mlsanityData to 7 Oct 2026

Non Gaussian Denoising Diffusion Models

arXiv 2106.07582 ↗First posted 14 Jun 2021cs.LG cs.CV cs.SDcited by 43

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

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.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 20 of its 29 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

20 of 29 references.

Closest ancestors · 3

Same direction, newest first

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  2. 2020Denoising Diffusion Implicit Models6 Oct
  3. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 17

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  10. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  11. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  12. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
5 more
  1. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  2. 2018Adversarial Audio Synthesiscited by 222
  3. 2018Efficient Neural Audio Synthesiscited by 218
  4. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  5. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 18; 2024: 5; 2025: 3; 2026: 5.

43 papers.

Sort:

By area:

  1. 2022Diffusion Models in Vision: A Surveycited by 1,008
  2. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  3. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  4. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  5. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 181
  6. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  7. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  8. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  9. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  10. 2022Progressive Distillation for Fast Sampling of Diffusion Modelscited by 61
  11. 2022Wavelet Score-Based Generative Modelingcited by 61
  12. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
31 more
  1. 2022Efficient Diffusion Models for Vision: A Surveycited by 50
  2. 2022Maximum Likelihood Training of Implicit Nonlinear Diffusion Modelscited by 42
  3. 2023Sampling, Diffusions, and Stochastic Localizationcited by 38
  4. 2024Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspectivecited by 24
  5. 2022Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generationcited by 20
  6. 2023Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Timecited by 20
  7. 2023Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstructioncited by 18
  8. 2021Heavy-tailed denoising score matchingcited by 17
  9. 2023A Complete Recipe for Diffusion Generative Modelscited by 17
  10. 2023Gaussian Mixture Solvers for Diffusion Modelscited by 17
  11. 2023DPoser: Diffusion Model as Robust 3D Human Pose Priorcited by 17
  12. 2025Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Artcited by 13
  13. 2023Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Modelscited by 12
  14. 2024Structured Diffusion Models with Mixture of Gaussians as Prior Distributioncited by 8
  15. 2023SDDPM: Speckle Denoising Diffusion Probabilistic Modelscited by 6
  16. 2023Improved DDIM Sampling with Moment Matching Gaussian Mixturescited by 3
  17. 2023Fully Spiking Denoising Diffusion Implicit Modelscited by 2
  18. 2025Improved probabilistic regression using diffusion modelscited by 2
  19. 2023Understanding and contextualising diffusion modelscited by 1
  20. 2023GlyphDiffusion: Text Generation as Image Generationcited by 1
  21. 2023An Efficient 1 Iteration Learning Algorithm for Gaussian Mixture Model And Gaussian Mixture Embedding For Neural Networkcited by 1
  22. 2024Diffusion Model Conditioning on Gaussian Mixture Model and Negative Gaussian Mixture Gradientcited by 1
  23. 2024Directly Denoising Diffusion Modelscited by 1
  24. 2023Diffusion-C: Unveiling the Generative Challenges of Diffusion Models through Corrupted Datacited by 0
  25. 2024Hardware-Friendly Diffusion Models with Fixed-Size Reusable Structures for On-Device Image Generationcited by 0
  26. 2025Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Modelscited by 0
  27. 2026HyperNet-Adaptation for Diffusion-Based Test Case Generationcited by 0
  28. 2026Selective Denoising Diffusion Model for Time Series Anomaly Detectioncited by 0
  29. 2026Mat'ern Noise for Triangulation-Agnostic Flow Matching on Meshescited by 0
  30. 2026Noise in Diffusion Models Is a Learnable Inputcited by 0
  31. 2026Spatially-Grounded Flow Matching: Structured Source Distributions for Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Denoising Diffusion Gamma Models
  2. 2021Noise Estimation for Generative Diffusion Models
  3. 2023Diffusion Model for Generative Image Denoising
  4. 2022Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
  5. 2023Diffusion models with location-scale noise
  6. 2024GUD: Generation with Unified Diffusion
  7. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Models
  8. 2024Blue noise for diffusion models