mlsanityData to 7 Oct 2026

Subspace Diffusion Generative Models

arXiv 2205.01490 ↗First posted 3 May 2022cs.LG cs.CVcited by 70

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all the inconveniences thereof. Instead, we restrict the diffusion via projections onto subspaces as the data distribution evolves toward noise. When applied to state-of-the-art models, our framework simultaneously improves sample quality -- reaching an FID of 2.17 on unconditional CIFAR-10 -- and reduces the computational cost of inference for the same number of denoising steps. Our framework is fully compatible with continuous-time diffusion and retains its flexible capabilities, including exact log-likelihoods and controllable generation. Code is available at https://github.com/bjing2016/subspace-diffusion.

Key facts. Cited by 70 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 22 references that are in the map. First posted on arXiv 3 May 2022.

Builds on

20 of 22 references.

Closest ancestors · 14

Same direction, newest first

  1. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  2. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  3. 2021Variational Diffusion Models1 Jul
  4. 2021Score-based Generative Modeling in Latent Space10 Jun
  5. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
  6. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  7. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  8. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Noise Estimation for Generative Diffusion Models6 Apr
  11. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
2 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 6

  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  4. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  5. 2018Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscalingcited by 74
  6. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesiscited by 64

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 19; 2023: 26; 2024: 12; 2025: 9; 2026: 4.

70 papers.

Sort:

By area:

  1. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2022Diffusion Models in Vision: A Surveycited by 1,008
  4. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  5. 2023Structural Pruning for Diffusion Modelscited by 193
  6. 2022Convergence of score-based generative modeling for general data distributionscited by 179
  7. 2022Convergence for score-based generative modeling with polynomial complexitycited by 176
  8. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  9. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  10. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrappingcited by 96
  11. 2022Blurring Diffusion Modelscited by 89
  12. 2023Reflected Diffusion Modelscited by 81
38 more
  1. 2023Score-based Diffusion Models in Function Spacecited by 80
  2. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  3. 2022Wavelet Score-Based Generative Modelingcited by 61
  4. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  5. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 56
  6. 2022Efficient Diffusion Models for Vision: A Surveycited by 50
  7. 2023OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Modelscited by 44
  8. 2023Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transportcited by 39
  9. 2022Few-Shot Diffusion Modelscited by 37
  10. 2022Fast Graph Generation via Spectral Diffusioncited by 36
  11. 2022Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesiscited by 34
  12. 2023Trans-Dimensional Generative Modeling via Jump Diffusion Modelscited by 33
  13. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformationcited by 32
  14. 2024Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priorscited by 28
  15. 2022Spectral Diffusion Processescited by 24
  16. 2022Pyramidal Denoising Diffusion Probabilistic Modelscited by 22
  17. 2024Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transportcited by 22
  18. 2023∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified Statescited by 21
  19. 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modelingcited by 18
  20. 2023A Complete Recipe for Diffusion Generative Modelscited by 17
  21. 2023Dehazing Ultrasound using Diffusion Modelscited by 17
  22. 2023Renormalizing Diffusion Modelscited by 16
  23. 2022Improving Diffusion Model Efficiency Through Patchingcited by 15
  24. 2023Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flowscited by 15
  25. 2025Lipschitz-Guided Design of Interpolation Schedules in Generative Modelscited by 15
  26. 2023Removing Structured Noise with Diffusion Modelscited by 14
  27. 2024Reflected Flow Matchingcited by 13
  28. 2022Dimensionality-Varying Diffusion Processcited by 12
  29. 2023Generative Fractional Diffusion Modelscited by 12
  30. 2025FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Computecited by 12
  31. 2022Accelerating Score-based Generative Models for High-Resolution Image Synthesiscited by 10
  32. 2023Geometric Neural Diffusion Processescited by 10
  33. 2023Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecturescited by 9
  34. 2023Image generation with shortest path diffusioncited by 8
  35. 2023Analyzing and Improving Optimal-Transport-based Adversarial Networkscited by 8
  36. 2023Diffusion Models with Deterministic Normalizing Flow Priorscited by 7
  37. 2023Preconditioned Score-based Generative Modelscited by 6
  38. 2023Restoration based Generative Modelscited by 6

50 most cited of 70 All 70 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022How Much is Enough? A Study on Diffusion Times in Score-based Generative Models
  2. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
  3. 2025Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
  4. 2024Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
  5. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
  6. 2024Evaluating the design space of diffusion-based generative models
  7. 2026Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
  8. 2025From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting