mlsanityData to 7 Oct 2026

Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation

arXiv 2412.00205 ↗First posted 29 Nov 2024cs.CV cs.LG stat.MLcited by 17

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Despite the remarkable progress in generative modelling, current diffusion models lack a quantitative approach to assess image quality. To address this limitation, we propose to estimate the pixel-wise aleatoric uncertainty during the sampling phase of diffusion models and utilise the uncertainty to improve the sample generation quality. The uncertainty is computed as the variance of the denoising scores with a perturbation scheme that is specifically designed for diffusion models. We then show that the aleatoric uncertainty estimates are related to the second-order derivative of the diffusion noise distribution. We evaluate our uncertainty estimation algorithm and the uncertainty-guided sampling on the ImageNet and CIFAR-10 datasets. In our comparisons with the related work, we demonstrate promising results in filtering out low quality samples. Furthermore, we show that our guided approach leads to better sample generation in terms of FID scores.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 37 of its 54 references that are in the map. First posted on arXiv 29 Nov 2024.

Builds on

37 of 54 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  2. 2023DiffEnc: Variational Diffusion with a Learned Encoder30 Oct
  3. 2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference17 Oct
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  6. 2021Variational Diffusion Models1 Jul
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Implicit Models6 Oct
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 27

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  7. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  8. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  9. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  10. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
  11. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  12. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 161
15 more
  1. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  2. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  3. 2018Bayesian Uncertainty Estimation for Batch Normalized Deep Networkscited by 70
  4. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  5. 2017Bayesian GANcited by 31
  6. 2019Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogatecited by 28
  7. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  8. 2024Multi-conditioned Graph Diffusion for Neural Architecture Searchcited by 13
  9. 2024Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Modelscited by 13
  10. 2018Deep Generative Models in the Real-World: An Open Challenge from Medical Imagingcited by 12
  11. 2018Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximizationcited by 12
  12. 2020Uncertainty Quantification using Variational Inference for Biomedical Image Segmentationcited by 10
  13. 2023Joint Out-of-Distribution Detection and Uncertainty Estimation for Trajectory Predictioncited by 10
  14. 2022Heatmap-based Out-of-Distribution Detectioncited by 9
  15. 2023Out-of-Distribution Detection for Monocular Depth Estimationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 14.

17 papers.

Sort:

By area:

  1. 2025Generative Uncertainty in Diffusion Modelscited by 20
  2. 2026Self-Refining Video Samplingcited by 14
  3. 2026Epistemic Generative Adversarial Networkscited by 4
  4. 2026PAD-Hand: Physics-Aware Diffusion for Hand Motion Recoverycited by 4
  5. 2025Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detectioncited by 3
  6. 2026Flow Matching with Uncertainty Quantification and Guidancecited by 3
  7. 2026Quantifying Epistemic Uncertainty in Diffusion Modelscited by 2
  8. 2026When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Modelscited by 1
  9. 2026Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imagingcited by 1
  10. 2026Spatially Adaptive Noise Injectioncited by 1
  11. 2025LC4-DViT: Land-cover Creation for Land-cover Classification with Deformable Vision Transformercited by 0
  12. 2026Inline Critic Steers Image Editingcited by 0
5 more
  1. 2026Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generationcited by 0
  2. 2026Uncertainty Estimation for Molecular Diffusion Modelscited by 0
  3. 2026LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Predictioncited by 0
  4. 2026Is your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternativecited by 0
  5. 2026Generative Uncertainty as a Self-supervised Signal for Semantic Similarity Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation
  2. 2023Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
  3. 2025Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model
  4. 2026On the Robustness of Distribution Support under Diffusion Guidance
  5. 2024Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models
  6. 2022Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
  7. 2025Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
  8. 2024Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis