# GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images

arXiv: https://arxiv.org/abs/1905.10488 · HTML: https://mlsanity.com/paper/1905.10488/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2019.

## Built on by (most cited first, 12 of 12)

- [C2N: Practical Generative Noise Modeling for Real-World Denoising](https://mlsanity.com/paper/2202.09533/) (2022)
- [Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches](https://mlsanity.com/paper/2308.06776/) (2023)
- [Optimal Transport for Unsupervised Denoising Learning](https://mlsanity.com/paper/2108.02574/) (2021)
- [FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise](https://mlsanity.com/paper/2105.10967/) (2021)
- [End-to-End Unsupervised Document Image Blind Denoising](https://mlsanity.com/paper/2105.09437/) (2021)
- [Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration](https://mlsanity.com/paper/2408.09241/) (2024)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [MEGA: Model Stealing via Collaborative Generator-Substitute Networks](https://mlsanity.com/paper/2202.00008/) (2022)
- [Data-Driven Modeling of Noise Time Series with Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/2207.01110/) (2022)
- [High Dynamic Range Image Reconstruction via Deep Explicit Polynomial Curve Estimation](https://mlsanity.com/paper/2307.16426/) (2023)
- [Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising](https://mlsanity.com/paper/2603.25869/) (2026)
- [SelfReDepth: Self-Supervised Real-Time Depth Restoration for Consumer-Grade Sensors](https://mlsanity.com/paper/2406.03388/) (2024)

## Abstract (arXiv)

We tackle a challenging blind image denoising problem, in which only single distinct noisy images are available for training a denoiser, and no information about noise is known, except for it being zero-mean, additive, and independent of the clean image. In such a setting, which often occurs in practice, it is not possible to train a denoiser with the standard discriminative training or with the recently developed Noise2Noise (N2N) training; the former requires the underlying clean image for the given noisy image, and the latter requires two independently realized noisy image pair for a clean image. To that end, we propose GAN2GAN (Generated-Artificial-Noise to Generated-Artificial-Noise) method that first learns a generative model that can 1) simulate the noise in the given noisy images and 2) generate a rough, noisy estimates of the clean images, then 3) iteratively trains a denoiser with subsequently synthesized noisy image pairs (as in N2N), obtained from the generative model. In results, we show the denoiser trained with our GAN2GAN achieves an impressive denoising performance on both synthetic and real-world datasets for the blind denoising setting; it almost approaches the performance of the standard discriminatively-trained or N2N-trained models that have more information than ours, and it significantly outperforms the recent baseline for the same setting, textite.g., Noise2Void, and a more conventional yet strong one, BM3D. The official code of our method is available at https://github.com/csm9493/GAN2GAN.