mlsanityData to 7 Oct 2026

WaveDM: Wavelet-Based Diffusion Models for Image Restoration

arXiv 2305.13819 ↗First posted 23 May 2023cs.CVcited by 46

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

Abstract (arXiv)

Latest diffusion-based methods for many image restoration tasks outperform traditional models, but they encounter the long-time inference problem. To tackle it, this paper proposes a Wavelet-Based Diffusion Model (WaveDM). WaveDM learns the distribution of clean images in the wavelet domain conditioned on the wavelet spectrum of degraded images after wavelet transform, which is more time-saving in each step of sampling than modeling in the spatial domain. To ensure restoration performance, a unique training strategy is proposed where the low-frequency and high-frequency spectrums are learned using distinct modules. In addition, an Efficient Conditional Sampling (ECS) strategy is developed from experiments, which reduces the number of total sampling steps to around 5. Evaluations on twelve benchmark datasets including image raindrop removal, rain steaks removal, dehazing, defocus deblurring, demoir'eing, and denoising demonstrate that WaveDM achieves state-of-the-art performance with the efficiency that is comparable to traditional one-pass methods and over 100× faster than existing image restoration methods using vanilla diffusion models.

Key facts. Cited by 46 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 100 of its 132 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

100 of 132 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration30 Jan
  2. 2022DifFace: Blind Face Restoration with Diffused Error Contraction13 Dec
  3. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  4. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problems19 Nov
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  6. 2022AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Models24 Aug
  7. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models29 Jul
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun
  9. 2022Denoising Diffusion Restoration Models27 Jan
  10. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec
  11. 2021Deblurring via Stochastic Refinement5 Dec
  12. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 88

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  12. 2022Classifier-Free Diffusion Guidancecited by 5,717
38 more
  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  3. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  4. 2016Wide Residual Networkscited by 3,057
  5. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  6. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  7. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  8. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  9. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  10. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  11. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  12. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  13. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  14. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  15. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  16. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  17. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  18. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  19. 2021Multi-Stage Progressive Image Restorationcited by 813
  20. 2022On Distillation of Guided Diffusion Modelscited by 721
  21. 2022Simple Baselines for Image Restorationcited by 701
  22. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  23. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  24. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  25. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  26. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  27. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  28. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  29. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  30. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  31. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  32. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  33. 2022Inversion-Based Style Transfer with Diffusion Modelscited by 290
  34. 2022Vision Transformers for Single Image Dehazingcited by 255
  35. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  36. 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 229
  37. 2019GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazingcited by 227
  38. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 15; 2025: 17; 2026: 9.

46 papers.

Sort:

By area:

  1. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  2. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  3. 2025A Fourier Space Perspective on Diffusion Modelscited by 48
  4. 2024Token Caching for Diffusion Transformer Accelerationcited by 29
  5. 2023KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editingcited by 21
  6. 2023PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editingcited by 20
  7. 2024MagicEraser: Erasing Any Objects via Semantics-Aware Controlcited by 15
  8. 2023FEC: Three Finetuning-free Methods to Enhance Consistency for Real Image Editingcited by 11
  9. 2024Conditioning diffusion models by explicit forward-backward bridgingcited by 11
  10. 2024On the Asymptotic Mean Square Error Optimality of Diffusion Modelscited by 10
  11. 2024Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editingcited by 10
  12. 2026RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Modelscited by 9
34 more
  1. 2024Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editingcited by 8
  2. 2025Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesiscited by 6
  3. 2023Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancementcited by 5
  4. 2024Edge-preserving noise for diffusion modelscited by 5
  5. 2024SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editingcited by 4
  6. 2024A Wavelet Diffusion GAN for Image Super-Resolutioncited by 4
  7. 2024CasDyF-Net: Image Dehazing via Cascaded Dynamic Filterscited by 3
  8. 2025DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Modelcited by 2
  9. 2025Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolutioncited by 2
  10. 2025DFDNet: Dynamic Frequency-Guided De-Flare Networkcited by 2
  11. 2025WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus Imagescited by 2
  12. 2023Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisationcited by 1
  13. 2024Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolutioncited by 1
  14. 2024Multi-scale Generative Modeling for Fast Samplingcited by 1
  15. 2024Controlling the Latent Diffusion Model for Generative Image Shadow Removal via Residual Generationcited by 1
  16. 2025Leveraging Contrast Information for Efficient Document Shadow Removalcited by 1
  17. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  18. 2025Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolutioncited by 1
  19. 2026Spectral Regularization for Diffusion Modelscited by 1
  20. 2025RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Priorcited by 0
  21. 2025RELD: Regularization by Latent Diffusion Models for Image Restorationcited by 0
  22. 2025ControlMambaIR: Conditional Controls with State-Space Model for Image Restorationcited by 0
  23. 2025Component Adaptive Clustering for Generalized Category Discoverycited by 0
  24. 2025WaFusion: A Wavelet-Enhanced Diffusion Framework for Face Morph Generationcited by 0
  25. 2025Diffusion Models for Low-Light Image Enhancement: A Multi-Perspective Taxonomy and Performance Analysiscited by 0
  26. 2025HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolutioncited by 0
  27. 2025Traffic Image Restoration under Adverse Weather via Frequency-Aware Mambacited by 0
  28. 2026SFKD: Spatial--Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interactioncited by 0
  29. 2026DiffCVE: Diffusion-based Compressed Video Enhancementcited by 0
  30. 2026Filtering-out poor-quality images for data preparationcited by 0
  31. 2026Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translationcited by 0
  32. 2026Beyond Edge Maps: Wavelet-Domain Conditioning for Multi-Adapter Map-to-Satellite Diffusioncited by 0
  33. 2026FLM: Frequency-Aware Language Models for Generative Image Compressioncited by 0
  34. 2026LLPR: Location-aware learning and physics-based reconstruction for raindrop removal from a single imagecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Models
  2. 2023A Unified Conditional Framework for Diffusion-based Image Restoration
  3. 2024Diffusion Posterior Proximal Sampling for Image Restoration
  4. 2026Efficient and Training-Free Single-Image Diffusion Models
  5. 2024Taming Diffusion Models for Image Restoration: A Review
  6. 2023Residual Denoising Diffusion Models
  7. 2023Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models
  8. 2023Restoration based Generative Models