https://github.com/dhruvsrikanth/monodepth
Monocular Depth Estimation via Transfer Learning using purely Tensorflow 2.0!
https://github.com/dhruvsrikanth/monodepth
autoencoder deep-learning depth-estimation machine-learning neural-networks python tensorflow tf2 transfer-learning
Last synced: 2 months ago
JSON representation
Monocular Depth Estimation via Transfer Learning using purely Tensorflow 2.0!
- Host: GitHub
- URL: https://github.com/dhruvsrikanth/monodepth
- Owner: DhruvSrikanth
- Created: 2020-11-21T11:30:18.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2021-12-17T07:54:28.000Z (over 4 years ago)
- Last Synced: 2025-04-23T22:13:53.011Z (about 1 year ago)
- Topics: autoencoder, deep-learning, depth-estimation, machine-learning, neural-networks, python, tensorflow, tf2, transfer-learning
- Language: Python
- Homepage:
- Size: 239 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MonoDepth - Monocular Depth Estimation via Transfer Learning (Tensorflow 2.0)
My take on implementing monocular depth estimation based off of the state-of-the-art technology currently being used. This is an implementation in tensorflow 2.0 of the following paper - [High Quality Monocular Depth Estimation via Transfer Learning](http://arxiv.org/abs/1812.11941), by Ibraheem Alhashim and Peter Wonka, in 2018.
The results were quite successful, although, very similar to what was achieved in the paper listed above. I was able to achieve an accuracy of 97%. The results can be seen within the source code directory. However, if you would like to see some more detailed results, please refer to the paper listed above. Enjoy!