mlsanityData to 7 Oct 2026

SUD2: Supervision by Denoising Diffusion Models for Image Reconstruction

arXiv 2303.09642 ↗First posted 16 Mar 2023cs.CV cs.LG eess.IVcited by 4

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Many imaging inverse problemsunicodex2014such as image-dependent in-painting and dehazingunicodex2014are challenging because their forward models are unknown or depend on unknown latent parameters. While one can solve such problems by training a neural network with vast quantities of paired training data, such paired training data is often unavailable. In this paper, we propose a generalized framework for training image reconstruction networks when paired training data is scarce. In particular, we demonstrate the ability of image denoising algorithms and, by extension, denoising diffusion models to supervise network training in the absence of paired training data.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 26 of its 42 references that are in the map. First posted on arXiv 16 Mar 2023.

Builds on

26 of 42 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2018Group Normalizationcited by 1,514
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  10. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  11. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  12. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
13 more
  1. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  2. 2017The Perception-Distortion Tradeoffcited by 582
  3. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  4. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  5. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  6. 2021A Survey on Deep Semi-supervised Learningcited by 250
  7. 2016The Importance of Skip Connections in Biomedical Image Segmentationcited by 126
  8. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 102
  9. 2018O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor imagescited by 95
  10. 2018Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazingcited by 79
  11. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  12. 2014From Denoising to Compressed Sensingcited by 67
  13. 2018I-HAZE: a dehazing benchmark with real hazy and haze-free indoor imagescited by 64

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  2. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  3. 2024Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariancecited by 42
  4. 2024Osmosis: RGBD Diffusion Prior for Underwater Image Restorationcited by 13

Similar, not cited

Close in wording, no citation either way

  1. 2022Denoising Diffusion Restoration Models
  2. 2024A Survey on Diffusion Models for Inverse Problems
  3. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
  4. 2025Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
  5. 2026Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems
  6. 2025Multi Task Denoiser Training for Solving Linear Inverse Problems ↗
  7. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models
  8. 2026Efficient and Training-Free Single-Image Diffusion Models