https://github.com/unrealcv/unrealcv

UnrealCV: Connecting Computer Vision to Unreal Engine
https://github.com/unrealcv/unrealcv

computer-vision embodied-ai machine-learning simulation synthetic-data ue4 virtual-worlds

Last synced: 24 days ago
JSON representation

UnrealCV: Connecting Computer Vision to Unreal Engine

• Host: GitHub
• URL: https://github.com/unrealcv/unrealcv
• Owner: unrealcv
• License: mit
• Created: 2016-09-08T18:03:51.000Z (about 8 years ago)
• Default Branch: 4.27-stable
• Last Pushed: 2024-04-10T06:46:37.000Z (7 months ago)
• Last Synced: 2024-04-10T18:18:25.021Z (7 months ago)
• Topics: computer-vision, embodied-ai, machine-learning, simulation, synthetic-data, ue4, virtual-worlds
• Language: C++
• Homepage: https://unrealcv.org
• Size: 18.1 MB
• Stars: 1,825
• Watchers: 96
• Forks: 419
• Open Issues: 107
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-unreal - unrealcv - UnrealCV: Connecting Computer Vision to Unreal Engine (Graphics Compute Plugins)
• awesome-simulation - UnrealCV - Connecting Computer Vision to Unreal Engine ([Unreal Engine](https://www.unrealengine.com/en-US/))
• awesome_unreal_engine_4_-_5 - UnrealCV (opencv)
• awesome_unreal_engine_4_-_5 - UnrealCV (opencv)

README

        
# UnrealCV

[![Join the chat at https://gitter.im/unrealcv/unrealcv](https://badges.gitter.im/unrealcv/unrealcv.svg)](https://gitter.im/unrealcv/unrealcv?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)

[![Docs Status](https://readthedocs.org/projects/unrealcv/badge/?version=latest

)](http://docs.unrealcv.org)

UnrealCV is a project to help computer vision researchers build virtual worlds using Unreal Engine 4 (UE4). It extends UE4 with a plugin by providing:

1. A set of UnrealCV commands to interact with the virtual world.

2. Communication between UE4 and an external program, such as Caffe.

UnrealCV can be used in two ways. The first one is using a compiled game binary with UnrealCV embedded. This is as simple as running a game, no knowledge of Unreal Engine is required. The second is installing UnrealCV plugin to Unreal Engine 4 (UE4) and use the editor of UE4 to build a new virtual world.

Please read [Tutorial: Getting Started](http://unrealcv.github.io/tutorial/getting_started.html) to learn using UnrealCV.



Images generated from the technical demo RealisticRendering


## New Features

 - Call any Blueprint function from Python by `vbp [obj_name] [func_name] [arg1] [arg2] ...` command.

 - Support RPC communication between Server and Client in Linux, higher FPS and more reliable.

 - A set of new commands for camera control and object manipulation, please refer to [command system](https://docs.unrealcv.org/en/latest/reference/commands.html) for more details.

## How to install UnrealCV

To install the UnrealCV Server, you need:

1. Download the source code and place it on the ``Plugin`` folder of a C++ UE4 project.

2. launch the C++ project with Visual Studio 2019, UnrealCV will be compiled at the same time.

3. To check the success installation of UnrealCV, you can run ``vget /unrealcv/status`` in the console (Press **`** to display the console).

To install the UnrealCV Client, just run:

``pip install unrealcv``

## Citation

If you found this project useful, please consider citing our paper

```bibtex

@article{qiu2017unrealcv,

  Author = {Weichao Qiu, Fangwei Zhong, Yi Zhang, Siyuan Qiao,Zihao Xiao, Tae Soo Kim, Yizhou Wang, Alan Yuille},

  Journal = {ACM Multimedia Open Source Software Competition},

  Title = {UnrealCV: Virtual Worlds for Computer Vision},

  Year = {2017}

}

```

## Contact

If you have any suggestion or interested in using UnrealCV, please [contact us](http://unrealcv.github.io/contact.html).