# Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising

arXiv: https://arxiv.org/abs/2603.25869 · HTML: https://mlsanity.com/paper/2603.25869/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Noisier2Noise: Learning to Denoise from Unpaired Noisy Data](https://mlsanity.com/paper/1910.11908/) (2019)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network](https://mlsanity.com/paper/2203.11799/) (2022)
- [Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots](https://mlsanity.com/paper/2203.06967/) (2022)
- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning](https://mlsanity.com/paper/2409.06219/) (2024)
- [Constrained Monotonic Neural Networks](https://mlsanity.com/paper/2205.11775/) (2022)
- [MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network](https://mlsanity.com/paper/2304.01598/) (2023)
- [DeepInverse: A Python package for solving imaging inverse problems with deep learning](https://mlsanity.com/paper/2505.20160/) (2025)
- [Image Restoration for Remote Sensing: Overview and Toolbox](https://mlsanity.com/paper/2107.00557/) (2021)
- [Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review](https://mlsanity.com/paper/2308.00247/) (2023)
- [UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate](https://mlsanity.com/paper/2409.01985/) (2024)
- [Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise](https://mlsanity.com/paper/2412.04648/) (2024)
- [GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images](https://mlsanity.com/paper/1905.10488/) (2019)
- [Self-Supervised Learning from Noisy and Incomplete Data](https://mlsanity.com/paper/2601.03244/) (2026)
- [Learning to Translate Noise for Robust Image Denoising](https://mlsanity.com/paper/2412.04727/) (2024)
- [Blind2Sound: Self-Supervised Image Denoising without Residual Noise](https://mlsanity.com/paper/2303.05183/) (2023)

## Built on by (most cited first, 1 of 1)

- [Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising](https://mlsanity.com/paper/2609.16788/) (2026)

## Abstract (arXiv)

Self-supervised image denoising methods have traditionally relied on architectural constraints, pseudo-pair constructions, or specialized loss functions to avoid the trivial identity mapping. Among these, approaches such as Noisier2Noise or R2R create training pairs by adding synthetic noise to noisy images. While effective, these recorruption-based approaches require precise knowledge of the noise distribution, which is often unavailable. We present Learning to Recorrupt (L2R), a self-supervised framework that does not require exact knowledge of the noise distribution. Our method introduces a learnable recorruptor jointly optimized with the denoiser through a min--max saddle-point objective. The proposed method achieves state-of-the-art performance among methods without prior knowledge of the noise distribution across unconventional and heavy-tailed noise distributions, such as log-gamma and Laplace, as well as spatially correlated noise, while obtaining competitive results on real-world denoising benchmarks characterized by signal-dependent noise.