mlsanityData to 7 Oct 2026

Diffusion Models in Vision: A Survey

arXiv 2209.04747 ↗First posted 10 Sep 2022cs.CV cs.AI cs.LGcited by 1,008

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. In the forward diffusion stage, the input data is gradually perturbed over several steps by adding Gaussian noise. In the reverse stage, a model is tasked at recovering the original input data by learning to gradually reverse the diffusion process, step by step. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens, i.e. low speeds due to the high number of steps involved during sampling. In this survey, we provide a comprehensive review of articles on denoising diffusion models applied in vision, comprising both theoretical and practical contributions in the field. First, we identify and present three generic diffusion modeling frameworks, which are based on denoising diffusion probabilistic models, noise conditioned score networks, and stochastic differential equations. We further discuss the relations between diffusion models and other deep generative models, including variational auto-encoders, generative adversarial networks, energy-based models, autoregressive models and normalizing flows. Then, we introduce a multi-perspective categorization of diffusion models applied in computer vision. Finally, we illustrate the current limitations of diffusion models and envision some interesting directions for future research.

Key facts. Cited by 1,008 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 142 of its 170 references that are in the map. First posted on arXiv 10 Sep 2022.

Builds on

142 of 170 references.

Closest ancestors · 56

Same direction, newest first

  1. 2022Classifier-Free Diffusion Guidance26 Jul
  2. 2022Non-Uniform Diffusion Models20 Jul
  3. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations14 Jul
  4. 2022Diffusion models as plug-and-play priors17 Jun
  5. 2022Accelerating Score-based Generative Models for High-Resolution Image Synthesis8 Jun
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  7. 2022DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder1 Jun
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  9. 2022Few-Shot Diffusion Models30 May
  10. 2022A Continuous Time Framework for Discrete Denoising Models30 May
  11. 2022Maximum Likelihood Training of Implicit Nonlinear Diffusion Models27 May
  12. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Process25 May
38 more
  1. 2022Subspace Diffusion Generative Models3 May
  2. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  3. 2022Perception Prioritized Training of Diffusion Models1 Apr
  4. 2022Generating High Fidelity Data from Low-density Regions using Diffusion Models31 Mar
  5. 2022Diffusion Models for Counterfactual Explanations29 Mar
  6. 2022Dynamic Dual-Output Diffusion Models8 Mar
  7. 2022Conditional Simulation Using Diffusion Schr"odinger Bridges27 Feb
  8. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  9. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders19 Feb
  10. 2022Understanding DDPM Latent Codes Through Optimal Transport14 Feb
  11. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality11 Feb
  12. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  13. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  14. 2021Heavy-tailed denoising score matching17 Dec
  15. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  16. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  17. 2021Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation3 Dec
  18. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation30 Nov
  19. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesis29 Nov
  20. 2021Conditional Image Generation with Score-Based Diffusion Models26 Nov
  21. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes24 Nov
  22. 2021Diffusion Normalizing Flow14 Oct
  23. 2021Score-Based Generative Classifiers1 Oct
  24. 2021Bilateral Denoising Diffusion Models26 Aug
  25. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  26. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  27. 2021Variational Diffusion Models1 Jul
  28. 2021Non Gaussian Denoising Diffusion Models14 Jun
  29. 2021Score-based Generative Modeling in Latent Space10 Jun
  30. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
  31. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  32. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  33. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  34. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  35. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  36. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  37. 2021UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models12 Apr
  38. 2021Noise Estimation for Generative Diffusion Models6 Apr

50 newest of 56 All 56 (JSON)

Other references · 86

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  10. 2022Generative Adversarial Networkscited by 5,603
  11. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  12. 2017Neural Discrete Representation Learningcited by 4,650
38 more
  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  3. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  6. 2022Video Diffusion Modelscited by 2,280
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  10. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  11. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  12. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  13. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  14. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  15. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  16. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  17. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  18. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  19. 2022Denoising Diffusion Restoration Modelscited by 951
  20. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  21. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  22. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  23. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  24. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  25. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  26. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  27. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  28. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  29. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  30. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  31. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  32. 2022Diffusion Models for Adversarial Purificationcited by 469
  33. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  34. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  35. 2022Blended Latent Diffusioncited by 430
  36. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  37. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  38. 2021Score-based diffusion models for accelerated MRIcited by 308

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 24; 2023: 204; 2024: 324; 2025: 292; 2026: 164.

1,008 papers.

Sort:

By area:

  1. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  2. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 641
  3. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  4. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  5. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  6. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionscited by 440
  7. 2023TokenFlow: Consistent Diffusion Features for Consistent Video Editingcited by 440
  8. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 358
  9. 2023Pix2Video: Video Editing using Image Diffusioncited by 318
  10. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 269
  11. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  12. 2022Post-training Quantization on Diffusion Modelscited by 262
38 more
  1. 2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generationcited by 258
  2. 2023Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translationcited by 253
  3. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  4. 2022SpaText: Spatio-Textual Representation for Controllable Image Generationcited by 217
  5. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  6. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Nowcited by 204
  7. 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelscited by 164
  8. 2023A Reparameterized Discrete Diffusion Model for Text Generationcited by 152
  9. 2023Rich Human Feedback for Text-to-Image Generationcited by 139
  10. 2024Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editingcited by 134
  11. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  12. 2023Large Language Models in Law: A Surveycited by 128
  13. 2023Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfercited by 124
  14. 2024GameGen-X: Interactive Open-world Game Video Generationcited by 124
  15. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  16. 2023VidToMe: Video Token Merging for Zero-Shot Video Editingcited by 111
  17. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  18. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  19. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  20. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 103
  21. 2022Soft Diffusion: Score Matching for General Corruptionscited by 101
  22. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
  23. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 91
  24. 2023Input Perturbation Reduces Exposure Bias in Diffusion Modelscited by 88
  25. 2023TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targetscited by 88
  26. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88
  27. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 86
  28. 2024Video as the New Language for Real-World Decision Makingcited by 86
  29. 2024MAISI: Medical AI for Synthetic Imagingcited by 86
  30. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  31. 2023Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Modelscited by 84
  32. 2023LLM-grounded Video Diffusion Modelscited by 83
  33. 2023Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Modelscited by 82
  34. 2024Controllable Generation with Text-to-Image Diffusion Models: A Surveycited by 82
  35. 2024Diffusion Actor-Critic with Entropy Regulatorcited by 81
  36. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 81
  37. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
  38. 2022Diffusion models for missing value imputation in tabular datacited by 77

50 most cited of 1,008 All 1,008 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications
  3. 2025Diffusion Models: A Mathematical Introduction
  4. 2022Image Embedding for Denoising Generative Models
  5. 2024A Comprehensive Survey on Diffusion Models and Their Applications
  6. 2023Diffusion Model for Generative Image Denoising
  7. 2023Denoising Diffusion Bridge Models
  8. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise