality samples.

READ FULL TEXT

page 1

page 13

06/14/2021

Non Gaussian Denoising Diffusion Models

Generative diffusion processes are an emerging and effective tool for im...
06/11/2021

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior

Denoising diffusion probabilistic models have been recently proposed to ...
12/17/2021

Heavy-tailed denoising score matching

Score-based model research in the last few years has produced state of t...
06/17/2022

Lossy Compression with Gaussian Diffusion

We describe a novel lossy compression approach called DiffC which is bas...
10/11/2022

Markup-to-Image Diffusion Models with Scheduled Sampling

Building on recent advances in image generation, we present a fully data...
05/31/2022

On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models

Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art pe...
11/30/2022

Denoising Deep Generative Models

Likelihood-based deep generative models have recently been shown to exhi...