Metadata-Version: 2.1
Name: dungeon-maps
Version: 0.0.2a0
Summary: A tiny PyTorch library for depth map manipulations
Home-page: https://github.com/Ending2015a/dungeon_map
Author: JoeHsiao
Author-email: joehsiao@gapp.nthu.edu.tw
License: MIT
Keywords: deep learning,computer vision,machine learning,robotics,depth map,point cloud,orthographic projection
Platform: UNKNOWN
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Provides-Extra: sim
License-File: LICENSE

# Dungeon Maps
A tiny PyTorch library for depth map manipulations.

Version: `0.0.2a0`

## Features

| | Batching | Multi-channels | GPU acceleration |
|:-:|:-:|:-:|:-:|
| Orthographic projection<br>(Top-down map) |:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|
| Egocentric motion flow |:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|
| 3D affine transformation<br>(Camera space) |:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|
| 2D affine transformation<br>(Top-down view) |:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|
| Map builder |:heavy_check_mark:|:heavy_check_mark:|:heavy_minus_sign:|

## Demos

### Orthographic projection


<img src="https://github.com/Ending2015a/dungeon_maps/blob/master/assets/demos_height_map.gif">

[(Watch this video in high quality)](https://youtu.be/vXpTaCOoH24)


Projecting top-down maps (plan view) from depth maps.
* Top left: RGB
* Top right: Depth map
* Bottom left: top-down maps in local space
* Bottom right: top-down maps in global space


Run this example
```shell
python -m dungeon_maps.demos.height_map.run
```
Control: `W`, `A`, `S`, `D`. `Q` for exit

### Egocentric motion flow

<img src="https://github.com/Ending2015a/dungeon_maps/blob/master/assets/demos_ego_flow.gif">

[(Watch this video in high quality)](https://youtu.be/q6HnNAVr2ps)

Calculating the flow fields caused by camera motion.

Run this example
```shell
python -m dungeon_maps.demos.ego_flow.run
```

## Installation

Basic requirements:
* Python >= 3.6
* PyTorch >= 1.8.0
* [PyTorch Scatter](https://github.com/rusty1s/pytorch_scatter)

Install from pip
```shell
pip install dungeon_maps
```

Install from GitHub repo
```shell
pip install git+https://github.com.Ending2015a/dungeon_map.git@master
```

Install demos
```shell
pip install dungeon_maps[sim]
```


