Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with Spiking Neurons

Novel view synthesis for dynamic scenes remains challenging due to complex motion variations. Recent methods represent dynamic and static regions with separate Gaussians to improve efficiency and accuracy, but inaccurate assignment of static and dynamic Gaussian primitive still limits performance. We identify two key issues, namely inaccurate mask priors and improper tag representations, which lead to boundary artifacts, loss of finegrained motion details, and overfitting on input views, resulting in degraded side-view synthesis. To address these problems, we propose a spatio-temporally fine-grained mask field and a discontinuous dynamic-static tagging field to achieve accurate assignment of dynamic and static Gaussian primitives, enabling high-quality novel view synthesis, especially in fine-grained motions, motion boundary regions, and side viewpoints. Experiments show that our method achieves state-of-the-art rendering quality and real-time performance. More demos and code will be available at https://zju-bmi-lab.github.io/ SpikeMaskGS-homepage.