# Self-Supervised Poisson-Gaussian Denoising

arXiv: https://arxiv.org/abs/2002.09558 · HTML: https://mlsanity.com/paper/2002.09558/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift](https://mlsanity.com/paper/2203.09294/) (2022)
- [Complex-valued Retrievals From Noisy Images Using Diffusion Models](https://mlsanity.com/paper/2212.03235/) (2022)
- [Reinforcement Learning of Self Enhancing Camera Image and Signal Processing](https://mlsanity.com/paper/2111.07499/) (2021)
- [Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging](https://mlsanity.com/paper/2205.04821/) (2022)
- [Self-supervised conformal prediction for uncertainty quantification in Poisson imaging problems](https://mlsanity.com/paper/2502.19194/) (2025)
- [Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing](https://mlsanity.com/paper/2104.00253/) (2021)
- [Toward Accurate and Temporally Consistent Video Restoration from Raw Data](https://mlsanity.com/paper/2312.16247/) (2023)
- [Investigating Self-Supervised Image Denoising with Denaturation](https://mlsanity.com/paper/2405.01124/) (2024)
- [Vision without Images: End-to-End Computer Vision from Single Compressive Measurements](https://mlsanity.com/paper/2501.15122/) (2025)

## Abstract (arXiv)

We extend the blindspot model for self-supervised denoising to handle Poisson-Gaussian noise and introduce an improved training scheme that avoids hyperparameters and adapts the denoiser to the test data. Self-supervised models for denoising learn to denoise from only noisy data and do not require corresponding clean images, which are difficult or impossible to acquire in some application areas of interest such as low-light microscopy. We introduce a new training strategy to handle Poisson-Gaussian noise which is the standard noise model for microscope images. Our new strategy eliminates hyperparameters from the loss function, which is important in a self-supervised regime where no ground truth data is available to guide hyperparameter tuning. We show how our denoiser can be adapted to the test data to improve performance. Our evaluations on microscope image denoising benchmarks validate our approach.