mlsanityData to 7 Oct 2026

Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling

arXiv 2307.03992 ↗First posted 8 Jul 2023cs.CVcited by 17

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion. Recently, the emerging diffusion model has achieved state-of-the-art performance in various tasks and demonstrates great potential for image denoising. However, stimulating diffusion models for image denoising is not straightforward and requires solving several critical problems. For one thing, the input inconsistency hinders the connection between diffusion models and image denoising. For another, the content inconsistency between the generated image and the desired denoised image introduces distortion. To tackle these problems, we present a novel strategy called the Diffusion Model for Image Denoising (DMID) by understanding and rethinking the diffusion model from a denoising perspective. Our DMID strategy includes an adaptive embedding method that embeds the noisy image into a pre-trained unconditional diffusion model and an adaptive ensembling method that reduces distortion in the denoised image. Our DMID strategy achieves state-of-the-art performance on both distortion-based and perception-based metrics, for both Gaussian and real-world image denoising.The code is available at https://github.com/Li-Tong-621/DMID.

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 55 of its 100 references that are in the map. First posted on arXiv 8 Jul 2023.

Builds on

55 of 100 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023Diffusion models with location-scale noise12 Apr
  2. 2023Diffusion Model for Generative Image Denoising5 Feb
  3. 2022SinDDM: A Single Image Denoising Diffusion Model29 Nov
  4. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise19 Aug
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  6. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  8. 2020Denoising Diffusion Implicit Models6 Oct
  9. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 46

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  7. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  8. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  9. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  10. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  11. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  12. 2020Pre-Trained Image Processing Transformercited by 891
34 more
  1. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  2. 2021Multi-Stage Progressive Image Restorationcited by 813
  3. 2022Simple Baselines for Image Restorationcited by 701
  4. 2017The Perception-Distortion Tradeoffcited by 582
  5. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  6. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  7. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  8. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  9. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  10. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  11. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  12. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  13. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  14. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  15. 2021Deblurring via Stochastic Refinementcited by 248
  16. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  17. 2018Residual Dense Network for Image Restorationcited by 181
  18. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  19. 2020Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generationcited by 101
  20. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 92
  21. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  22. 2018Denoising Prior Driven Deep Neural Network for Image Restorationcited by 80
  23. 2020NBNet: Noise Basis Learning for Image Denoising with Subspace Projectioncited by 77
  24. 2018Real-world Noisy Image Denoising: A New Benchmarkcited by 74
  25. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 70
  26. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 59
  27. 2022C2N: Practical Generative Noise Modeling for Real-World Denoisingcited by 56
  28. 2018Training Deep Learning Based Denoisers without Ground Truth Datacited by 43
  29. 2023LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoisingcited by 37
  30. 2020Learning Camera-Aware Noise Modelscited by 32
  31. 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
  32. 2019On The Classification-Distortion-Perception Tradeoffcited by 21
  33. 2022Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Imagescited by 17
  34. 2020Reconstructing the Noise Manifold for Image Denoisingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 12; 2026: 1.

17 papers.

Sort:

By area:

  1. 2025Visual Prompting for One-shot Controllable Video Editing without Inversioncited by 8
  2. 2024Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoisingcited by 6
  3. 2024Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoisingcited by 5
  4. 2024PFCM: Poisson flow consistency models for low-dose CT image denoisingcited by 4
  5. 2024Image Denoising Using Green Channel Priorcited by 4
  6. 2025Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Trackingcited by 2
  7. 2025Blind-Spot Guided Diffusion for Self-supervised Real-World Denoisingcited by 2
  8. 2025Test-Time Preference Optimization for Image Restorationcited by 2
  9. 2025CoCA: Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuningcited by 1
  10. 2025Continuous-variable Quantum Diffusion Model for State Generation and Restorationcited by 1
  11. 2025MegaSR: Mining Customized Semantics and Expressive Guidance for Real-World Image Super-Resolutioncited by 0
  12. 2025Efficient Image Denoising Using Global and Local Circulant Representationcited by 0
5 more
  1. 2025Transforming Noise Distributions with Histogram Matching: Towards a Single Denoiser for Allcited by 0
  2. 2025MID: A Self-supervised Multimodal Iterative Denoising Frameworkcited by 0
  3. 2025Establishing Stochastic Object Models from Noisy Data via Ambient Measurement-Integrated Diffusioncited by 0
  4. 2025Image Denoising Using Global and Local Circulant Representationcited by 0
  5. 2026Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image Denoising
  2. 2024Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
  3. 2023Real-World Denoising via Diffusion Model
  4. 2023Simple diffusion: End-to-end diffusion for high resolution images
  5. 2024Diffusion Model-Based Image Editing: A Survey
  6. 2023Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising
  7. 2023High-Fidelity Diffusion-based Image Editing
  8. 2023Residual Denoising Diffusion Models