# Improving Blind Spot Denoising for Microscopy

arXiv: https://arxiv.org/abs/2008.08414 · HTML: https://mlsanity.com/paper/2008.08414/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

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

- [Interpretable Unsupervised Diversity Denoising and Artefact Removal](https://mlsanity.com/paper/2104.01374/) (2021)
- [μSplit: efficient image decomposition for microscopy data](https://mlsanity.com/paper/2211.12872/) (2022)
- [Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising](https://mlsanity.com/paper/2407.17399/) (2024)
- [Joint self-supervised blind denoising and noise estimation](https://mlsanity.com/paper/2102.08023/) (2021)
- [Semi- and Self-Supervised Multi-View Fusion of 3D Microscopy Images using Generative Adversarial Networks](https://mlsanity.com/paper/2108.02743/) (2021)
- [DeepContrast: Deep Tissue Contrast Enhancement using Synthetic Data Degradations and OOD Model Predictions](https://mlsanity.com/paper/2308.08365/) (2023)
- [Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising](https://mlsanity.com/paper/2606.23098/) (2026)

## Abstract (arXiv)

Many microscopy applications are limited by the total amount of usable light and are consequently challenged by the resulting levels of noise in the acquired images. This problem is often addressed via (supervised) deep learning based denoising. Recently, by making assumptions about the noise statistics, self-supervised methods have emerged. Such methods are trained directly on the images that are to be denoised and do not require additional paired training data. While achieving remarkable results, self-supervised methods can produce high-frequency artifacts and achieve inferior results compared to supervised approaches. Here we present a novel way to improve the quality of self-supervised denoising. Considering that light microscopy images are usually diffraction-limited, we propose to include this knowledge in the denoising process. We assume the clean image to be the result of a convolution with a point spread function (PSF) and explicitly include this operation at the end of our neural network. As a consequence, we are able to eliminate high-frequency artifacts and achieve self-supervised results that are very close to the ones achieved with traditional supervised methods.