用于快速动态场景表示的混合3D-4D高斯泼溅（Gaussian Splatting）方法
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
AI总结：
针对现有4DGS方法静态区域高斯冗余导致的算力与内存开销高、画质下降问题，提出混合3D-4DGS框架，将时序不变高斯转为3D、动态区域保留4D，在保持或提升画质的同时显著加快训练速度。
摘要：
动态3D场景重建领域的最新进展已展现出可观成果，能够实现具备更优时序一致性的高保真3D新视角合成。其中，4D高斯泼溅（4D Gaussian Splatting，4DGS）因能够建模高保真的时空变化，成为一种颇具吸引力的方法。但现有方法存在计算与内存开销过大的问题，原因是静态区域被冗余分配了4D高斯，这也会降低图像质量。\n在本研究中，我们提出混合3D-4D高斯泼溅（3D-4DGS）——一种全新框架：用3D高斯自适应表示静态区域，同时为动态元素保留4D高斯。我们的方法以全4D高斯表示为初始状态，迭代地将时序不变的高斯转换为3D形式，大幅减少参数量并提升计算效率；同时，动态高斯保留完整的4D表示，以高保真度捕捉复杂运动。与基线4D高斯泼溅方法相比，我们的方法训练速度显著提升，同时保持甚至改善了视觉质量。
英文摘要：
Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing approach due to its ability to model high-fidelity spatial and temporal variations. However, existing methods suffer from substantial computational and memory overhead due to the redundant allocation of 4D Gaussians to static regions, which can also degrade image quality. In this work, we introduce hybrid 3D-4D Gaussian Splatting (3D-4DGS), a novel framework that adaptively represents static regions with 3D Gaussians while reserving 4D Gaussians for dynamic elements. Our method begins with a fully 4D Gaussian representation and iteratively converts temporally invariant Gaussians into 3D, significantly reducing the number of parameters and improving computational efficiency. Meanwhile, dynamic Gaussians retain their full 4D representation, capturing complex motions with high fidelity. Our approach achieves significantly faster training times compared to baseline 4D Gaussian Splatting methods while maintaining or improving the visual quality.
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。
