Keras code of "Fast Disparity Estimation using Dense Networks" paper at the International Conference on Robotics and Automation, Australia, 2018 (ICRA 2018)

DenseMapNet Features

• Predicts disparity map using full resolution stereo RGB
• Fast at >=30Hz on NVIDIA 1080Ti GPU
• Tiny network with only 290k parameters
• Accurate with Low End-Point-Error or EPE

Download datasets:

1. driving
2. mpi

Copy: cp driving.tar.bz2 densemapnet/dataset

Change dir and extract: cd densemanpnet/dataset; tar jxvf driving.tar.bz2

Available datasets:

1. driving - Driving
2. mpi - MPI Sintel

Additional datasets will be available in the future.

In some datasets, the train data is split into multiple files. For example, driving is split into 4 files while mpi fits into 1 file.

To train the network:

python3 predictor.py --dataset=driving --num_dataset=4

Alterntaively, load the pre-trained weigths:

python3 predictor.py --dataset=driving --num_dataset=4 --weights=checkpoint/driving.densemapnet.weights.h5

To measure EPE using test set:

python3 predictor.py --dataset=driving --num_dataset=4 --weights=checkpoint/driving.densemapnet.weights.h5 --notrain

To benchmark speed only:

python3 predictor.py --dataset=driving --num_dataset=4 --weights=checkpoint/driving.densemapnet.weights.h5 --predict

To generate disparity predictions on both train and test datasets (complete sequential images used to create the video):

python3 predictor.py --dataset=driving --num_dataset=4 --weights=checkpoint/driving.densemapnet.weights.h5 --predict --images

If you find this work useful, please cite:

@conference{Atienza18,
  title = {Fast Disparity Estimation using Dense Networks},
  author = {Atienza, Rowel},
  booktitle = {Proceedings 2018 IEEE International Conference on Robotics and Automation (ICRA)},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = May,
  year = {2018},
  month_numeric = {5}
}