用连续刚体运动建模，让动态场景重建更稳定、可扩展。
TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting
- 采用统一连续变换建模，避免碎片化时间片段
- 支持600至1200帧长视频，内存增长可控
- 适合需要长时间动态重建的场景应用
近期4D高斯点阵（4DGS）方法在动态场景重建上表现优异，但通常依赖分段线性速度近似和短时窗，导致严重的时间碎片化。这迫使高斯点频繁删除与重建以追踪复杂非线性运动，破坏物体长期时间一致性，并引发高斯点数量无限制增长，难以扩展至长视频序列。为此，本文提出TRiGS，一种新型4D表示方法，利用统一的连续几何变换。通过整合$SE(3)$变换、分层贝塞尔残差与可学习局部锚点，TRiGS为每个原始对象建模几何一致的刚体运动。该连续公式保持时间身份，有效抑制内存无限增长。大量实验表明，TRiGS在标准基准上实现高保真渲染，且首次实现对600至1200帧长视频序列的稳定重建，显著优于以往方法，在时间稳定性上表现突出。
原文摘要 · Abstract (English)
Recent 4D Gaussian Splatting (4DGS) methods achieve impressive dynamic scene reconstruction but often rely on piecewise linear velocity approximations and short temporal windows. This disjointed modeling leads to severe temporal fragmentation, forcing primitives to be repeatedly eliminated and regenerated to track complex nonlinear dynamics. This makeshift approximation eliminates the long-term temporal identity of objects and causes an inevitable proliferation of Gaussians, hindering scalability to extended video sequences. To address this, we propose TRiGS, a novel 4D representation that utilizes unified, continuous geometric transformations. By integrating $SE(3)$ transformations, hierarchical Bezier residuals, and learnable local anchors, TRiGS models geometrically consistent rigid motions for individual primitives. This continuous formulation preserves temporal identity and effectively mitigates unbounded memory growth. Extensive experiments demonstrate that TRiGS achieves high fidelity rendering on standard benchmarks while uniquely scaling to extended video sequences (e.g., 600 to 1200 frames) without severe memory bottlenecks, significantly outperforming prior works in temporal stability.
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。