mlsanityData to 7 Oct 2026

Noise Estimation for Generative Diffusion Models

arXiv 2104.02600 ↗First posted 6 Apr 2021cs.LG cs.CVcited by 94

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning of the set of noise parameters is needed. In this work, we present a simple and versatile learning scheme that can step-by-step adjust those noise parameters, for any given number of steps, while the previous work needs to retune for each number separately. Furthermore, without modifying the weights of the diffusion model, we are able to significantly improve the synthesis results, for a small number of steps. Our approach comes at a negligible computation cost.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 23 of its 33 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

23 of 33 references.

Closest ancestors · 4

Same direction, newest first

  1. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  3. 2020Denoising Diffusion Implicit Models6 Oct
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  9. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  11. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  12. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
7 more
  1. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  2. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  3. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  4. 2018Adversarial Audio Synthesiscited by 222
  5. 2018Efficient Neural Audio Synthesiscited by 218
  6. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  7. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 26; 2023: 25; 2024: 18; 2025: 12.

94 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  4. 2022Diffusion Models in Vision: A Surveycited by 1,008
  5. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  6. 2021Score-based Generative Modeling in Latent Spacecited by 634
  7. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  8. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  9. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  10. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  11. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  12. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 266
38 more
  1. 2022Post-training Quantization on Diffusion Modelscited by 262
  2. 2021Deblurring via Stochastic Refinementcited by 248
  3. 2022A Survey on Generative Diffusion Modelcited by 238
  4. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  5. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  6. 2021Gotta Go Fast When Generating Data with Score-Based Modelscited by 218
  7. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  8. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  9. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  10. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 181
  11. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  12. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 147
  13. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
  14. 2022Semantic Image Synthesis via Diffusion Modelscited by 131
  15. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  16. 2024Transparent Image Layer Diffusion using Latent Transparencycited by 111
  17. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Schemecited by 99
  18. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  19. 2022Subspace Diffusion Generative Modelscited by 70
  20. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesiscited by 64
  21. 2022Progressive Distillation for Fast Sampling of Diffusion Modelscited by 61
  22. 2022Wavelet Score-Based Generative Modelingcited by 61
  23. 2023One-Step Diffusion Distillation via Deep Equilibrium Modelscited by 60
  24. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  25. 2023DreamDiffusion: Generating High-Quality Images from Brain EEG Signalscited by 56
  26. 2022Efficient Diffusion Models for Vision: A Surveycited by 50
  27. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42
  28. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  29. 2021Bilateral Denoising Diffusion Modelscited by 36
  30. 2024Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Modelscited by 35
  31. 2023Relightify: Relightable 3D Faces from a Single Image via Diffusion Modelscited by 34
  32. 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIcited by 32
  33. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Trainingcited by 28
  34. 2022Denoising Diffusion Error Correction Codescited by 23
  35. 2024MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariantcited by 21
  36. 2023Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Timecited by 20
  37. 2022Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image Segmentationcited by 18
  38. 2024Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generationcited by 18

50 most cited of 94 All 94 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2021Non Gaussian Denoising Diffusion Models
  2. 2023Single and Few-step Diffusion for Generative Speech Enhancement
  3. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Models
  4. 2025Is Noise Conditioning Necessary for Denoising Generative Models?
  5. 2021Denoising Diffusion Gamma Models
  6. 2025Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance
  7. 2023Diffusion Model for Generative Image Denoising
  8. 2025Beyond Fixed Horizons: A Theoretical Framework for Adaptive Denoising Diffusions