提出动态感知的流式4D重建方法，实现快速在线建模与实时渲染。
Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction
- 分三阶段处理：保留时序连续性、区分动静态点云、误差引导增量优化
- 在streaming场景下达到最快在线训练速度与最优重建质量
- 适合需要实时动态3D建模的场景，如AR/VR、机器人导航
3D高斯点阵（3DGS）的兴起推动了4D动态空间重建的发展。现有方法多依赖完整的多视角视频，而对支持在线重建与逐帧流式训练的方法研究较少。当前基于3DGS的流式方法对高斯原语一视同仁，持续更新稠密点，忽视了动态与静态特征的差异以及场景的时间连续性。为此，我们提出一种新型三阶段迭代式可流式4D动态空间重建框架：选择性继承阶段以保持时序连续性；动态感知偏移阶段区分动态与静态原语并优化其运动；误差引导稠密化阶段适应新出现物体。该方法在在线4D重建中达到当前最佳性能，展现出最快的在线训练速度、更优的表示质量及实时渲染能力。
原文摘要 · Abstract (English)
The recent development of 3D Gaussian Splatting (3DGS) has led to great interest in 4D dynamic spatial reconstruction. Existing approaches mainly rely on full-length multi-view videos, while there has been limited exploration of online reconstruction methods that enable on-the-fly training and per-timestep streaming. Current 3DGS-based streaming methods treat the Gaussian primitives uniformly and constantly renew the densified Gaussians, thereby overlooking the difference between dynamic and static features as well as neglecting the temporal continuity in the scene. To address these limitations, we propose a novel three-stage pipeline for iterative streamable 4D dynamic spatial reconstruction. Our pipeline comprises a selective inheritance stage to preserve temporal continuity, a dynamics-aware shift stage to distinguish dynamic and static primitives and optimize their movements, and an error-guided densification stage to accommodate emerging objects. Our method achieves state-of-the-art performance in online 4D reconstruction, demonstrating the fastest on-the-fly training, superior representation quality, and real-time rendering capability. Project page: https://www.liuzhening.top/DASS
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。