Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Code for "DeepDRR: A Catalyst for Machine Learning in Fluoroscopy-guided Procedures". https://arxiv.org/abs/1803.08606
| Date | Stars |
|---|---|
| 2026-07-25 | 277 |
| 2026-07-28 | 277 |
| 2026-07-30 | 277 |
| 2026-07-31 | 277 |
| 2026-08-06 | 278 |
Today
+1 stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.36%/day
<div align="center">
# DeepDRR
<a href="https://arxiv.org/abs/1803.08606">
<img src="http://img.shields.io/badge/paper-arxiv.1803.08606-B31B1B.svg" alt="Paper" />
</a>
<a href="https://pepy.tech/project/deepdrr">
<img src="https://pepy.tech/badge/deepdrr/month" alt="Downloads" />
</a>
<a href="https://github.com/arcadelab/deepdrr/releases/">
<img src="https://img.shields.io/github/release/arcadelab/deepdrr.svg" alt="GitHub release" />
</a>
<a href="https://pypi.org/project/deepdrr/">
<img src="https://img.shields.io/pypi/v/deepdrr" alt="PyPI" />
</a>
<a href="http://deepdrr.readthedocs.io/?badge=latest">
<img src="https://readthedocs.org/projects/deepdrr/badge/?version=latest" alt="Documentation Status" />
</a>
<a href="https://github.com/psf/black">
<img src="https://img.shields.io/badge/code%20style-black-000000.svg" alt="Code style: black" />
</a>
<a href="https://colab.research.google.com/github/arcadelab/deepdrr/blob/main/deepdrr_demo.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab" />
</a>
</div>
DeepDRR is a GPU-based framework for efficient simulation of X-ray images—or digitally reconstructed radiographs (DRRs)—from 3D CT images and meshes. It is intended for large-scale generation of synthetic X-ray datasets for training machine learning models.
DeepDRR has been used for a variety of applications, including:
- Voice control of robotic X-ray devices [here](https://link.springer.com/article/10.1007/s11548-025-03351-y) and [here](https://link.springer.com/article/10.1007/s11548-024-03120-3).
- [Sim-to-real learning in X-ray guided procedures](https://www.nature.com/articles/s42256-023-00629-1).
- [Foundation models for X-ray image segmentation](https://arxiv.org/abs/2403.08059).
- [Virtual reality simulation of X-ray guided procedures](https://link.springer.com/article/10.1007/s11548-024-03138-7).
- [Augmented reality visualization and control of robotic C-arms](https://doi.org/10.1080/21681163.2022.2154272)
- [Automated standard view acquisition in orthopedic surgery](https://link.springer.com/article/10.1007/s11548-020-02204-0).
- [Autonomous image acquisition and interpretation for AR-assisted pelvic trauma surgery](https://link.springer.com/article/10.1007/s11548-023-02941-y)
- 2D/3D X-ray Image Registration with [CT images](https://doi.org/10.1109/TMI.2021.3073815) and [atlases](https://link.springer.com/article/10.1007/s11548-022-02586-3).
- [Biplanar CT reconstruction](https://link.springer.com/chapter/10.1007/978-3-031-43999-5_66)
- [Closed-loop control of a surgical robot using fluoroscopic navigation](https://doi.org/10.1109/TBME.2021.3097631)
- [Surgical phase recognition in X-ray guided pelvic trauma surgery](https://link.springer.com/chapter/10.1007/978-3-031-43996-4_13)
- [Instrument pose estimation in X-ray images](https://link.springer.com/article/10.1007/s11548-020-02157-4).
If you have other appplications that could be highlighted here, please let us know!
DeepDRR is not a differentiable renderer, but it is fast and realistic, supporting multiple overlapping volumes and meshes with different materials. For a differentiable DRR framework, we recommend [ProST](https://github.com/gaocong13/Projective-Spatial-Transformers) or [DiffDRR](https://github.com/gaocong13/Projective-Spatial-Transformers), which follow the same physics-based simulation principles as DeepDRR.
## Usage
The following example loads a CT volume from a NifTi `.nii.gz` file and simulates a single X-ray projection:
```python
from deepdrr import Volume, SimpleDevice, Projector
import killeengeo as kg
device = SimpleDevice()
ct = Volume.from_nifti('/path/to/ct_image.nii.gz')
with Projector(ct, device=device) as projector:
device.set_view(
point=ct.center_in_world,
direction=ct.world_from_anatomical @ kg.vector(0, 1, 0),
up=ct.world_from_anatomical @ kg.vector(0, 0, 1),
source_to_point_fraction=0.5,
)
image = projector()
```
A more invoExcerpt of 18,434 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bdebd882b29c6177, topic:pytorch
matched fp:bdebd882b29c6177, topic:simulation