Generate neural graphics datasets with Neural Graphics Data Capture in Unreal Engine
Introduction
Benefits of Neural Graphics Data Capture for game developers
Install and enable the plugin
Configure Level Blueprint capture controls
Run capture and verify outputs
Capture settings and troubleshooting
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Introductory
Reading time:  30 min
Last updated:  18 Aug 2026
Skill level:
  Introductory
Reading time:
  30 min
Last updated:
  18 Aug 2026
Authors:Annie Tallund, Arm
Richard Burton, Arm
Arm IP:Mali Immortalis
Tags: Graphics Windows Unreal Engine Visual Studio NX
Authors:
  • Annie Tallund, Arm
  • Richard Burton, Arm
Arm IP:
Mali Immortalis
Tags:
Graphics Windows Unreal Engine Visual Studio 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

AI-assisted

This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
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

AI-assisted

These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
Do I need a C++ Unreal project to build the plugin?
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.
Which play mode should I use for capture, and where do I change it?
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.
How do I start and stop a capture during gameplay?
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.
Where are the exported datasets saved, and how do I verify the capture finished?
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.
How can I adjust capture quality, scaling, or lock the frame rate?
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.
Next