# Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image

arXiv: https://arxiv.org/abs/2206.01856 · HTML: https://mlsanity.com/paper/2206.01856/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 4 Jun 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images](https://mlsanity.com/paper/1812.10366/) (2018)
- [Rethinking the CSC Model for Natural Images](https://mlsanity.com/paper/1909.05742/) (2019)
- [Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imaging](https://mlsanity.com/paper/2106.12175/) (2021)
- [Non-Adversarial Video Synthesis with Learned Priors](https://mlsanity.com/paper/2003.09565/) (2020)
- [Sparsity Based Poisson Denoising with Dictionary Learning](https://mlsanity.com/paper/1309.4306/) (2013)
- [Deep Quantized Representation for Enhanced Reconstruction](https://mlsanity.com/paper/2107.14368/) (2021)

## Built on by (most cited first, 2 of 2)

- [Domino Denoise: An Accurate Blind Zero-Shot Denoiser using Domino Tilings](https://mlsanity.com/paper/2212.02439/) (2022)
- [Investigating Self-Supervised Image Denoising with Denaturation](https://mlsanity.com/paper/2405.01124/) (2024)

## Abstract (arXiv)

Image enhancement approaches often assume that the noise is signal independent, and approximate the degradation model as zero-mean additive Gaussian. However, this assumption does not hold for biomedical imaging systems where sensor-based sources of noise are proportional to signal strengths, and the noise is better represented as a Poisson process. In this work, we explore a sparsity and dictionary learning-based approach and present a novel self-supervised learning method for single-image denoising where the noise is approximated as a Poisson process, requiring no clean ground-truth data. Specifically, we approximate traditional iterative optimization algorithms for image denoising with a recurrent neural network that enforces sparsity with respect to the weights of the network. Since the sparse representations are based on the underlying image, it is able to suppress the spurious components (noise) in the image patches, thereby introducing implicit regularization for denoising tasks through the network structure. Experiments on two bio-imaging datasets demonstrate that our method outperforms the state-of-the-art approaches in terms of PSNR and SSIM. Our qualitative results demonstrate that, in addition to higher performance on standard quantitative metrics, we are able to recover much more subtle details than other compared approaches. Our code is made publicly available at https://github.com/tacalvin/Poisson2Sparse