Spatia：具有可更新空间记忆的视频生成
Spatia: Video Generation with Updatable Spatial Memory
将3D点云作为持久空间记忆，通过视觉SLAM迭代更新，为视频生成提供几何约束，可复用于长视频生成中的空间一致性保持与相机控制。
原文依据 explicitly preserves a 3D scene point cloud as persistent spatial memory
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有视频生成模型由于视频信号密集且高维的特性，难以保持长期的空间与时间一致性。为克服这一局限，我们提出Spatia，一种空间记忆感知的视频生成框架，它显式地保留3D场景点云作为持久空间记忆。Spatia以该空间记忆为条件迭代生成视频片段，并通过视觉SLAM持续更新它。这种动态-静态解耦设计增强了整个生成过程中的空间一致性，同时保留了模型生成真实动态实体的能力。此外，Spatia支持显式相机控制和3D感知交互编辑等应用，为可扩展的、记忆驱动的视频生成提供了一个几何基础的框架。
英文原文摘要 838 字符
Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limitation, we propose Spatia, a spatial memory-aware video generation framework that explicitly preserves a 3D scene point cloud as persistent spatial memory. Spatia iteratively generates video clips conditioned on this spatial memory and continuously updates it through visual SLAM. This dynamic-static disentanglement design enhances spatial consistency throughout the generation process while preserving the model's ability to produce realistic dynamic entities. Furthermore, Spatia enables applications such as explicit camera control and 3D-aware interactive editing, providing a geometrically grounded framework for scalable, memory-driven video generation.