mlsanityData to 7 Oct 2026

Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise

arXiv 2412.04648 ↗First posted 5 Dec 2024eess.IV stat.MLcited by 13

Not on the map. Why?

Abstract (arXiv)

Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian noise remains unexplored. In this paper, we propose Generalized R2R (GR2R), extending the R2R framework to handle a broader class of noise distribution as additive noise like log-Rayleigh and address the natural exponential family including Poisson and Gamma noise distributions, which play a key role in many applications including low-photon imaging and synthetic aperture radar. We show that the GR2R loss is an unbiased estimator of the supervised loss and that the popular Stein's unbiased risk estimator can be seen as a special case. A series of experiments with Gaussian, Poisson, and Gamma noise validate GR2R's performance, showing its effectiveness compared to other self-supervised methods.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

20 of 35 references.

References · 20

  1. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  2. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  3. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  4. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  5. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  6. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  7. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 171
  8. 2022Measuring Forgetting of Memorized Training Examplescited by 118
  9. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
  10. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  11. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  12. 2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 83
8 more
  1. 2021Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurementscited by 56
  2. 2022Unsupervised Learning From Incomplete Measurements for Inverse Problemscited by 20
  3. 2021Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matchingcited by 18
  4. 2020SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategycited by 10
  5. 2021Unbiased Risk Estimation in the Normal Means Problem via Coupled Bootstrap Techniquescited by 6
  6. 2013Audio Texture Synthesis with Scattering Momentscited by 4
  7. 2023Image Denoising and the Generative Accumulation of Photonscited by 3
  8. 2022Unbiased Test Error Estimation in the Poisson Means Problem via Coupled Bootstrap Techniquescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

  1. 2026Self-Supervised Learning from Noisy and Incomplete Datacited by 5
  2. 2025Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurementscited by 3
  3. 2025Reconstruct Anything Model: a lightweight general model for computational imagingcited by 1
  4. 2025Equivariant Splitting: Self-supervised learning from incomplete datacited by 1
  5. 2025See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Modelscited by 1
  6. 2026Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoisingcited by 1
  7. 2025Hypothesis Testing in Imaging Inverse Problemscited by 0
  8. 2025SDPA++: A General Framework for Self-Supervised Denoising with Patch Aggregationcited by 0
  9. 2025Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurementscited by 0
  10. 2026Scale Equivariance Regularization and Feature Lifting in High Dynamic Range Modulo Imagingcited by 0
  11. 2026Perspective-Equivariant Fine-tuning for Multispectral Demosaicing without Ground Truthcited by 0
  12. 2026Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditionscited by 0
1 more
  1. 2026Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problemscited by 0