Denoising Diffusion Gamma Models
This work addresses a specific bottleneck in generative modeling for image and speech synthesis, but it is incremental as it modifies an existing paradigm with a different noise distribution.
The authors tackled the problem of limited noise distribution flexibility in generative diffusion models by introducing the Denoising Diffusion Gamma Model (DDGM), which uses Gamma noise instead of Gaussian noise and shows improved results for image and speech generation.
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.