mlsanityData to 7 Oct 2026

RELD: Regularization by Latent Diffusion Models for Image Restoration

arXiv 2503.22563 ↗First posted 28 Mar 2025eess.IV cs.CVcited by 0

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

Abstract (arXiv)

In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an approach that integrates a Latent Diffusion Model, trained for the denoising task, into a variational framework using Half-Quadratic Splitting, exploiting its regularization properties. This approach, under appropriate conditions that can be easily met in various imaging applications, allows for reduced computational cost while achieving high-quality results. The proposed strategy, called Regularization by Latent Denoising (RELD), is then tested on a dataset of natural images, for image denoising, deblurring, and super-resolution tasks. The numerical experiments show that RELD is competitive with other state-of-the-art methods, particularly achieving remarkable results when evaluated using perceptual quality metrics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 51 of its 72 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

51 of 72 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models27 May
  2. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction25 Mar
  3. 2024Efficient Diffusion Model for Image Restoration by Residual Shifting12 Mar
  4. 2023Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance27 Dec
  5. 2023Prompt-tuning latent diffusion models for inverse problems2 Oct
  6. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey18 Aug
  7. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
  8. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restoration23 May
  9. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  10. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models17 Apr
  11. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement3 Apr
  12. 2023DiffIR: Efficient Diffusion Model for Image Restoration16 Mar
2 more
  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  2. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun

Other references · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  10. 2015Variational Inference with Normalizing Flowscited by 2,161
  11. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  12. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
25 more
  1. 2017Deep Image Priorcited by 1,097
  2. 2022Diffusion Models in Vision: A Surveycited by 1,008
  3. 2016Pixel Recurrent Neural Networkscited by 814
  4. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  5. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  6. 2017Compressed Sensing using Generative Modelscited by 337
  7. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  8. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  9. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  10. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  11. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  12. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
  13. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 194
  14. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 102
  15. 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 94
  16. 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
  17. 2018Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteescited by 58
  18. 2020Regularization by Denoising via Fixed-Point Projection (RED-PRO)cited by 55
  19. 2018Blind Image Deconvolution using Deep Generative Priorscited by 40
  20. 2021Regularising Inverse Problems with Generative Machine Learning Modelscited by 22
  21. 2023Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problemscited by 14
  22. 2020Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMMcited by 13
  23. 2023Learning from small data sets: Patch-based regularizers in inverse problems for image reconstructioncited by 9
  24. 2021Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restorationcited by 7
  25. 2023Constrained Regularization by Denoising with Automatic Parameter Selectioncited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Image Embedding for Denoising Generative Models
  2. 2024Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
  3. 2022Denoising Diffusion Restoration Models
  4. 2025LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image Restoration
  5. 2023Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
  6. 2023Diffusion Model for Generative Image Denoising
  7. 2025Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
  8. 2023Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising