Analyze Neural Frame Rate Upscaling using Project Moku
Introduction
Understand Project Moku as an NFRU test environment
Enable the Arm Neural Graphics plugin
Validate NFRU with Streamline and RenderDoc
Analyze occlusion with NFRU and Project Moku
Analyze particle effects with NFRU and Project Moku
Analyze lighting changes with NFRU and Project Moku
Analyze and adjust NFRU frame pacing
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Advanced
Reading time:  30 min
Last updated:  03 Aug 2026
Skill level:
  Advanced
Reading time:
  30 min
Last updated:
  03 Aug 2026
Author:Powen Yang
Arm IP:Mali Immortalis
Tags: ML Windows Unreal Engine Vulkan SDK Visual Studio Arm Performance Studio NX
Author:
  • Powen Yang
Arm IP:
Mali Immortalis
Tags:
ML Windows Unreal Engine Vulkan SDK Visual Studio Arm Performance Studio NX

Who is this for?

This Learning Path is for game and graphics developers who want to evaluate Neural Frame Rate Upscaling (NFRU) in Unreal Engine using Arm ML Extensions for Vulkan.

What will you learn?

Upon completion of this Learning Path, you will be able to:

  • Understand how NFRU generates intermediate frames for smoother motion.
  • Evaluate NFRU visual quality across occlusion, particle, and lighting-change scenarios.
  • Measure NFRU performance and tune frame pacing with Unreal Engine console variables.
  • Analyze generated frames with RenderDoc for Arm GPUs.

Prerequisites

Before starting, you will need the following:

  • (Recommended) Complete Enable Neural Frame Rate Upscaling in Unreal Engine
  • Windows 11
  • Unreal Engine 5.4 or 5.6 with Templates and Feature Pack enabled
  • Visual Studio with Desktop Development with C++ and .NET desktop build tools
  • Familiarity with Unreal Engine project setup and rendering settings

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 use Project Moku, an Arm Unreal Engine sample, to evaluate NFRU on mobile GPUs. You’ll enable the Arm Neural Graphics Plugin and create repeatable reference cuts. Using the reference cuts with Streamline and RenderDoc, you’ll validate frame generation, inspect visual differences, and measure NFRU performance. You’ll analyze occlusion, particle, and lighting-change scenarios before tuning NFRU for your own Unreal Engine content.

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
?
What is Project Moku used for?
Project Moku is an Arm Unreal Engine sample that provides a controlled environment for evaluating NFRU and related neural rendering techniques on supported mobile GPUs.
How does NFRU improve perceived smoothness?
NFRU generates an intermediate frame between rendered frames, increasing the presentation cadence without requiring the engine to render every displayed frame.
Which tools validate NFRU?
Use Streamline to confirm NFRU activity and measure GPU and neural workload. Use RenderDoc to inspect frame-generation events, inputs, intermediate resources, and generated output.
Which scenes are useful for evaluating NFRU visual quality?
Test repeatable scenes with occlusion changes, alpha-blended particles, and lighting changes. These scenarios expose differences around visibility, disocclusion, transparency, and screen edges.
How should NFRU performance be measured?
Compare render FPS with present FPS, then check GPU and neural workload, display limits, and frame-pacing gaps. Use the pace adjuster to select a presentation target the workload can sustain.
Next