Skip to content
SegStereo: Exploiting Semantic Information for Disparity Estimation
C++ Python Cuda CMake MATLAB Makefile Other
Branch: master
Clone or download
yangguorun
Latest commit 717f590 Jan 28, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.github SegStereo and ResNetCorr code Nov 30, 2018
cmake
data Update README and add data examples Dec 3, 2018
docker SegStereo and ResNetCorr code Nov 30, 2018
docs SegStereo and ResNetCorr code Nov 30, 2018
examples SegStereo and ResNetCorr code Nov 30, 2018
include/caffe SegStereo and ResNetCorr code Nov 30, 2018
matlab SegStereo and ResNetCorr code Nov 30, 2018
models Add get_disp script and KITTI finetuned models Jan 28, 2019
python SegStereo and ResNetCorr code Nov 30, 2018
scripts SegStereo and ResNetCorr code Nov 30, 2018
src SegStereo and ResNetCorr code Nov 30, 2018
tools SegStereo and ResNetCorr code Nov 30, 2018
.Doxyfile SegStereo and ResNetCorr code Nov 30, 2018
.gitignore SegStereo and ResNetCorr code Nov 30, 2018
.travis.yml SegStereo and ResNetCorr code Nov 30, 2018
CMakeLists.txt SegStereo and ResNetCorr code Nov 30, 2018
CONTRIBUTING.md SegStereo and ResNetCorr code Nov 30, 2018
CONTRIBUTORS.md SegStereo and ResNetCorr code Nov 30, 2018
INSTALL.md
LICENSE SegStereo and ResNetCorr code Nov 30, 2018
Makefile SegStereo and ResNetCorr code Nov 30, 2018
Makefile.config.example SegStereo and ResNetCorr code Nov 30, 2018
README.md Add get_disp script and KITTI finetuned models Jan 28, 2019
caffe.cloc SegStereo and ResNetCorr code Nov 30, 2018

README.md

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

  • ResNetCorr_SRC_pretrain.caffemodel: Google Drive
  • SegStereo_SRC_pretrain.caffemodel: Google Drive
  • SegStereo_pre_corr_SRC_pretrain.caffemodel: Google Drive
  • ResNetCorr_KITTI_finetune.caffemodel: Google Drive
  • SegStereo_KITTI_finetune.caffemodel: Google Drive
  • SegStereo_pre_corr_KITTI_finetune.caffemodel: Google Drive

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

  • If our SegStereo or ResNetCorr models help your research, please consider citing:
@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}
}
  • If you find our synthetic realistic collaborative (SRC) training strategy useful, please consider citing:
@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

You can’t perform that action at this time.