mlsanityData to 14 Oct 2026

Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising

arXiv 2509.16091 ↗First posted 19 Sep 2025cs.CVcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this work, we present Blind-Spot Guided Diffusion, a novel self-supervised framework for real-world image denoising. Our approach addresses two major challenges: the limitations of blind-spot networks (BSNs), which often sacrifice local detail and introduce pixel discontinuities due to spatial independence assumptions, and the difficulty of adapting diffusion models to self-supervised denoising. We propose a dual-branch diffusion framework that combines a BSN-based diffusion branch, generating semi-clean images, with a conventional diffusion branch that captures underlying noise distributions. To enable effective training without paired data, we use the BSN-based branch to guide the sampling process, capturing noise structure while preserving local details. Extensive experiments on the SIDD and DND datasets demonstrate state-of-the-art performance, establishing our method as a highly effective self-supervised solution for real-world denoising. Code and pre-trained models are released at: https://github.com/Sumching/BSGD.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 51 of its 64 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

51 of 64 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling8 Jul
  2. 2023Diffusion Model for Dense Matching30 May
  3. 2022Classifier-Free Diffusion Guidance26 Jul
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 44

  1. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  3. 2017Deep Image Priorcited by 1,098
  4. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  5. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  6. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  7. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  8. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 364
  9. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  10. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 327
  11. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 312
  12. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
32 more
  1. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  2. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  3. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  4. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  5. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 195
  6. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 173
  7. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  8. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 127
  9. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  10. 2020Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generationcited by 101
  11. 2019Coherent Semantic Attention for Image Inpaintingcited by 97
  12. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 93
  13. 2020NBNet: Noise Basis Learning for Image Denoising with Subspace Projectioncited by 77
  14. 2020Unpaired Learning of Deep Image Denoisingcited by 74
  15. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  16. 2020Noise2Same: Optimizing A Self-Supervised Bound for Image Denoisingcited by 56
  17. 2019When AWGN-based Denoiser Meets Real Noisescited by 53
  18. 2022CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Imagecited by 45
  19. 2023DiffusionTrack: Diffusion Model For Multi-Object Trackingcited by 40
  20. 2023LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoisingcited by 37
  21. 2023Spatially Adaptive Self-Supervised Learning for Real-World Image Denoisingcited by 33
  22. 2023MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Networkcited by 30
  23. 2023Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarioscited by 17
  24. 2023PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoisingcited by 16
  25. 2023Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoisingcited by 15
  26. 2016Generalized Deep Image to Image Regressioncited by 14
  27. 2024RecDiffusion: Rectangling for Image Stitching with Diffusion Modelscited by 14
  28. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactionscited by 13
  29. 2024Masked and Shuffled Blind Spot Denoising for Real-World Imagescited by 12
  30. 2018DN-ResNet: Efficient Deep Residual Network for Image Denoisingcited by 9
  31. 2023SS-BSN: Attentive Blind-Spot Network for Self-Supervised Denoising with Nonlocal Self-Similaritycited by 4
  32. 2018Survey of Face Detection on Low-quality Imagescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstructioncited by 1
  2. 2026ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
  2. 2023Real-World Denoising via Diffusion Model
  3. 2024Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
  4. 2025DiffDenoise: Self-Supervised Medical Image Denoising with Conditional Diffusion Models
  5. 2023Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild
  6. 2023Simple diffusion: End-to-end diffusion for high resolution images
  7. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
  8. 2026Efficient and Training-Free Single-Image Diffusion Models