Skip to content
master
Switch branches/tags
Code

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
Mar 8, 2019
doc
.
May 21, 2020
fig
Feb 18, 2021
Dec 25, 2019
Mar 8, 2019
Mar 8, 2019
Nov 23, 2018
Mar 8, 2019

Stereo Matching in O(1) with Slanted Support Windows

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018

ActiveStereoNet:End-to-End Self-Supervised Learning for Active Stereo Systems ECCV2018 Oral

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

If you want to communicate with me about the StereoNet, please concact me without hesitating. My email:

xuanyili.edu@gmail.com

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018

StereoNet Introduction

I implement the real-time stereo model according to the StereoNet model in pytorch.

Method EPE_all on sceneflow dataset EPE_all on kitti2012 dataset EPE_all on kitti2015 dataset
ours(8X single) stage0:2.26 stage1:1.38
Reference[1] stage1: 1.525

my model result

Now, my model's speed can achieve 25 FPS on 540*960 img with the best result of 1.87 EPE_all with 16X multi model, 1.95 EPE_all with 16X single model on sceneflow dataset by end-to-end training. the following are the side outputs and the prediction example

train example

train example

test example

test example

test example real time version submission

point cloud view example

test example

ActiveStereoNet:End-to-End Self-Supervised Learning for Active Stereo Systems ECCV2018 Oral

ActiveStereoNet model disparity vis result

test example

ActiveStereoNet model surface normal vis result

test example

plane fit mertric result

ActiveStereoNet youtube video demo

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

Method EPE_all on sceneflow dataset Bad3 on kitti2015 dataset
ours 0.70 2.43
Reference 0.53 1.98

Citation

  • refercence[1]

If you find our work useful in your research, please consider citing:

@inproceedings{khamis2018stereonet, title={Stereonet: Guided hierarchical refinement for real-time edge-aware depth prediction}, author={Khamis, Sameh and Fanello, Sean and Rhemann, Christoph and Kowdle, Adarsh and Valentin, Julien and Izadi, Shahram}, booktitle={Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany}, pages={8--14}, year={2018} }

License

  • Our code is released under MIT License (see LICENSE file for details).

Installaton

  • python3.6
  • pytorch0.4

Usage

  • run main8Xmulti.py

Updates

  • finetune the performance beating the original paper.

rethink

  • Do not design massive deep networks with multiple stages to improve kitti by 1%(no meaning doing this)
  • Use metrics that matter for visual navigation (hint: not L1 depth error)
  • ...

pretrain model

StereoNet pretrain model(pytorch version)

ActiveStereoNet pretrain model(pytorch version)

ActiveStereoNet pretrain model(tensorflow version)

Citation

  • refercence[1] @article{tankovich2020hitnet, title={HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching}, author={Tankovich, Vladimir and H{"a}ne, Christian and Fanello, Sean and Zhang, Yinda and Izadi, Shahram and Bouaziz, Sofien}, journal={arXiv preprint arXiv:2007.12140}, year={2020} }

  • refercence[2] @inproceedings{tankovich2018sos, title={Sos: Stereo matching in o (1) with slanted support windows}, author={Tankovich, Vladimir and Schoenberg, Michael and Fanello, Sean Ryan and Kowdle, Adarsh and Rhemann, Christoph and Dzitsiuk, Maksym and Schmidt, Mirko and Valentin, Julien and Izadi, Shahram}, booktitle={2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, pages={6782--6789}, year={2018}, organization={IEEE} }

  • refercence[3] @inproceedings{fanello2017low, title={Low compute and fully parallel computer vision with hashmatch}, author={Fanello, Sean Ryan and Valentin, Julien and Kowdle, Adarsh and Rhemann, Christoph and Tankovich, Vladimir and Ciliberto, Carlo and Davidson, Philip and Izadi, Shahram}, booktitle={2017 IEEE International Conference on Computer Vision (ICCV)}, pages={3894--3903}, year={2017}, organization={IEEE} }

Thanks

About

SOS IROS 2018 GOOGLE; StereoNet ECCV2018 GOOGLE; ActiveStereoNet ECCV2018 Oral GOOGLE; HITNET CVPR2021 GOOGLE

Topics

Resources

License

Releases

No releases published

Packages

No packages published

Languages