GDC 2025 Session Viewer
Global Illumination in 'Once Human': A Hybrid Approach for 16km Open World
Location: Room 2018, West Hall
Date: Wednesday, March 19
Time: 3:30 pm - 4:30 pm
Pass Type: All Access Pass, Core Pass - Get your pass now!
Track: Programming
Format: Lecture
Vault Recording: Video
Audience Level: Intermediate
'Once Human' was released on July 10, 2024, with a vast 16km×16km open world featuring dynamic time-of-day (TOD) cycles and real-time player-driven construction. This demanded a global illumination (GI) system capable of delivering both pre-baked cinematic quality and real-time responsiveness to dynamically built environments.
In this session, we present our hybrid GI solution:
For pre-baked GI:
- We introduce a neural network-driven method that achieves more than 69:1 compression ratio on 24-hour GI probe data, reducing GI storage to under 800MB for the entire 16km world.
- We also showcase how we use neural network to enable probes to react dynamically to player flashlights.
- A novel machine learning pipeline automates the resolution of indoor-outdoor light leaks in probes.
For real-time GI, we demonstrate performance-optimized techniques that enhance visual consistency while maintaining scalability across all devices compared to previous methods.
Takeaway
Attendees can learn about a hybrid global illumination(GI) solution across various platforms(pc/mobile), how the neural network can be used to compress GI for different time frames and dynamic flashlight, and how to use machine learning to help solve the light leaking problem of GI probes, and get a deeper dive into how to address challenges for real-time GI such as memory usage, performance, and visual effect
Intended Audience
Graphic and rendering programmers, or anyone interested in global illumination. Prior knowledge about global illumination and some basic understanding of machine learning will be useful.
