Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/facebookresearch/meshrcnn
code for Mesh R-CNN, ICCV 2019
https://github.com/facebookresearch/meshrcnn
Last synced: about 1 month ago
JSON representation
code for Mesh R-CNN, ICCV 2019
- Host: GitHub
- URL: https://github.com/facebookresearch/meshrcnn
- Owner: facebookresearch
- License: other
- Created: 2020-01-07T23:40:23.000Z (almost 5 years ago)
- Default Branch: main
- Last Pushed: 2024-06-06T18:27:21.000Z (5 months ago)
- Last Synced: 2024-09-26T21:43:50.440Z (about 2 months ago)
- Language: Python
- Homepage:
- Size: 155 KB
- Stars: 1,130
- Watchers: 42
- Forks: 173
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# Mesh R-CNN
Code for the paper
**[Mesh R-CNN][1]**
[Georgia Gkioxari][gg], Jitendra Malik, [Justin Johnson][jj]
ICCV 2019
[](https://colab.research.google.com/drive/1eQLZrNYRZMo9zdnGGccE0hFswGiinO-Z?usp=sharing)
(thanks to [Alberto Tono][at]!)
## Installation Requirements
- [Detectron2][d2]
- [PyTorch3D][py3d]
The implementation of Mesh R-CNN is based on [Detectron2][d2] and [PyTorch3D][py3d].
You will first need to install those in order to be able to run Mesh R-CNN.
To install
```
git clone https://github.com/facebookresearch/meshrcnn.git
cd meshrcnn && pip install -e .
```
## Demo
Run Mesh R-CNN on an input image
```
python demo/demo.py \
--config-file configs/pix3d/meshrcnn_R50_FPN.yaml \
--input /path/to/image \
--output output_demo \
--onlyhighest MODEL.WEIGHTS meshrcnn://meshrcnn_R50.pth
```
See [demo.py](demo/demo.py) for more details.
## Running Experiments
### Pix3D
See [INSTRUCTIONS_PIX3D.md](INSTRUCTIONS_PIX3D.md) for more instructions.
### ShapeNet
See [INSTRUCTIONS_SHAPENET.md](INSTRUCTIONS_SHAPENET.md) for more instructions.
## License
The Mesh R-CNN codebase is released under [BSD-3-Clause License](LICENSE)
[1]: https://arxiv.org/abs/1906.02739
[gg]: https://github.com/gkioxari
[jj]: https://github.com/jcjohnson
[d2]: https://github.com/facebookresearch/detectron2
[py3d]: https://github.com/facebookresearch/pytorch3d
[at]: https://github.com/albertotono