Home

Awesome

SegStereo

Caffe implementation of SegStereo and ResNetCorr models.

Requirements

This code is tested with Caffe, CUDA 8.0 and Ubuntu 16.04.

Data

Our models require rectified stereo pairs. We provide several examples in data directory

Models

Evaluation

To test or evaluate the disparity model, you can use the script in model/get_disp.py. We recommend that you put the model under correponding directory.

python get_disp.py --model_weights ./ResNetCorr/ResNetCorr_SRC_pretrain.caffemodel --model_deploy ./ResNetCorr/ResNetCorr_deploy.prototxt --data ../data/KITTI --result ./ResNetCorr/result/kitti --gpu 0 --colorize --evaluate

Reference

@inproceedings{yang2018SegStereo,
  author    = {Yang, Guorun and
               Zhao, Hengshuang and
               Shi, Jianping and
               Deng, Zhidong and
               Jia, Jiaya},
  title     = {SegStereo: Exploiting Semantic Information for Disparity Estimation},
  booktitle = ECCV,
  year      = {2018}
}
@inproceedings{yang2018srcdisp,
  author    = {Yang, Guorun and
               Deng, Zhidong and
               Lu, Hongchao and
               Li, Zeping},
  title     = {SRC-Disp: Synthetic-Realistic Collaborative Disparity Learning for Stereo Mathcing},
  booktitle = ACCV,
  year      = {2018}
}

Questions

Please contact ygr13@mails.tsinghua.edu.cn