Spatia: Video Generation with Updatable Spatial Memory

Long-horizon, spatially consistent video generation enabled by persistent 3D scene point clouds and dynamic-static disentanglement.

Jinjing Zhao^*1   Fangyun Wei^*2   Zhening Liu³   Hongyang Zhang⁴   Chang Xu¹   Yan Lu²

¹The University of Sydney   ²Microsoft Research   ³HKUST   ⁴University of Waterloo
^*Equal Contribution

   

---

📖 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
• 3D-Aware Interactive Editing
• Long-horizon Scene Exploration

---

Citation

If you find this project useful, please cite the paper.

@inproceedings{zhao2026spatia,
  title={Spatia: Video Generation with Updatable Spatial Memory},
  author={Zhao, Jinjing and Wei, Fangyun and Liu, Zhening and Zhang, Hongyang and Xu, Chang and Lu, Yan},
  booktitle={Proceedings of the IEEE/cvf conference on computer vision and pattern recognition},
  year={2026}
}

---

© 2025 Spatia Project. Licensed under CC BY-SA 4.0.