Skip to content
Depth from Uncalibrated Small Motion Clip
C++ C CMake
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Dataset Synthetic datasets uploaded Jul 12, 2017
Result Delete LICENSE~ Jun 23, 2016
Yang_cvpr12 Delete .DS_Store Jun 25, 2016
CMakeLists.txt Initial commit Jun 24, 2016
DfUSMC.cpp Bug fix Jul 13, 2017
DfUSMC.hpp Update DfUSMC.hpp Jun 25, 2016
LICENSE Initial commit Jun 23, 2016
README.md Update README.md Mar 16, 2017
main.cpp Update main.cpp Jun 25, 2016

README.md

DfUSMC

(DfUSMC: Depth from Uncalibrated Small Motion Clip)

Source code and datasets for the paper:

H. Ha, S. Im, J. Park, H.-G. Jeon and I.S. Kweon, High-quality Depth from Uncalibrated Small Motion Clip, CVPR 2016

Dependencies

How to Run

  1. Put your small motion clip in "Dataset" folder
  2. Run (with sudo)
cmake .
make
./DfUSMC data_name video_extension
(for example, ./DfUSMC Bikes avi)

Important Information

Frame selection

The current implementation uses only the first 30 frames of your video clip. If you want to try with a different number of images or different sampling rate, please modify the "LoadSmallMotionClip" function.

Dense matching step

We implemented the function "DenseMatching" to receive a scale for image downsampling and the number of labels for your convenience in testing. (Default: 0.5 scale and 64 labels for quick tests, but please remind that 1.0 and 256 were used in the paper)

For the depth refinement, we utilized a tree-based depth upsampling approach [1,2].

Authors

© 2016 Hyowon Ha, Korea Advanced Institute of Science and Technology (KAIST)

IMPORTANT: If you use this software please cite the following in any resulting publication:

@inproceedings{ha2016high,
  title={High-quality Depth from Uncalibrated Small Motion Clip},
  author={Ha, Hyowon and Im, Sunghoon and Park, Jaesik and Jeon, Hae-Gon and Kweon, In So},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016}
}

References

  1. Yang, Qingxiong. "Stereo matching using tree filtering." IEEE transactions on pattern analysis and machine intelligence 37.4 (2015): 834-846.
  2. Yang, Qingxiong. "A non-local cost aggregation method for stereo matching." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012.
You can’t perform that action at this time.