将动态场景分解为静止与运动部分，提升重建稳定性与清晰度。
SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
- 分离静态与动态成分，分别建模几何与运动
- 相比现有方法，渲染质量提升，无运动伪影
- 适合需要精确动态分离的视觉重建任务
从单目视频重建动态3D场景仍面临根本性挑战，需从有限观测中联合推断运动、结构和外观。基于高斯点阵的现有方法常将静态与动态元素耦合在统一表示中，导致运动泄漏、几何失真和时间闪烁。我们发现根源在于几何与外观随时间耦合建模，影响稳定性和可解释性。为此提出SplitGaussian，显式将场景表示分解为静态与动态两部分。通过解耦运动建模与背景几何，并仅允许动态分支随时间变形，本方法避免了静态区域的运动伪影，同时支持视图与时间依赖的外观优化。该解耦设计不仅提升时序一致性与重建保真度，还加速收敛。大量实验表明，本方法在渲染质量、几何稳定性与运动分离方面均优于当前最优方法。
原文摘要 · Abstract (English)
Reconstructing dynamic 3D scenes from monocular video remains fundamentally challenging due to the need to jointly infer motion, structure, and appearance from limited observations. Existing dynamic scene reconstruction methods based on Gaussian Splatting often entangle static and dynamic elements in a shared representation, leading to motion leakage, geometric distortions, and temporal flickering. We identify that the root cause lies in the coupled modeling of geometry and appearance across time, which hampers both stability and interpretability. To address this, we propose SplitGaussian, a novel framework that explicitly decomposes scene representations into static and dynamic components. By decoupling motion modeling from background geometry and allowing only the dynamic branch to deform over time, our method prevents motion artifacts in static regions while supporting view- and time-dependent appearance refinement. This disentangled design not only enhances temporal consistency and reconstruction fidelity but also accelerates convergence. Extensive experiments demonstrate that our approach outperforms prior state-of-the-art methods in rendering quality, geometric stability, and motion separation.
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。