无限世界：实时3D感知长视频生成
Endless World: Real-Time 3D-Aware Long Video Generation
AI总结：
Endless World通过实时3D感知机制生成无限长且连贯的视频，解决长视频生成中的3D一致性与动态场景合成问题。
摘要：
生成长且连贯的视频序列并保持稳定的3D结构仍是一个重大挑战，特别是在流媒体场景中。受此启发，我们引入了Endless World，一个实时框架，用于无限、3D一致的视频生成。为了支持无限视频生成，我们引入了一种条件自回归训练策略，使新生成的内容与现有视频帧对齐。这种设计在保持长距离依赖性的同时保持计算效率，使单个GPU上的实时推断无需额外训练开销。此外，我们的Endless World集成了全局3D感知注意力，以在时间上提供连续的几何指导。我们的3D注入机制在整个扩展序列中强制物理合理性和几何一致性，解决了长视界和动态场景合成中的关键挑战。大量实验表明，Endless World生成长、稳定且视觉连贯的视频，在视觉保真度和空间一致性方面实现了与现有方法相当或更优的性能。我们的项目已在https://b wgzk-keke.github.io/EndlessWorld/上发布。
英文摘要：
Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video generation.To support infinite video generation, we introduce a conditional autoregressive training strategy that aligns newly generated content with existing video frames. This design preserves long-range dependencies while remaining computationally efficient, enabling real-time inference on a single GPU without additional training overhead.Moreover, our Endless World integrates global 3D-aware attention to provide continuous geometric guidance across time. Our 3D injection mechanism enforces physical plausibility and geometric consistency throughout extended sequences, addressing key challenges in long-horizon and dynamic scene synthesis.Extensive experiments demonstrate that Endless World produces long, stable, and visually coherent videos, achieving competitive or superior performance to existing methods in both visual fidelity and spatial consistency. Our project has been available on https://bwgzk-keke.github.io/EndlessWorld/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
