Non Gaussian Denoising Diffusion Models

2021/06/14 by Eliya Nachmani, Nachmani, Eliya, Robin San-Roman +3 · 4 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2106.07582

openalex publication_date 2021/06/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Generative Adversarial Networks
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• Generative Modeling by Estimating Gradients of the Data Distribution
• High Fidelity Speech Synthesis with Adversarial Networks
• Denoising Diffusion Probabilistic Models
• WaveGrad: Estimating Gradients for Waveform Generation
• Denoising Diffusion Implicit Models
• Score-Based Generative Modeling through Stochastic Differential Equations

Cited by

• Improved probabilistic regression using diffusion models
• Hierarchical Diffusion Motion Planning with Task-Conditioned Uncertainty-Aware Priors
• Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes
• Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Art

Related

• Denoising Diffusion Gamma Models
• Noise Estimation for Generative Diffusion Models
• Diffusion Model for Generative Image Denoising
• Diffusion models with location-scale noise
• Conditional Diffusion Probabilistic Model for Speech Enhancement