Presentation
InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation
SessionLayouts & Procedural
DescriptionWe introduce InfiniteDiffusion, a training-free algorithm enabling diffusion models to generate spatially infinite outputs with the core properties of procedural noise: seed-consistency (determinism) and constant-time random access. We incorporate a novel architecture for terrain generation to produce Terrain Diffusion, a learned, real-time, infinite terrain generator with a procedural noise-like interface.
Event Type
Technical Paper
TimeTuesday, 21 July 20269:40am - 9:50am PDT
LocationRoom 403 A
Digital Library
PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 20269:00am - 10:30am PDTRoom 403 A
Artificial Intelligence/Machine Learning
Generative AI
Full Conference Supporter
Full Conference
Similar Presentations
