#### NOTE
New to DeepInverse? Get started with the basics with the
[5 minute quickstart tutorial](https://deepinv.org/auto_examples/basics/demo_quickstart.html.md#sphx-glr-auto-examples-basics-demo-quickstart-py)..
# Poisson denoising using Poisson2Sparse
This code shows how to restore a single image corrupted by Poisson noise using Poisson2Sparse, without requiring external training or knowledge of the noise level.
This method is based on the paper “Poisson2Sparse” Ta *et al.*[1](#footcite-ta2022poisson2sparse) and restores an image by learning a sparse non-linear dictionary parametrized by a neural network using a combination of Neighbor2Neighbor Huang *et al.*[2](#footcite-huang2021neighbor2neighbor), of the negative log Poisson likelihood, of the $\ell^1$ pixel distance and of a sparsity-inducing $\ell^1$ regularization function on the weights.
```Python
import deepinv as dinv
import torch
```
## Load a Poisson corrupted image
This example uses an image from the microscopy dataset FMD Zhang *et al.*[3](#footcite-zhang2018poisson).
```Python
# Seed the RNGs for reproducibility
torch.manual_seed(0)
torch.cuda.manual_seed(0)
device = dinv.utils.get_device()
physics = dinv.physics.Denoising(dinv.physics.PoissonNoise(gain=0.01, normalize=True))
x = dinv.utils.demo.load_example(
"FMD_TwoPhoton_MICE_R_gt_12_avg50.png", img_size=(256, 256)
).to(device)
x = x[:, 0:1, :64, :64]
x = x.clamp(0, 1)
y = physics(x)
```
```none
Selected GPU 0 with 22455.25 MiB free memory
```
Define the Poisson2Sparse model
```Python
backbone = dinv.models.ConvLista(
in_channels=1,
out_channels=1,
kernel_size=3,
num_filters=512,
num_iter=10,
stride=2,
threshold=0.01,
)
model = dinv.models.Poisson2Sparse(
backbone=backbone,
lr=1e-4,
num_iter=200,
weight_n2n=2.0,
weight_l1_regularization=1e-5,
verbose=True,
).to(device)
```
## Run the model
Note that we do not pass in the physics model as Poisson2Sparse assumes a
Poisson noise model internally and does not depend on the noise level.
```Python
x_hat = model(y)
# Compute and display PSNR values
learning_free_psnr = dinv.metric.PSNR()(y, x).item()
model_psnr = dinv.metric.PSNR()(x_hat, x).item()
print(f"Measurement PSNR: {learning_free_psnr:.1f} dB")
print(f"Poisson2Sparse PSNR: {model_psnr:.1f} dB")
# Plot results
dinv.utils.plot(
[y, x_hat, x],
titles=["Measurement", "Poisson2Sparse", "Ground truth"],
subtitles=[f"{learning_free_psnr:.1f} dB", f"{model_psnr:.1f} dB", ""],
)
```
```none
0%| | 0/200 [00:00
* **References:**
* Calvin-Khang Ta, Abhishek Aich, Akash Gupta, and Amit K Roy-Chowdhury. Poisson2sparse: self-supervised poisson denoising from a single image. In *International Conference on Medical Image Computing and Computer-Assisted Intervention*, 557–567. Springer, 2022.
* Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, and Jianzhuang Liu. Neighbor2neighbor: self-supervised denoising from single noisy images. In *Proceedings of the IEEE/CVF conference on computer vision and pattern recognition*, 14781–14790. 2021.
* Yide Zhang, Yinhao Zhu, Evan Nichols, Qingfei Wang, Siyuan Zhang, Cody Smith, and Scott Howard. A poisson-gaussian denoising dataset with real fluorescence microscopy images. In *CVPR*. 2019.
**Total running time of the script:** (0 minutes 1.395 seconds)
🏷 Tags: Denoising
[`Download Jupyter notebook: demo_poisson2sparse.ipynb`](https://deepinv.org/auto_examples/self-supervised-learning/_downloads/e391e3e6e17d82d10dcf1de37f61019c/demo_poisson2sparse.ipynb)
[`Download Python source code: demo_poisson2sparse.py`](https://deepinv.org/auto_examples/self-supervised-learning/_downloads/86cf8d00a5166eeb264d55058eb8acc7/demo_poisson2sparse.py)
[`Download zipped: demo_poisson2sparse.zip`](https://deepinv.org/auto_examples/self-supervised-learning/_downloads/cd3f36cfd1f454e564bccda15c633ace/demo_poisson2sparse.zip)
[Gallery generated by Sphinx-Gallery](https://sphinx-gallery.github.io)