mlsanityData to 7 Oct 2026

Non-Uniform Diffusion Models

arXiv 2207.09786 ↗First posted 20 Jul 2022cs.LGcited by 14

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows. We experimentally find that in the same or less training time, the multi-scale diffusion model achieves better FID score than the standard uniform diffusion model. More importantly, it generates samples 4.4 times faster in 128× 128 resolution. The speed-up is expected to be higher in higher resolutions where more scales are used. Moreover, we show that non-uniform diffusion leads to a novel estimator for the conditional score function which achieves on par performance with the state-of-the-art conditional denoising estimator. Our theoretical and experimental findings are accompanied by an open source library MSDiff which can facilitate further research of non-uniform diffusion models.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 16 of its 29 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

16 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 12

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  9. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  10. 2015Holistically-Nested Edge Detectioncited by 590
  11. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  12. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 1; 2025: 0; 2026: 1.

14 papers.

Sort:

By area:

  1. 2022Diffusion Models in Vision: A Surveycited by 1,008
  2. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  3. 2022A Survey on Generative Diffusion Modelcited by 238
  4. 2023Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Modelscited by 61
  5. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  6. 2022Efficient Diffusion Models for Vision: A Surveycited by 50
  7. 2023Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generationcited by 37
  8. 2023Continuous Diffusion for Mixed-Type Tabular Datacited by 16
  9. 2023Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusioncited by 6
  10. 2022CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesiscited by 4
  11. 2024Hierarchic Flows to Estimate and Sample High-dimensional Probabilitiescited by 3
  12. 2023Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Modelscited by 2
2 more
  1. 2023How Good Are Deep Generative Models for Solving Inverse Problems?cited by 1
  2. 2026The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
  2. 2024Non-Normal Diffusion Models
  3. 2022Understanding Diffusion Models: A Unified Perspective
  4. 2025Diffusion Models: A Mathematical Introduction
  5. 2023Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
  6. 2026A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
  7. 2021Conditional Image Generation with Score-Based Diffusion Models
  8. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps