Denoising Diffusion Gamma Models

Abstract

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underlying noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom could improve the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we introduce the Denoising Diffusion Gamma Model (DDGM) and show that noise from Gamma distribution provides improved results for image and speech generation. Our approach preserves the ability to efficiently sample state in the training diffusion process while using Gamma noise.

arXiv admin note: substantial text overlap with arXiv:2106.07582

References in corpus (8)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Diffusion Models Beat GANs on Image Synthesis
• High Fidelity Speech Synthesis with Adversarial Networks
• On Fast Sampling of Diffusion Probabilistic Models
• Learning to Efficiently Sample from Diffusion Probabilistic Models
• A Variational Perspective on Diffusion-Based Generative Models and Score Matching
• Learning Energy-Based Models by Diffusion Recovery Likelihood
• Bilateral Denoising Diffusion Models