InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation
2025/12/09 by Alexander Goslin · 12 voices
#cs.CV #cs.AI #cs.GR #cs.LG
paper · pdf
Abstract
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. Conversely, diffusion models offer unprecedented fidelity but remain generally confined to bounded canvases. We introduce InfiniteDiffusion, a training-free algorithm that reformulates diffusion sampling for lazy and unbounded generation, bridging the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. To demonstrate the utility of this approach, we present Terrain Diffusion, a framework for learned procedural terrain generation with a procedural noise-like interface. Our framework outpaces orbital velocity by 9 times on a consumer GPU, enabling realistic terrain generation at interactive rates. We integrate a hierarchical stack of diffusion models to couple planetary context with local detail, a compact Laplacian encoding to stabilize outputs across Earth-scale dynamic ranges, and an open-source infinite-tensor framework for constant-memory manipulation of unbounded tensors. Together, these components position diffusion models as a practical foundation for the next generation of infinite virtual worlds.
Citations
Discussions
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise [hn, 154 points, 42 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise https://arxiv.org/abs/2512.08309 (https://news.ycombinator.com/item?id=46221594) [bsky, 0 points, 0 comments]
- https://bsky.app/profile/buzzing.cc.web.brid.gy/post/3m7os2ocnd2r2 [bsky, 0 points, 0 comments]
- "Replacing Perlin Noise generators with Diffusion algorithm-based generators, enabling a much greater and much more diverse range of procedurally generated landscapes and environments." Which sounds g [bsky, 0 points, 0 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise [bsky, 0 points, 0 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise https://arxiv.org/abs/2512.08309 https://news.ycombinator.com/item?id=46221594 [bsky, 0 points, 0 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise https://arxiv.org/abs/2512.08309 (https://news.ycombinator.com/item?id=46221594) [bsky, 0 points, 0 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise https://arxiv.org/abs/2512.08309 [comments] [108 points] [bsky, 0 points, 0 comments]
- Want to try something like this. Heck yes terrain diffusion, replacing perlin noise. arxiv.org/abs/2512.08309 [bsky, 0 points, 0 comments]
- https://arxiv.org/abs/2512.08309 この論文は、Terrain Diffusionという新しい地形生成手法を紹介しています。 これは、無限のリアルタイム地形生成において、Perlinノイズの後継となるDiffusionモデルに基づいています。 詳細な内容はリンク先をご参照ください。 [bsky, 0 points, 0 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise https:// arxiv.org/abs/2512.08309 # arxiv [mastodon, 0 points, 0 comments]
- Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise https://arxiv.org/abs/2512.08309 [bsky, 0 points, 0 comments]
Related