PSMNet-Tensorflow

=======

PMSNet-Tensorflow

Pyramid Stereo Matching Network

根据 "Pyramid Stereo Matching Network" paper (CVPR 2018) 在源代码基础上使用tensorflow进行移植（源代码使用的pytorch）

Citation

@inproceedings{chang2018pyramid,
  title={Pyramid Stereo Matching Network},
  author={Chang, Jia-Ren and Chen, Yong-Sheng},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={5410--5418},
  year={2018}
}

Contents

1. Introduction
2. Usage
3. Results
4. Contacts

Introduction

Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in illposed regions. To tackle this problem, we propose PSMNet, a pyramid stereo matching network consisting of two main modules: spatial pyramid pooling and 3D CNN. The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume. The 3D CNN learns to regularize cost volume using stacked multiple hourglass networks in conjunction with intermediate supervision.

Usage

Dependencies

• Python3.6
• Tensorflow(1.3.0)
• PIL
• KITTI Stereo
• Scene Flow

目前已经完成的工作

• 移植了KITTI2012数据集的读取工作
• 移植了preprocess中的部分函数
• 移植了KITTILoader，满足基本的数据读取
• 在tensorflow框架下完成了CNN子模块
• 在tensorflow框架下完成了SPP子模块
• 在tensorflow框架下完成了CNN3D子模块（这里只重写了论文中提到的stacked hourglass结构）
• 在tensorflow框架下完成了视差回归和损失函数
• 对main函数进行改写，满足输入输出需求

接下来的的工作

• 完善整体的model
• 加入论文中basic的模型
• 加入模型的保存和读取模块
• 加入tensorboard可视化需要的操作
• 完善输入和输出
• 整体进行训练