TensorX
返回文献探索

Paper · arXiv 2512.15716

Spatia: Video Generation with Updatable Spatial Memory

Jinjing Zhao, Fangyun Wei, Zhening Liu, Hongyang Zhang, Chang Xu, Yan Lu

35 upvotesDecember 17, 2025arXiv 预印本
AI 摘要

Spatia, a spatial memory-aware video generation framework, maintains long-term spatial and temporal consistency by preserving and updating a 3D scene point cloud, enabling realistic video generation and interactive editing.

spatial memory-awarevideo generation framework3D scene point clouddynamic-static disentanglementvisual SLAMexplicit camera control3D-aware interactive editing

Abstract

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.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号