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

arXiv: https://arxiv.org/abs/2206.00070 · HTML: https://mlsanity.com/paper/2206.00070/

## 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 (most cited first, 20 of 20)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [A Variational Perspective on Diffusion-Based Generative Models and Score Matching](https://mlsanity.com/paper/2106.02808/) (2021)
- [Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit](https://mlsanity.com/paper/1905.09883/) (2019)
- [Generalized Denoising Auto-Encoders as Generative Models](https://mlsanity.com/paper/1305.6663/) (2013)
- [Diffusion Priors In Variational Autoencoders](https://mlsanity.com/paper/2106.15671/) (2021)
- [Dynamic Dual-Output Diffusion Models](https://mlsanity.com/paper/2203.04304/) (2022)

## Built on by (most cited first, 30 of 31)

- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)
- [AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration](https://mlsanity.com/paper/2309.10438/) (2023)
- [On the Design Fundamentals of Diffusion Models: A Survey](https://mlsanity.com/paper/2306.04542/) (2023)
- [A Residual Diffusion Model for High Perceptual Quality Codec Augmentation](https://mlsanity.com/paper/2301.05489/) (2023)
- [Denoising Task Difficulty-based Curriculum for Training Diffusion Models](https://mlsanity.com/paper/2403.10348/) (2024)
- [DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation](https://mlsanity.com/paper/2308.02915/) (2023)
- [Continual Learning of Diffusion Models with Generative Distillation](https://mlsanity.com/paper/2311.14028/) (2023)
- [Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis](https://mlsanity.com/paper/2407.12173/) (2024)
- [Clockwork Diffusion: Efficient Generation With Model-Step Distillation](https://mlsanity.com/paper/2312.08128/) (2023)
- [Exploring Continual Learning of Diffusion Models](https://mlsanity.com/paper/2303.15342/) (2023)
- [T-LoRA: Single Image Diffusion Model Customization Without Overfitting](https://mlsanity.com/paper/2507.05964/) (2025)
- [On Denoising Walking Videos for Gait Recognition](https://mlsanity.com/paper/2505.18582/) (2025)
- [Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning](https://mlsanity.com/paper/2311.01018/) (2023)
- [A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization](https://mlsanity.com/paper/2302.01539/) (2023)
- [Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures](https://mlsanity.com/paper/2312.09181/) (2023)
- [ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models](https://mlsanity.com/paper/2505.22569/) (2025)
- [GeoGuide: Geometric guidance of diffusion models](https://mlsanity.com/paper/2407.12889/) (2024)
- [DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model](https://mlsanity.com/paper/2311.11417/) (2023)
- [Particle-Filtering-based Latent Diffusion for Inverse Problems](https://mlsanity.com/paper/2408.13868/) (2024)
- [Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models](https://mlsanity.com/paper/2502.05807/) (2025)
- [Diffusion Model Compression for Image-to-Image Translation](https://mlsanity.com/paper/2401.17547/) (2024)
- [DeepShade: Enable Shade Simulation by Text-conditioned Image Generation](https://mlsanity.com/paper/2507.12103/) (2025)
- [EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Models](https://mlsanity.com/paper/2406.17462/) (2024)
- [Fine-grained Forecasting Models Via Gaussian Process Blurring Effect](https://mlsanity.com/paper/2312.14280/) (2023)
- [Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation](https://mlsanity.com/paper/2511.18281/) (2025)
- [Flexiffusion: Segment-wise Neural Architecture Search for Flexible Denoising Schedule](https://mlsanity.com/paper/2409.17566/) (2024)
- [Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models](https://mlsanity.com/paper/2506.02488/) (2025)
- [Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling](https://mlsanity.com/paper/2505.19868/) (2025)
- [Diffusion Denoiser-Aided Gyrocompassing](https://mlsanity.com/paper/2507.21245/) (2025)

## 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.