# Noise2Fast: Fast Self-Supervised Single Image Blind Denoising

arXiv: https://arxiv.org/abs/2108.10209 · HTML: https://mlsanity.com/paper/2108.10209/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2021.

## Built on by (most cited first, 28 of 28)

- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising](https://mlsanity.com/paper/2308.04682/) (2023)
- [Self-supervised learning of hologram reconstruction using physics consistency](https://mlsanity.com/paper/2209.08288/) (2022)
- [Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods](https://mlsanity.com/paper/2305.19079/) (2023)
- [Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising](https://mlsanity.com/paper/2212.00422/) (2022)
- [Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising](https://mlsanity.com/paper/2407.17399/) (2024)
- [Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment Loss](https://mlsanity.com/paper/2307.10695/) (2023)
- [Masked Pre-training Enables Universal Zero-shot Denoiser](https://mlsanity.com/paper/2401.14966/) (2024)
- [bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction](https://mlsanity.com/paper/2410.23247/) (2024)
- [Zero-Shot Low-dose CT Denoising via Sinogram Flicking](https://mlsanity.com/paper/2504.07927/) (2025)
- [Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoising](https://mlsanity.com/paper/2504.13519/) (2025)
- [Self2Seg: Single-Image Self-Supervised Joint Segmentation and Denoising](https://mlsanity.com/paper/2309.10511/) (2023)
- [FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising](https://mlsanity.com/paper/2412.10031/) (2024)
- [Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework](https://mlsanity.com/paper/2506.12693/) (2025)
- [Domino Denoise: An Accurate Blind Zero-Shot Denoiser using Domino Tilings](https://mlsanity.com/paper/2212.02439/) (2022)
- [A unified framework of non-local parametric methods for image denoising](https://mlsanity.com/paper/2402.13816/) (2024)
- [Investigating Self-Supervised Image Denoising with Denaturation](https://mlsanity.com/paper/2405.01124/) (2024)
- [Fast Unsupervised Tensor Restoration via Low-rank Deconvolution](https://mlsanity.com/paper/2406.10679/) (2024)
- [Zero-Shot Image Denoising for High-Resolution Electron Microscopy](https://mlsanity.com/paper/2406.14264/) (2024)
- [Denoising diffusion models for high-resolution microscopy image restoration](https://mlsanity.com/paper/2409.12078/) (2024)
- [SNRAware: Improved Deep Learning MRI Denoising with SNR Unit Training and G-factor Map Augmentation](https://mlsanity.com/paper/2503.18162/) (2025)
- [Noise2Ghost: Self-supervised deep convolutional reconstruction for ghost imaging](https://mlsanity.com/paper/2504.10288/) (2025)
- [Median2Median: Zero-shot Suppression of Structured Noise in Images](https://mlsanity.com/paper/2510.01666/) (2025)
- [Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistency](https://mlsanity.com/paper/2510.12646/) (2025)
- [Learning-based Statistical Refinement for Denoising](https://mlsanity.com/paper/2605.04332/) (2026)
- [Deploying Self-Supervised Learning for Real Seismic Data Denoising](https://mlsanity.com/paper/2605.11109/) (2026)
- [A Zero-Shot Deep Image Prior Framework for Denoising and Deconvolution in Fluorescence Microscopy](https://mlsanity.com/paper/2606.28431/) (2026)
- [ASTRA-SR: Atmospheric Seeing and Turbulence Restoration for Astronomical Image Super-Resolution](https://mlsanity.com/paper/2609.26731/) (2026)

## Abstract (arXiv)

In the last several years deep learning based approaches have come to dominate many areas of computer vision, and image denoising is no exception. Neural networks can learn by example to map noisy images to clean images. However, access to noisy/clean or even noisy/noisy image pairs isn't always readily available in the desired domain. Recent approaches have allowed for the denoising of single noisy images without access to any training data aside from that very image. But since they require both training and inference to be carried out on each individual input image, these methods require significant computation time. As such, they are difficult to integrate into automated microscopy pipelines where denoising large datasets is essential but needs to be carried out in a timely manner. Here we present Noise2Fast, a fast single image blind denoiser. Our method is tailored for speed by training on a four-image dataset produced using a unique form of downsampling we refer to as "checkerboard downsampling". Noise2Fast is faster than all tested approaches and is more accurate than all except Self2Self, which takes well over 100 times longer to denoise an image. This allows for a combination of speed and flexibility that was not previously attainable using any other method.