基于脉冲神经元的动态场景动静分解新视角合成
Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with Spiking Neurons
用脉冲神经元构建时空细粒度掩码场与不连续动静标签场，替代不准确的掩码先验来分配动态/静态高斯基元，可直接迁移到任何基于高斯泼溅的动态场景重建管线中以改善运动边界与侧视角渲染。
原文依据 we propose a spatio-temporally fine-grained mask field and a discontinuous dynamic-static tagging field
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态场景的新视角合成由于复杂的运动变化而仍具挑战性。近期方法用分离的高斯表示动态与静态区域以提升效率与精度，但静态与动态高斯基元的不准确分配仍限制性能。我们识别出两个关键问题，即不准确的掩码先验与不恰当的标签表示，它们导致边界伪影、细粒度运动细节丢失以及对输入视角的过拟合，从而造成侧视角合成质量下降。为解决这些问题，我们提出时空细粒度掩码场与不连续动静标签场，以实现动态与静态高斯基元的准确分配，从而获得高质量的新视角合成，尤其是在细粒度运动、运动边界区域与侧视角下。实验表明，我们的方法取得了最优的渲染质量与实时性能。
英文原文摘要 972 字符
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 primitives still limits performance. We identify two key issues, namely inaccurate mask priors and improper tag representations, which lead to boundary artifacts, loss of fine-grained 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.