DfUSMC

(DfUSMC: Depth from Uncalibrated Small Motion Clip)

Source code and dataset 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

• Project page

Dependencies

• OpenCV
• Ceres solver

How to Run

1. Put your small motion clip in "Dataset" folder
2. Open main.cpp
3. Change "data_name" and "video_format" accordingly.
4. Run

cmake .
sudo make
./DfUSMC

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 this function.

Dense matching step

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

Authors

• Hyowon Ha
• Sunghoon Im
• Jaesik Park
• Hae-Gon Jeon
• In So Kweon

© 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}
}