Home

Awesome

Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior

teaser

General Information

For information please see the paper (paper website link):

Please cite our paper if you use any of the free material in this website:

@InProceedings{Jeonetal:CVPR:2018,
  author  = {Daniel S. Jeon and Seung-Hwan Baek and Inchang Choi
            and Min H. Kim},
  title   = {Enhancing the Spatial Resolution of Stereo Images
            using a Parallax Prior},
  booktitle = {Proc. IEEE Computer Vision and Pattern Recognition
            (CVPR 2018)},
  publisher = {IEEE},  
  address = {Salt Lake City, Utah, United States},
  year = {2018},
  pages = {},
  volume  = {},
}    

License Information

Requirements

We developed the codes on Ubuntu 14.04 (which was explicitly tested) but believe that our codes could be executed on other platforms of Ubuntu, Windows, and OSX as well. When using different versions of Python and Tensorflow, minor modifications, such as function names, in the codes would be necessary.

How to Execute Demo

We have written a demo code in demo_predict.py.

python demo_predict.py

You can change the scale parameter in demo_predict.py file. You also need to change model name corresponding to the scale. There are 2x, 3x and 4x models.

Training data

We trained our network with five middlebury stereo datasets except cloth2, motorcycle, piano, pipes, sword2, which are used for test.

Contacts

For questions, please send an email to sjjeon@vclab.kaist.ac.kr