Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/khanovico/depthimage-single
depth estimation from monocular camera
https://github.com/khanovico/depthimage-single
deep-neural-network depth-estimation image-processing image-segmentation
Last synced: 2 months ago
JSON representation
depth estimation from monocular camera
- Host: GitHub
- URL: https://github.com/khanovico/depthimage-single
- Owner: khanovico
- License: mit
- Created: 2024-06-21T12:36:06.000Z (8 months ago)
- Default Branch: master
- Last Pushed: 2024-06-28T14:27:18.000Z (7 months ago)
- Last Synced: 2024-08-05T00:57:16.016Z (6 months ago)
- Topics: deep-neural-network, depth-estimation, image-processing, image-segmentation
- Language: Jupyter Notebook
- Homepage:
- Size: 4.11 MB
- Stars: 4
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Depth Image from Single Camera
MIT License
A simple end-to-end model that achieves state-of-the-art performance in depth prediction implemented in PyTorch. We used a Feature Pyramid Network (FPN) backbone to estimate depth map from a single input RGB image. We tested the performance of our model on the NYU Depth V2 Dataset (Official Split) and the KITTI Dataset (Eigen Split).
## Requirements
* Python 3
* Jupyter Notebook (for visualization)
* PyTorch
* Tested with PyTorch 0.3.0.post4
* CUDA 8 (if using CUDA)
## To Run
```
python3 main_fpn.py --cuda --bs 6
```
To continue training from a saved model, use
```
python3 main_fpn.py --cuda --bs 6 --r True --checkepoch 10
```
To visualize the reconstructed data, run the jupyter notebook in vis.ipynb.
## References
* Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multiscale
deep network. In: Advances in neural information processing systems (NIPS). (2014)
2366–2374
* Geiger, Andreas, et al. "Vision meets robotics: The KITTI dataset." The International Journal of Robotics Research 32.11 (2013): 1231-1237.
* C. Godard, O. Mac Aodha, and G. J. Brostow. Unsupervised monocular depth estimation with left-right consistency. arXiv:1609.03677v2, 2016.
* Hu, Junjie, et al. "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries." arXiv preprint arXiv:1803.08673 (2018).