DSD-GS: 面向高效高保真动态场景重建的高斯泼溅动态-静态分解
DSD-GS: Dynamic-Static Decomposition of Gaussian Splatting for Efficient and High-Fidelity Dynamic Scene Reconstruction
AI总结：
提出基于前馈高斯泼溅编码器和光流模型的动态-静态分解框架，通过消除静态区域冗余计算，在渲染质量、训练/渲染速度和存储效率上达到最优。
摘要：
动态场景重建和新视角合成是虚拟现实、机器人、数字孪生等下一代视觉智能应用的基础。然而，从任意视角对复杂时变场景进行高保真重建仍是一个重大挑战。现有的动态3DGS方法由于将所有高斯体建模为动态组件，存在计算效率低下的问题。虽然近期基于分解的方法试图解决这一问题，但仍面临重建质量下降和训练时间延长的问题。为缓解这些局限，我们提出一种新颖的动态重建框架，基于高效的静态-动态分解策略，使用前馈高斯泼溅编码器和光流模型。通过消除静态区域的冗余计算，我们的方法实现了最先进的性能，在渲染质量、训练和渲染速度以及存储效率上均优于现有基线。值得注意的是，在Neural 3D数据集上，我们的框架仅需10分钟训练，并在单张NVIDIA RTX 5090 GPU上以1352x1014分辨率实现了超过700 FPS的渲染速度。此外，我们的分解策略消除了COLMAP预处理的需求，并实现了确定性初始化，从而提高了效率和可重复性。
英文摘要：
Dynamic scene reconstruction and novel view synthesis are fundamental to next-generation visual intelligence applications such as virtual reality, robotics, and digital twins. However, high-fidelity reconstruction of complex, time-varying scenes from arbitrary viewpoints remains a significant challenge. Existing dynamic 3DGS methods suffer from computational inefficiency, since they model all Gaussians as dynamic components. While recent decomposition-based approaches address this issue, they still struggle with degraded reconstruction quality and prolonged training time. To mitigate these limitations, we propose a novel dynamic reconstruction framework built upon an efficient static-dynamic decomposition strategy using a Feed-Forward Gaussian Splatting encoder and an optical flow model. By eliminating redundant computations on static regions, our method achieves state-of-the-art performance, outperforming existing baselines across rendering quality, training and rendering speed, and storage efficiency. Notably, on the Neural 3D dataset, our framework requires only 10 minutes for training and achieves a rendering speed of over 700 FPS on a single NVIDIA RTX 5090 GPU at resolution of 1352x1014. Furthermore, our decomposition strategy eliminates the need for COLMAP preprocessing and enables deterministic initialization, thereby enhancing both efficiency and reproducibility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
