This codebase (in progress) implements the system described in the paper:
Unsupervised Learning of Depth and Ego-Motion from Video
Tinghui Zhou, Matthew Brown, Noah Snavely, David G. Lowe
In CVPR 2017 (Oral).
See the project webpage for more details. Please contact Tinghui Zhou (tinghuiz@berkeley.edu) if you have any questions.
This codebase was developed and tested with Tensorflow 1.0, CUDA 8.0 and Ubuntu 16.04.
We provide the demo code for running our single-view depth prediction model. First, download the pre-trained model by running the following
bash ./models/download_model.shThen you can use the provided ipython-notebook demo.ipynb to run the demo.
- Full training code for Cityscapes and KITTI.
- Evaluation code for the KITTI experiments.
This is the authors' implementation of the system described in the paper and not an official Google product.