Multi4D：通过多层竞争分配实现高保真动态高斯撒布技术
Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation
摘要
动态3D高斯点云渲染面临着运动一致性与视觉质量之间的根本矛盾。基于变形的方法能够保持时间上的对应关系，但存在过度参数化问题，导致高频动态效果被过度平滑。相比之下，4D基础方法能够捕捉到精细的视觉细节，但会导致时间上的过度参数化，从而破坏物体的身份特征，并造成严重的存储负担。为了解决这一问题，我们提出了Multi4D框架——一种基于多级竞争分配的高保真动态高斯点云渲染方法。与单一的表示方式不同，我们将建模能力分配到三个结构化的层次上：静态结构、持续变化的动态几何结构以及瞬态外观元素。通过共享的渲染机制与残差驱动的优化过程，这些层次能够动态竞争以修正光度误差，从而实现自适应优化，无需预先指定的分解方式。这种分配方式既保留了长期运动的一致性，又能捕捉到精细的动态细节，从而获得最先进的渲染质量和实时性能，同时使用的动态元素数量也大大减少。此外，由于我们的表示方式能够明确追踪随时间变化的紧凑型高斯点，因此可以在之后嵌入语义特征，使得Multi4D能够实现最先进的4D分割精度，且速度提升数个数量级。项目页面：https://batfacewayne.github.io/Multi4D.io/
English Abstract
Dynamic 3D Gaussian splatting faces a fundamental tension between motion consistency and visual fidelity. Deformation-based approaches preserve temporal correspondence but suffer from motion over-factorization, oversmoothing high-frequency dynamics. In contrast, 4D-primitive methods capture fine visual details yet incur temporal overparameterization, breaking object identity and leading to severe storage overhead. To resolve this, we introduce Multi4D, a framework for high-fidelity dynamic Gaussian Splatting based on multi-level competitive allocation. Instead of a monolithic representation, we distribute modeling capacity across three structured levels: static structure, persistent dynamic geometry, and transient appearance primitives. Through shared rasterization and residual-driven optimization, these levels dynamically compete to explain photometric error, enabling adaptive specialization without pre-assigned decomposition. This allocation preserves long-term motion consistency while capturing fine dynamic detail, achieving state-of-the-art rendering quality and real-time performance with significantly fewer dynamic primitives. Furthermore, because our representation explicitly tracks compact persistent Gaussians over time, semantic features can be embedded afterward, enabling Multi4D to achieve state-of-the-art 4D segmentation accuracy with an order-of-magnitude speedup. Project page: https://batfacewayne.github.io/Multi4D.io/