InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation
摘要
文章指出内容生成面临无限范围、无状态生成与学习真实感三难困境。扩散模型可实现真实感但范围有限，经典过程噪声虽无限无状态却无法学习，自回归外绘虽支持学习无界生成却需共享全局状态。InfiniteDiffusion 通过将任意扩散模型泛化为 MultiDiffusion，使其成为无限逻辑无状态数组，仅依种子与坐标索引，支持 O (1) 随机访问、全确定性与并行计算，内部仅用有界 LRU 缓存作为性能优化，无持久或外部状态。它作为即插即用组件，将扩散过程重构为按需懒惰计算，仅生成请求区域。文章对比显示其质量退化极小，保留了无限、无状态与懒惰生成的所有优势。
荐读理由
InfiniteDiffusion把任何扩散模型转为无限、无状态、可O(1)随机访问的数组，只用LRU缓存优化，适合无限世界地形，O(1)随机存取+并行性直接帮你省去全局状态麻烦和内存限制
原文
Until now, content generation has faced a fundamental trilemma: infinite extent, stateless generation, and learned realism - pick any two. Diffusion models achieve realism but are bounded. Classical procedural noise is infinite and stateless, but cannot learn. Auto-regressive outpainting allows learned unbounded generation, but requires a shared global state that precludes determinism and random access.
InfiniteDiffusion breaks this trilemma, transforming any diffusion model into an infinite, logically stateless array, indexed only by seed and coordinates, supporting O(1) random access, full determinism, and embarrassing parallelism. It internally uses only a bounded LRU cache as a performance optimization. No persistent or external state.
InfiniteDiffusion achieves this by generalizing MultiDiffusion for infinite or larger-than-memory domains, acting as a drop-in replacement that reformulates the diffusion process as a lazy computation that generates only the region you request, when you request it.
Each image below compares MultiDiffusion (top), which operates over a pre-defined, eagerly-generated, and bounded canvas, with InfiniteDiffusion (bottom), which imposes no such bounds. InfiniteDiffusion introduces little to no quality degradation compared to MultiDiffusion, while providing the benefits of infinite, stateless, and lazy generation.
这条对你有帮助吗？