# CSPN

**Repository Path**: itking666/CSPN

## Basic Information

- **Project Name**: CSPN
- **Description**: Convolutional Spatial Propagation Network
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2019-11-30
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Convolutional Spatial Propagation Network

By Xinjing Cheng, Peng Wang, Chenye Guan and Ruigang Yang

## Contents
0. [Introduction](#introduction)
0. [Citation](#citation)

## Introduction
This repo contains the CSPN models trained for depth completion and stereo depth estimation, as as described in the paper "[Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network](http://openaccess.thecvf.com/content_ECCV_2018/papers/Xinjing_Cheng_Depth_Estimation_via_ECCV_2018_paper.pdf)" and "[
Learning Depth with Convolutional Spatial Propagation Network](https://arxiv.org/abs/1810.02695)"

We provide two implementations here. First, we implement a naive 2D CSPN by Pytorch which combine 'offsite' and 'conv' operations. Then, we provide a more efficient implementation of 2D/3D CSPN by CUDA and integrated them to the PaddlePaddle, which is more stable and easy to use.

## Citation

If you use this method in your research, please cite:
```
@inproceedings{cheng2018depth,
  title={Depth estimation via affinity learned with convolutional spatial propagation network},
  author={Cheng, Xinjing and Wang, Peng and Yang, Ruigang},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={103--119},
  year={2018}
}
```

```
@article{cheng2018learning,
  title={Learning depth with convolutional spatial propagation network},
  author={Cheng, Xinjing and Wang, Peng and Yang, Ruigang},
  journal={arXiv preprint arXiv:1810.02695},
  year={2018}
}
```