用高斯点追踪动态表面，支持拓扑变化的精准重建。
GauSTAR: Gaussian Surface Tracking and Reconstruction
- 将高斯点绑定到网格面，动态更新拓扑结构。
- 在拓扑变化区域自动解绑高斯点，生成新表面。
- 适合复杂动态场景的实时追踪与渲染，如物体分裂或消失。
3D高斯点阵技术已实现静态场景的高效逼真渲染。近期工作将其扩展至表面重建与追踪，但面对拓扑变化（如表面出现、消失或分裂）时仍具挑战。为此，我们提出GauSTAR，一种新型方法，可对具有拓扑变化的通用动态场景实现逼真渲染、精确表面重建和可靠3D追踪。输入为多视角图像，GauSTAR将高斯点绑定至网格面以表示动态物体。对于拓扑稳定的区域，保持网格结构并用高斯点追踪；在拓扑变化区域，自适应解绑高斯点，基于优化后的高斯点实现新表面的准确注册与生成。此外，引入基于表面的场景光流方法，为帧间追踪提供鲁棒初始化。实验表明，该方法能有效追踪与重建动态表面，支持多种应用。项目页面及代码已公开：https://eth-ait.github.io/GauSTAR/。
原文摘要 · Abstract (English)
3D Gaussian Splatting techniques have enabled efficient photo-realistic rendering of static scenes. Recent works have extended these approaches to support surface reconstruction and tracking. However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GauSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GauSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GauSTAR maintains the mesh topology and tracks the meshes using Gaussians. For regions where topology changes, GauSTAR adaptively unbinds Gaussians from the mesh, enabling accurate registration and generation of new surfaces based on these optimized Gaussians. Additionally, we introduce a surface-based scene flow method that provides robust initialization for tracking between frames. Experiments demonstrate that our method effectively tracks and reconstructs dynamic surfaces, enabling a range of applications. Our project page with the code release is available at https://eth-ait.github.io/GauSTAR/.
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。