# [Generate neural graphics datasets with Neural Graphics Data Capture in Unreal Engine](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/)

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/)
- [Benefits of Neural Graphics Data Capture for game developers](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/01-why-ngdc/)
- [Install and enable the plugin](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/02-install-and-enable-plugin/)
- [Configure Level Blueprint capture controls](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/03-configure-level-blueprint/)
- [Run capture and verify outputs](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/04-run-capture-and-verify-output/)
- [Capture settings and troubleshooting](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/05-settings-and-troubleshooting/)
- [Next Steps](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/neural-graphics-data-capture-unreal/_next-steps/)

## About this Learning Path

| Skill level:       | Introductory       |
|---------------------|--------------------|
| Reading time:       | 30 min             |
| Last updated:       | 18 Aug 2026        |

| Authors:            | Annie Tallund, Arm [GitHub](https://github.com/annietllnd) [LinkedIn](https://linkedin.com/in/annietallund)  <br/> Richard Burton, Arm [GitHub](https://github.com/Burton2000) |
|---------------------|--------------------|
| Arm IP:             | [Mali](https://support.arm.com/?tab=compute-ip&Product%20Type=Graphics%20Processors) [Immortalis](https://support.arm.com/?tab=compute-ip&Product%20Type=Graphics%20Processors) |
| Tags:               | [Graphics](/tag/graphics) [Windows](/tag/windows) [Unreal Engine](/tag/unreal-engine) [Visual Studio](/tag/visual-studio) [NX](/tag/nx) |

### Who is this for?
This Learning Path is for Unreal Engine developers who want to generate high-quality frame datasets for training and evaluating neural graphics models.

### What will you learn?
Upon completion of this Learning Path, you will be able to:
- Understand why Neural Graphics Data Capture is useful in a neural graphics workflow.
- Install and enable the Neural Graphics Data Capture plugin in Unreal Engine 5.5.
- Configure a Level Blueprint to start and stop capture with hotkeys.
- Run Standalone capture and verify exported dataset outputs.

### Prerequisites
Before starting, you will need the following:
- Windows 11
- Unreal Engine 5.5 installed
- Visual Studio with C++ game development tools
- A C++ Unreal project (such as the Third Person template)

### Summary
You’ll add Neural Graphics Data Capture to a C++ Unreal Engine 5.5 project and export gameplay frames as a structured dataset. First, you’ll build the plugin, bind capture controls, and record in **Standalone Game**. Then, you’ll verify the output and tune rendering and export settings to prepare data for training or evaluating neural upscalers.

### Frequently asked questions
<details>
<summary>Do I need a C++ Unreal project to build the plugin?</summary>
Yes. The plugin targets Unreal Engine 5.5 and requires a C++ Unreal project so the module compiles through Visual Studio. Open a C++ project before adding the plugin files.
</details>

<details>
<summary>Which play mode should I use for capture, and where do I change it?</summary>
Use **Standalone Game**. Open the menu next to the **Play** button and select **Standalone Game** to avoid play-in-editor resizing and preserve expected frame dimensions.
</details>

<details>
<summary>How do I start and stop a capture during gameplay?</summary>
Press **Play**, then press the **C** key to start capture and the **V** key to stop capture. Move through the level while recording to gather frames.
</details>

<details>
<summary>Where are the exported datasets saved, and how do I verify the capture finished?</summary>
The output directory and capture name come from `NGDCExportSettings` (`DatasetDir` and `CaptureName`). After stopping capture, check that directory for the exported capture folder and files.
</details>

<details>
<summary>How can I adjust capture quality, scaling, or lock the frame rate?</summary>
Use `NGDCRenderingSettings` and `NGDCExportSettings`. Set `UpscalingRatio` and `SupersamplingRatio` for input and output scaling and quality, and set `FixedFrameRate` to a value greater than 0 to lock the frame rate.
</details>