https://github.com/matthewfilipovich/torchoptics
Differentiable wave optics simulation library built on PyTorch
https://github.com/matthewfilipovich/torchoptics
computational-optics deep-learning differentiable-optics diffraction fourier-optics holography imaging inverse-design machine-learning microscopy optical-neural-network optics physics pytorch wave-optics
Last synced: 7 months ago
JSON representation
Differentiable wave optics simulation library built on PyTorch
- Host: GitHub
- URL: https://github.com/matthewfilipovich/torchoptics
- Owner: MatthewFilipovich
- License: mit
- Created: 2024-11-27T22:32:02.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-08-17T22:12:09.000Z (10 months ago)
- Last Synced: 2025-09-05T07:42:33.020Z (9 months ago)
- Topics: computational-optics, deep-learning, differentiable-optics, diffraction, fourier-optics, holography, imaging, inverse-design, machine-learning, microscopy, optical-neural-network, optics, physics, pytorch, wave-optics
- Language: Python
- Homepage: https://torchoptics.readthedocs.io
- Size: 37.3 MB
- Stars: 74
- Watchers: 2
- Forks: 12
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
- awesome_photonics - TorchOptics
README
[](https://github.com/MatthewFilipovich/torchoptics/actions/workflows/build.yml)
[](https://codecov.io/gh/MatthewFilipovich/torchoptics)
[](https://torchoptics.readthedocs.io/en/latest/?badge=latest)
[](https://pypi.org/project/torchoptics/)
[](https://www.python.org/downloads/)
[](https://github.com/MatthewFilipovich/torchoptics/blob/main/LICENSE)
> TorchOptics is a differentiable wave optics simulation library built on PyTorch.
# Key Features
- 🌊 **Differentiable Wave Optics** — Model, analyze, and optimize optical systems using Fourier optics.
- 🔥 **Built on PyTorch** — GPU acceleration, batch processing, and automatic differentiation.
- 🛠️ **End-to-End Optimization** — Joint optimization of optical hardware and machine learning models.
- 🔬 **Optical Elements** — Lenses, modulators, detectors, polarizers, and more.
- 🖼️ **Spatial Profiles** — Hermite-Gaussian, Laguerre-Gaussian, Zernike modes, and others.
- 🔆 **Polarization and Coherence** — Simulate polarized light and fields with arbitrary spatial coherence.
Learn more about TorchOptics in our research paper on [arXiv](https://arxiv.org/abs/2411.18591).
# Installation
TorchOptics is available on [PyPI](https://pypi.org/project/torchoptics/) and can be installed with:
```bash
pip install torchoptics
```
## Documentation
Read the full documentation at [torchoptics.readthedocs.io](https://torchoptics.readthedocs.io/).
## Usage
[](https://colab.research.google.com/github/MatthewFilipovich/torchoptics/blob/main/docs/source/_static/torchoptics_colab.ipynb)
This example shows how to simulate a 4f imaging system using TorchOptics, computing and visualizing the field at each focal plane along the optical axis:
```python
import torch
import torchoptics
from torchoptics import Field, System
from torchoptics.elements import Lens
from torchoptics.profiles import checkerboard
# Set simulation properties
shape = 1000 # Number of grid points in each dimension
spacing = 10e-6 # Spacing between grid points (m)
wavelength = 700e-9 # Field wavelength (m)
focal_length = 200e-3 # Lens focal length (m)
tile_length = 400e-6 # Checkerboard tile length (m)
num_tiles = 15 # Number of tiles in each dimension
# Determine device
device = "cuda" if torch.cuda.is_available() else "cpu"
# Configure default properties
torchoptics.set_default_spacing(spacing)
torchoptics.set_default_wavelength(wavelength)
# Initialize input field with checkerboard pattern
field_data = checkerboard(shape, tile_length, num_tiles)
input_field = Field(field_data).to(device)
# Define 4f optical system with two lenses
system = System(
Lens(shape, focal_length, z=1 * focal_length),
Lens(shape, focal_length, z=3 * focal_length),
).to(device)
# Measure field at focal planes along the z-axis
measurements = [
system.measure_at_z(input_field, z=i * focal_length)
for i in range(5)
]
# Visualize the measured intensity distributions
for i, measurement in enumerate(measurements):
measurement.visualize(title=f"z={i}f", vmax=1)
```
Intensity distributions at different focal planes in the 4f system.
Propagation of the intensity distribution.
_For more examples and detailed usage, please refer to the [documentation](https://torchoptics.readthedocs.io/)._
## Contributing
We welcome contributions! See our [Contributing Guide](https://github.com/MatthewFilipovich/torchoptics/blob/main/CONTRIBUTING.md) for details.
## Citing TorchOptics
If you use TorchOptics in your research, please cite our [paper](https://arxiv.org/abs/2411.18591):
```bibtex
@misc{filipovich2024torchoptics,
title={TorchOptics: An open-source Python library for differentiable Fourier optics simulations},
author={Matthew J. Filipovich and A. I. Lvovsky},
year={2024},
eprint={2411.18591},
archivePrefix={arXiv},
primaryClass={physics.optics},
url={https://arxiv.org/abs/2411.18591},
}
```
## License
TorchOptics is distributed under the MIT License. See the [LICENSE](https://github.com/MatthewFilipovich/torchoptics/blob/main/LICENSE) file for more details.