# N2V2 -- Fixing Noise2Void Checkerboard Artifacts with Modified Sampling Strategies and a Tweaked Network Architecture

arXiv: https://arxiv.org/abs/2211.08512 · HTML: https://mlsanity.com/paper/2211.08512/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 15 Nov 2022.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [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)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Probabilistic Noise2Void: Unsupervised Content-Aware Denoising](https://mlsanity.com/paper/1906.00651/) (2019)
- [Interpretable Unsupervised Diversity Denoising and Artefact Removal](https://mlsanity.com/paper/2104.01374/) (2021)
- [DenoiSeg: Joint Denoising and Segmentation](https://mlsanity.com/paper/2005.02987/) (2020)
- [Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks](https://mlsanity.com/paper/1704.01510/) (2017)
- [Fully Unsupervised Probabilistic Noise2Void](https://mlsanity.com/paper/1911.12291/) (2019)
- [Cryo-CARE: Content-Aware Image Restoration for Cryo-Transmission Electron Microscopy Data](https://mlsanity.com/paper/1810.05420/) (2018)

## Built on by (most cited first, 7 of 7)

- [MicroSSIM: Improved Structural Similarity for Comparing Microscopy Data](https://mlsanity.com/paper/2408.08747/) (2024)
- [Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising](https://mlsanity.com/paper/2407.17399/) (2024)
- [Image Denoising and the Generative Accumulation of Photons](https://mlsanity.com/paper/2307.06607/) (2023)
- [bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction](https://mlsanity.com/paper/2410.23247/) (2024)
- [Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise](https://mlsanity.com/paper/2310.07887/) (2023)
- [GARD: Gamma-based Anatomical Restoration and Denoising for Retinal OCT](https://mlsanity.com/paper/2509.10341/) (2025)
- [RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics](https://mlsanity.com/paper/2510.06020/) (2025)

## Abstract (arXiv)

In recent years, neural network based image denoising approaches have revolutionized the analysis of biomedical microscopy data. Self-supervised methods, such as Noise2Void (N2V), are applicable to virtually all noisy datasets, even without dedicated training data being available. Arguably, this facilitated the fast and widespread adoption of N2V throughout the life sciences. Unfortunately, the blind-spot training underlying N2V can lead to rather visible checkerboard artifacts, thereby reducing the quality of final predictions considerably. In this work, we present two modifications to the vanilla N2V setup that both help to reduce the unwanted artifacts considerably. Firstly, we propose a modified network architecture, i.e., using BlurPool instead of MaxPool layers throughout the used U-Net, rolling back the residual U-Net to a non-residual U-Net, and eliminating the skip connections at the uppermost U-Net level. Additionally, we propose new replacement strategies to determine the pixel intensity values that fill in the elected blind-spot pixels. We validate our modifications on a range of microscopy and natural image data. Based on added synthetic noise from multiple noise types and at varying amplitudes, we show that both proposed modifications push the current state-of-the-art for fully self-supervised image denoising.