Home

Awesome

Single View Stereo Matching

<img src="figs/result.png" width="1200" height="250" />

This repo includes the source code of the paper: "Single View Stereo Matching" (CVPR'18 Spotlight) by Yue Luo*, Jimmy Ren*, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin.

Contact: Yue Luo (lawy623@gmail.com)

Prerequisites

The code is tested on 64 bit Linux (Ubuntu 14.04 LTS). You should also install Matlab (We have tested on R2015a). We have tested our code on GTX TitanX with CUDA8.0+cuDNNv5. Please install all these prerequisites before running our code.

Installation

  1. Get the code.

    git clone https://github.com/lawy623/SVS.git
    cd SVS
    
  2. Build the code. Please follow Caffe instruction to install all necessary packages and build it.

    cd caffe/
    # Modify Makefile.config according to your Caffe installation/. Remember to allow CUDA and CUDNN.
    make -j8
    make matcaffe
    
  3. Prepare data. We write all data and labels into .mat files.

Training

View Synthesis Network

   ## To run the training matlab scripts from terminal
   sh prototxt/viewSynthesis/train_ViewSyn.sh   #To trained the view synthesis network

Stereo Matching Network

Single View Stereo Matching - End-to-end finetune.

   ## To run the training matlab scripts from terminal
   sh prototxt/svs/train_svs.sh   #To trained the svs network

Testing

Results

<img src="figs/1.jpg" width="1000" height="1000" /> <img src="figs/2.jpg" width="1000" height="1000" /> <img src="figs/3.jpg" width="1000" height="1000" />

Citation

Please cite our paper if you find it useful for your work:

@InProceedings{Luo2018SVS,
    title={Single View Stereo Matching},
    author={Yue Luo, Jimmy Ren, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin},
    booktitle ={CVPR},
    year={2018},
}