mlsanityData to 13 Oct 2026

Bilateral Denoising Diffusion Models

arXiv 2108.11514 ↗First posted 26 Aug 2021cs.LG cs.AI cs.SDcited by 36

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Denoising diffusion probabilistic models (DDPMs) have emerged as competitive generative models yet brought challenges to efficient sampling. In this paper, we propose novel bilateral denoising diffusion models (BDDMs), which take significantly fewer steps to generate high-quality samples. From a bilateral modeling objective, BDDMs parameterize the forward and reverse processes with a score network and a scheduling network, respectively. We show that a new lower bound tighter than the standard evidence lower bound can be derived as a surrogate objective for training the two networks. In particular, BDDMs are efficient, simple-to-train, and capable of further improving any pre-trained DDPM by optimizing the inference noise schedules. Our experiments demonstrated that BDDMs can generate high-fidelity samples with as few as 3 sampling steps and produce comparable or even higher quality samples than DDPMs using 1000 steps with only 16 sampling steps (a 62x speedup).

Key facts. Cited by 36 papers in the map (data through 13 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 31 of its 46 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

31 of 46 references.

Closest ancestors · 9

Same direction, newest first

  1. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  2. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  3. 2021Noise Estimation for Generative Diffusion Models6 Apr
  4. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  5. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Implicit Models6 Oct
  8. 2020Denoising Diffusion Probabilistic Models19 Jun
  9. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,077
  4. 2018Neural Ordinary Differential Equationscited by 3,750
  5. 2016Density estimation using Real NVPcited by 2,033
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,717
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,542
  8. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,381
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,348
  10. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,317
  11. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 621
  12. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 588
10 more
  1. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 353
  2. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 339
  3. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 260
  4. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  5. 2019Large Scale Adversarial Representation Learningcited by 239
  6. 2018Efficient Neural Audio Synthesiscited by 219
  7. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
  8. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 91
  9. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  10. 2021Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networkscited by 8

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 17; 2023: 12; 2024: 3; 2025: 1.

36 papers.

Sort:

By area:

  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,974
  2. 2022Diffusion Models in Vision: A Surveycited by 1,012
  3. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 931
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 697
  5. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 596
  6. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 448
  7. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 343
  8. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 333
  9. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 174
  10. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Cachingcited by 150
  11. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 148
  12. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
24 more
  1. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  2. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  3. 2022Progressive Distillation for Fast Sampling of Diffusion Modelscited by 67
  4. 2022Efficient Diffusion Models for Vision: A Surveycited by 51
  5. 2022BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesiscited by 44
  6. 2023Bespoke Solvers for Generative Flow Modelscited by 37
  7. 2022TranSpeech: Speech-to-Speech Translation With Bilateral Perturbationcited by 34
  8. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidancecited by 33
  9. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Trainingcited by 28
  10. 2021Denoising Diffusion Gamma Modelscited by 27
  11. 2023ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformercited by 24
  12. 2022GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speechcited by 21
  13. 2022ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speechcited by 21
  14. 2023DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transportcited by 14
  15. 2022VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglementcited by 11
  16. 2023Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysiscited by 8
  17. 2023AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translationcited by 6
  18. 2023Wav2SQL: Direct Generalizable Speech-To-SQL Parsingcited by 4
  19. 2024SonicVisionLM: Playing Sound with Vision Language Modelscited by 3
  20. 2025DreamAudio: Customized Text-to-Audio Generation with Diffusion Modelscited by 2
  21. 2021TFDPM: Attack detection for cyber-physical systems with diffusion probabilistic modelscited by 1
  22. 2023Understanding and contextualising diffusion modelscited by 1
  23. 2024Directly Denoising Diffusion Modelscited by 1
  24. 2022R-MelNet: Reduced Mel-Spectral Modeling for Neural TTScited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
  2. 2026Blind denoising diffusion models and the blessings of dimensionality
  3. 2023The Missing U for Efficient Diffusion Models
  4. 2024Denoising Diffusion Probabilistic Models in Six Simple Steps
  5. 2025Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds
  6. 2023Fast Inference in Denoising Diffusion Models via MMD Finetuning
  7. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models
  8. 2023ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories