This course will take place as an online event. The link to the streaming platform will be provided to the registrants only.
Contents:
The Unreal Engine is one of the state-of-the-art 3D rendering engines, primarily used for game development. In recent years, its application in generating synthetic data for machine learning research has expanded significantly, supported by new features from Epic Games Inc. This course provides comprehensive training on creating virtual worlds and procedural content generation (PCG) techniques that can serve as data sources for machine learning applications.
Participants will learn to build realistic virtual environments with controllable parameters, create procedural content generation systems, and implement data capture mechanisms. The course covers virtual city creation with AI traffic systems, render target implementations for various output formats, and real-time camera feed capture systems using NDI integration.
At the end of the course, participants will have built their own virtual world environments with data export capabilities, suitable for generating training datasets for computer vision and AI applications.
Target audience:
Users interested in learning virtual world creation techniques, procedural content generation, and building synthetic environments that can generate data for machine learning research. Suitable for researchers, developers, and content creators working on simulation environments or synthetic data generation.
Language:
This course is taught in English.
Duration:
2 days
Dates:
23-24 September 2025, 09:00-12:00, 13:00-16:00
Venue:
Online via Zoom
Getting Started
Please follow the guide to see requirements and setting up the project:
https://gitlab.jsc.fz-juelich.de/hedgedoc/24tF29QsTe-ijNBHU1I5VQ
Number of Participants:
minimum 5, maximum 30
Instructor:
Thomas George, JSC