CVAIGRLGDec 9, 2025

Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation

arXiv:2512.08309v1Has Code
Originality Incremental advance
AI Analysis

This addresses the problem of low realism and coherence in procedural worlds for game developers and simulation creators, representing a novel paradigm shift rather than an incremental improvement.

The paper tackles the limitations of Perlin noise in procedural terrain generation by introducing Terrain Diffusion, a diffusion-based method that achieves seamless, infinite, and real-time synthesis of landscapes, enabling coherent planet-scale generation with constant-time access.

For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally limited in realism and large-scale coherence. We introduce Terrain Diffusion, an AI-era successor to Perlin noise that bridges the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. At its core is InfiniteDiffusion, a novel algorithm for infinite generation, enabling seamless, real-time synthesis of boundless landscapes. A hierarchical stack of diffusion models couples planetary context with local detail, while a compact Laplacian encoding stabilizes outputs across Earth-scale dynamic ranges. An open-source infinite-tensor framework supports constant-memory manipulation of unbounded tensors, and few-step consistency distillation enables efficient generation. Together, these components establish diffusion models as a practical foundation for procedural world generation, capable of synthesizing entire planets coherently, controllably, and without limits.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes