mlsanityData to 7 Oct 2026

Conffusion: Confidence Intervals for Diffusion Models

arXiv 2211.09795 ↗First posted 17 Nov 2022cs.CVcited by 33

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion-based methods do not provide statistical guarantees regarding the generated results, often preventing their use in high-stakes situations. To bridge this gap, we construct a confidence interval around each generated pixel such that the true value of the pixel is guaranteed to fall within the interval with a probability set by the user. Since diffusion models parametrize the data distribution, a straightforward way of constructing such intervals is by drawing multiple samples and calculating their bounds. However, this method has several drawbacks: i) slow sampling speeds ii) suboptimal bounds iii) requires training a diffusion model per task. To mitigate these shortcomings we propose Conffusion, wherein we fine-tune a pre-trained diffusion model to predict interval bounds in a single forward pass. We show that Conffusion outperforms the baseline method while being three orders of magnitude faster.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 33 of its 39 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

33 of 39 references.

Closest ancestors · 7

Same direction, newest first

  1. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation30 Nov
  4. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  5. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 26

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  10. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  12. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
14 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  3. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  4. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  5. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  6. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  7. 2020ResNeSt: Split-Attention Networkscited by 445
  8. 2022Blended Latent Diffusioncited by 430
  9. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  10. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  11. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  12. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  13. 2022Predictive Inference with Feature Conformal Predictioncited by 33
  14. 2022Semantic uncertainty intervals for disentangled latent spacescited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 8; 2025: 6; 2026: 4.

33 papers.

Sort:

By area:

  1. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 230
  2. 2023Dreamix: Video Diffusion Models are General Video Editorscited by 189
  3. 2023Conformal Language Modelingcited by 163
  4. 2023The Chosen One: Consistent Characters in Text-to-Image Diffusion Modelscited by 62
  5. 2023Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Modelscited by 61
  6. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 52
  7. 2023How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Controlcited by 50
  8. 2023On the Posterior Distribution in Denoising: Application to Uncertainty Quantificationcited by 31
  9. 2023Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problemscited by 28
  10. 2023Conformal Contextual Robust Optimizationcited by 25
  11. 2023Uncertainty Quantification via Neural Posterior Principal Componentscited by 16
  12. 2023From Posterior Sampling to Meaningful Diversity in Image Restorationcited by 12
21 more
  1. 2024Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filteringcited by 10
  2. 2024Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Predictioncited by 8
  3. 2024C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Setscited by 7
  4. 2024X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Modelscited by 5
  5. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  6. 2024Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classificationcited by 5
  7. 2025Statistical Methods in Generative AIcited by 4
  8. 2023Uncertainty Visualization via Low-Dimensional Posterior Projectionscited by 3
  9. 2024Ultrasound Imaging based on the Variance of a Diffusion Restoration Modelcited by 3
  10. 2024Metric-Guided Conformal Bounds for Probabilistic Image Reconstructioncited by 3
  11. 2023Diffusion Reconstruction of Ultrasound Images with Informative Uncertaintycited by 2
  12. 2025Conformal Bounds on Full-Reference Image Quality for Imaging Inverse Problemscited by 2
  13. 2025Singleton-Optimized Conformal Predictioncited by 2
  14. 2023How Good Are Deep Generative Models for Solving Inverse Problems?cited by 1
  15. 2025Segmentation-Guided CT Synthesis with Pixel-Wise Conformal Uncertainty Boundscited by 1
  16. 2025Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priorscited by 1
  17. 2026Empirical Bayes Conformal Prediction for Vision and Language Modelscited by 1
  18. 2025Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problemscited by 0
  19. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  20. 2026KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problemscited by 0
  21. 2026Matisse: Evidence-Space Reasoning for Active 3D Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
  2. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Images
  3. 2023AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation
  4. 2023Improved Sample Complexity Bounds for Diffusion Model Training
  5. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
  6. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
  7. 2021Variational Diffusion Models
  8. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models