让动态3D高斯点云随时间变化自动优化，解决模糊问题
Temporally Aware Densification for Dynamic 3D Gaussian Splatting
- 根据高斯点的持续时间动态调整补充策略
- 在三个动态场景数据集上显著提升动态区域清晰度
- 可无缝接入多种动态3D高斯方法，适合做视频重建
尽管动态3D高斯溅射（3DGS）方法已建模时间运动，但仍沿用静态补充策略，不适用于动态场景。这种对时间行为的忽视导致短生命周期高斯点监督稀疏，难以有效补充，造成动态区域重建不足、模糊。本文提出可见性感知补充（VAD）框架，将时间可见性融入补充过程，确保高斯点基于实际时间存在性进行优化。引入时间自适应阈值（TAT）机制，根据每个高斯点的时间寿命动态调整其补充阈值，平衡静态与动态区域的优化。此外，时间偏移扭曲（TOW）设计增强了时间中心附近的形变能力，延长高度动态高斯点的寿命，促进更有效的补充。所提方法在三个动态多视角基准数据集上显著提升动态区域视觉质量，优于现有方法。VAD模块具备跨多种动态3DGS方法的泛化能力，作为即插即用组件持续改进动态重建效果。
原文摘要 · Abstract (English)
Despite modeling temporal motion, dynamic 3D Gaussian Splatting (3DGS) methods still inherit a static densification strategy that is ill-suited for dynamic scenes. This neglect of temporal behavior leads to under-reconstructed and blurry dynamic regions, as short-lived Gaussians receive sparse supervision and fail to densify effectively. We propose a Visibility-Aware Densification (VAD) framework that integrates temporal visibility into the densification process, ensuring that Gaussians are refined based on their actual temporal presence. A Temporally-Adaptive Thresholding (TAT) mechanism further adjusts each Gaussian's densification threshold according to its temporal lifespan, promoting balanced refinement of both static and dynamic regions. Finally, a Temporal Offset Warping (TOW) design enhances deformation capacity around temporal centers, extending the lifespan of highly dynamic Gaussians and facilitating more effective densification. Our approach achieves substantial improvements in the visual quality of dynamic regions, outperforming existing methods across three dynamic multi-view benchmark datasets. Moreover, the proposed VAD module generalizes across diverse dynamic 3DGS methods, consistently improving dynamic reconstruction as a plug-and-play component.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。