mlsanityData to 7 Oct 2026

Zero-Shot Noise2Noise: Efficient Image Denoising without any Data

arXiv 2303.11253 ↗First posted 20 Mar 2023cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

Recently, self-supervised neural networks have shown excellent image denoising performance. However, current dataset free methods are either computationally expensive, require a noise model, or have inadequate image quality. In this work we show that a simple 2-layer network, without any training data or knowledge of the noise distribution, can enable high-quality image denoising at low computational cost. Our approach is motivated by Noise2Noise and Neighbor2Neighbor and works well for denoising pixel-wise independent noise. Our experiments on artificial, real-world camera, and microscope noise show that our method termed ZS-N2N (Zero Shot Noise2Noise) often outperforms existing dataset-free methods at a reduced cost, making it suitable for use cases with scarce data availability and limited computational resources. A demo of our implementation including our code and hyperparameters can be found in the following colab notebook: https://colab.research.google.com/drive/1i82nyizTdszyHkaHBuKPbWnTzao8HF9b

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

25 of 40 references.

References · 25

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2017Deep Image Priorcited by 1,097
  6. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  7. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  8. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  9. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  10. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  11. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  12. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 212
13 more
  1. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 171
  2. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  3. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  4. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  5. 2018Real-world Noisy Image Denoising: A New Benchmarkcited by 74
  6. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 70
  7. 2019Probabilistic Noise2Void: Unsupervised Content-Aware Denoisingcited by 51
  8. 2018Training Deep Learning Based Denoisers without Ground Truth Datacited by 43
  9. 2021Noise2Fast: Fast Self-Supervised Single Image Blind Denoisingcited by 28
  10. 2020Polyblur: Removing mild blur by polynomial reblurringcited by 13
  11. 2022Zero-shot Blind Image Denoising via Implicit Neural Representationscited by 12
  12. 2022Image-to-Image MLP-mixer for Image Reconstructioncited by 9
  13. 2018Fully Convolutional Pixel Adaptive Image Denoisercited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 22; 2025: 19; 2026: 15.

59 papers.

Sort:

By area:

  1. 2024LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detectioncited by 88
  2. 2024NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Resultscited by 26
  3. 2023Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensemblingcited by 17
  4. 2024LAN: Learning to Adapt Noise for Image Denoisingcited by 10
  5. 2023Deep Internal Learning: Deep Learning from a Single Inputcited by 9
  6. 2023Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methodscited by 8
  7. 2024Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Modelcited by 8
  8. 2024Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoisingcited by 6
  9. 2025Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinementcited by 6
  10. 2024Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoisingcited by 5
  11. 2025Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoisingcited by 5
  12. 2024Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoisingcited by 4
38 more
  1. 2024Robust multi-coil MRI reconstruction via self-supervised denoisingcited by 4
  2. 2024Learning to Translate Noise for Robust Image Denoisingcited by 4
  3. 2025Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancementcited by 4
  4. 2025YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependencycited by 4
  5. 2025IGDNet: Zero-Shot Robust Underexposed Image Enhancement via Illumination-Guided and Denoisingcited by 4
  6. 2024Masked Pre-training Enables Universal Zero-shot Denoisercited by 3
  7. 2024Neighboring Slice Noise2Noise: Self-Supervised Medical Image Denoising from Single Noisy Image Volumecited by 3
  8. 2025U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matchingcited by 3
  9. 2024Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robotscited by 2
  10. 2024Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurringcited by 2
  11. 2025Lightweight Data-Free Denoising for Detail-Preserving Biomedical Image Restorationcited by 2
  12. 2024DARDA: Domain-Aware Real-Time Dynamic Neural Network Adaptationcited by 1
  13. 2024FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoisingcited by 1
  14. 2025Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoisingcited by 1
  15. 2025Zero-shot Denoising via Neural Compression: Theoretical and algorithmic frameworkcited by 1
  16. 2025Lightweight Physics-Aware Zero-Shot Ultrasound Plane-Wave Denoisingcited by 1
  17. 2025Equivariant Sampling for Improving Diffusion Model-based Image Restorationcited by 1
  18. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1
  19. 2026Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoisingcited by 1
  20. 2024A unified framework of non-local parametric methods for image denoisingcited by 0
  21. 2024GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restorationcited by 0
  22. 2024Investigating Self-Supervised Image Denoising with Denaturationcited by 0
  23. 2024Zero-Shot Image Denoising for High-Resolution Electron Microscopycited by 0
  24. 2024Diffusion Priors for Variational Likelihood Estimation and Image Denoisingcited by 0
  25. 2024An Efficient Self-supervised Seismic Data Reconstruction Method Based on Self-Consistency Learningcited by 0
  26. 2024Adaptive Domain Learning for Cross-domain Image Denoisingcited by 0
  27. 2025Towards Robust Image Denoising with Scale Equivariancecited by 0
  28. 2025Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstructioncited by 0
  29. 2025Median2Median: Zero-shot Suppression of Structured Noise in Imagescited by 0
  30. 2025Net2Net: When Un-trained Meets Pre-trained Networks for Robust Real-World Denoisingcited by 0
  31. 2025Transforming Noise Distributions with Histogram Matching: Towards a Single Denoiser for Allcited by 0
  32. 2025Spectral Prefiltering of Neural Fieldscited by 0
  33. 2025Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistencycited by 0
  34. 2025TPCNet: Triple physical constraints for Low-light Image Enhancementcited by 0
  35. 2026A low-complexity method for efficient depth-guided image deblurringcited by 0
  36. 2026A Single-Parameter Factor-Graph Image Priorcited by 0
  37. 2026SSC-UNet: UNet with Self-Supervised Contrastive Learning for Phonocardiography Noise Reductioncited by 0
  38. 2026SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTioncited by 0

50 most cited of 59 All 59 (JSON)