# DispNet_Keras

**Repository Path**: hankersyan/DispNet_Keras

## Basic Information

- **Project Name**: DispNet_Keras
- **Description**: No description available
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-04-10
- **Last Updated**: 2024-04-15

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# DispNet_Keras
Implementation of DispNet in Keras

The method is suggested by Nikolaus Mayer et al.. Here is the DispNet paper: 
<a href="https://arxiv.org/abs/1512.02134">https://arxiv.org/abs/1512.02134</a>

Download the dataset from the link below: 

<a href="https://github.com/LouisFoucard/DepthMap_dataset">DepthMap_dataset</a>

Sample stereo images:

<img src="images/Stereoimages.png" alt="input images" class="inline" width="450" height="150"/>

Ground truth:

<img src="images/gt.png" alt="gt" class="inline" width="320" height="238" />

Here is the prediction after 200 epochs:

<img src="images/dispnet_predict.png" alt="predicted result" class="inline" width="320" height="298" />