Ibraheem Alhashim and Peter Wonka

Offical Keras (TensorFlow) implementaiton. If you have any questions or need more help with the code, feel free to contact the first author.

• KITTI

• NYU Depth V2

• This code is tested with Keras 2.2.4, Tensorflow 1.13, CUDA 9.0, on a machine with an NVIDIA Titan V and 16GB+ RAM running on Windows 10 or Ubuntu 16.
• Other packages needed keras pillow matplotlib scikit-learn scikit-image opencv-python pydot and GraphViz.
• Training takes about 20 hours with 4 NVIDIA Titan Xp (or above).

• NYU Depth V2 (165 MB)
• KITTI (165 MB)

• After downloading the pre-trained model (nyu.h5), run python test.py. You should see a montage of images with their estimated depth maps.

• NYU Depth V2 (50K) (4.1 GB): You don't need to extract the dataset since the code loads the entire zip file into memory when training.
• KITTI: copy the raw data to a folder with the path '../kitti'. Our method expects dense input depth maps, therefore, you need to run a depth inpainting method on the Lidar data. For our experiments, we used our Python re-implmentaiton of the Matlab code provided with NYU Depth V2 toolbox. The entire 80K images took 2 hours on an 80 nodes cluster for inpainting. For our training, we used the subset defined here.
• Unreal-1k: coming soon.

• Run python train.py --data nyu --gpus 4 --bs 8.

• Download, but don't extract, the ground truth test data from here (1.4 GB). Then simply run python evaluate.py.

Corresponding paper to cite:

@article{Alhashim2018,
  author    = {Ibraheem Alhashim and Peter Wonka},
  title     = {High Quality Monocular Depth Estimation via Transfer Learning},
  journal   = {arXiv e-prints},
  volume    = {abs/1812.11941},
  year      = {2018},
  url       = {https://arxiv.org/abs/1812.11941},
  eid       = {arXiv:1812.11941},
  eprint    = {1812.11941}
}