• Stars
    star
    188
  • Rank 205,563 (Top 5 %)
  • Language
    C++
  • License
    GNU General Publi...
  • Created almost 6 years ago
  • Updated over 5 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Direct Sparse Odometry with CNN Depth Prediction

CNN-DSO: A combination of Direct Sparse Odometry and CNN Depth Prediction

1. Overview

This code provides a combination of DSO and Monodepth. For every keyframe, depth values are initialized with the prediction from Monodepth.

Absolute keyframe trajectory RMSE (in meter) on KITTI dataset (DSO and ORB-SLAM numbers are from CNN-SVO paper)

Sequence on KITTI CNN-DSO DSO ORB-SLAM
00 15.13 113.18 77.95
01 5.901 X X
02 12.53 116.81 41.00
03 1.516 1.3943 1.018
04 0.100 0.422 0.930
05 20.3 47.46 40.35
06 1.547 55.61 52.22
07 8.369 16.71 16.54
08 10.53 111.08 51.62
09 14.00 52.22 58.17
10 4.10 11.09 18.47

2. Installation

2.1 Dependencies

DSO
Monodepth

2.3 Build

  • Download the repository.

      git clone https://github.com/muskie82/CNN-DSO.git
    
  • Modify paths to include directories and libraries of TensorFlow and monodepth-cpp in CMakeLists.txt (4 lines of /abosolute/path/to/XXXXX).

  • Build

      cd CNN-DSO
      mkdir build
      cd build
      cmake ..
      make -j4
    

3 Usage

In addition to original DSO command line, you should specify the path to pre-trained model by cnn.

	bin/dso_dataset \
		files=XXXXX/sequence_XX/image_0 \
		calib=XXXXX/sequence_XX/camera.txt \
		cnn=XXXXX/model_city2kitti.pb \
		preset=0 \
		mode=1

4 Reference

5 License

GPLv3 license. I don't take any credit from DSO, Monodepth and monodepth-cpp. Please check them.