mlsanityData to 14 Oct 2026

On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models

arXiv 2206.00070 ↗First posted 31 May 2022cs.LGcited by 31

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art performance in generative modeling. Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward diffusion process, which gradually adds noise to the input signal. Although DDGMs are well studied, it is still unclear how the small amount of noise is transformed during the backward diffusion process. Here, we focus on analyzing this problem to gain more insight into the behavior of DDGMs and their denoising and generative capabilities. We observe a fluid transition point that changes the functionality of the backward diffusion process from generating a (corrupted) image from noise to denoising the corrupted image to the final sample. Based on this observation, we postulate to divide a DDGM into two parts: a denoiser and a generator. The denoiser could be parameterized by a denoising auto-encoder, while the generator is a diffusion-based model with its own set of parameters. We experimentally validate our proposition, showing its pros and cons.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

20 of 35 references.

References · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  12. 2021Variational Diffusion Modelscited by 1,153
8 more
  1. 2021Score-based Generative Modeling in Latent Spacecited by 636
  2. 2018Assessing Generative Models via Precision and Recallcited by 406
  3. 2021Generating Images with Sparse Representationscited by 266
  4. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 183
  5. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 176
  6. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  7. 2021Diffusion Priors In Variational Autoencoderscited by 25
  8. 2022Dynamic Dual-Output Diffusion Modelscited by 25

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 13; 2024: 7; 2025: 10.

31 papers.

Sort:

By area:

  1. 2022Diffusion Models in Vision: A Surveycited by 1,015
  2. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 340
  3. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Accelerationcited by 70
  4. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  5. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 35
  6. 2024Denoising Task Difficulty-based Curriculum for Training Diffusion Modelscited by 27
  7. 2023DiffDance: Cascaded Human Motion Diffusion Model for Dance Generationcited by 23
  8. 2023Continual Learning of Diffusion Models with Generative Distillationcited by 20
  9. 2024Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysiscited by 19
  10. 2023Clockwork Diffusion: Efficient Generation With Model-Step Distillationcited by 18
  11. 2023Exploring Continual Learning of Diffusion Modelscited by 15
  12. 2025T-LoRA: Single Image Diffusion Model Customization Without Overfittingcited by 15
19 more
  1. 2025On Denoising Walking Videos for Gait Recognitioncited by 14
  2. 2023Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuningcited by 11
  3. 2023A Lipschitz Bandits Approach for Continuous Hyperparameter Optimizationcited by 9
  4. 2023Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecturescited by 9
  5. 2025ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Modelscited by 8
  6. 2024GeoGuide: Geometric guidance of diffusion modelscited by 7
  7. 2023DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Modelcited by 6
  8. 2024Particle-Filtering-based Latent Diffusion for Inverse Problemscited by 5
  9. 2025Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Modelscited by 5
  10. 2024Diffusion Model Compression for Image-to-Image Translationcited by 4
  11. 2025DeepShade: Enable Shade Simulation by Text-conditioned Image Generationcited by 4
  12. 2024EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Modelscited by 3
  13. 2023Fine-grained Forecasting Models Via Gaussian Process Blurring Effectcited by 2
  14. 2025Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generationcited by 2
  15. 2024Flexiffusion: Segment-wise Neural Architecture Search for Flexible Denoising Schedulecited by 1
  16. 2025Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Modelscited by 1
  17. 2025Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Samplingcited by 0
  18. 2025Diffusion Denoiser-Aided Gyrocompassingcited by 0
  19. 2025Structured Noise Modeling for Enhanced Time-Series Forecastingcited by 0