pith. sign in

arxiv: 2106.07582 · v1 · pith:IF7DZXZLnew · submitted 2021-06-14 · 💻 cs.LG · cs.CV· cs.SD· eess.AS

Non Gaussian Denoising Diffusion Models

classification 💻 cs.LG cs.CVcs.SDeess.AS
keywords diffusionnoiseprocessdistributiongaussiangammagenerationgenerative
0
0 comments X
read the original abstract

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom, could help the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we show that noise from Gamma distribution provides improved results for image and speech generation. Moreover, we show that using a mixture of Gaussian noise variables in the diffusion process improves the performance over a diffusion process that is based on a single distribution. Our approach preserves the ability to efficiently sample state in the training diffusion process while using Gamma noise and a mixture of noise.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes

    cs.GR 2026-05 unverdicted novelty 7.0

    Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.

  2. Progressive Distillation for Fast Sampling of Diffusion Models

    cs.LG 2022-02 unverdicted novelty 7.0

    Progressive distillation halves sampling steps repeatedly in diffusion models, reaching 4 steps with FID 3.0 on CIFAR-10 from 8192-step samplers.

  3. Improved DDIM Sampling with Moment Matching Gaussian Mixtures

    cs.CV 2023-11 unverdicted novelty 6.0

    Moment-matched GMM kernels in DDIM yield lower FID and higher IS than Gaussian kernels at small sampling steps on CelebA-HQ, FFHQ, ImageNet, and Stable Diffusion tasks.