GauSTAR: Gaussian Surface Tracking and Reconstruction

TL;DR

GauSTAR introduces a novel approach for photo-realistic rendering, surface reconstruction, and 3D tracking of dynamic scenes with topology changes by adaptively binding and unbinding Gaussians to mesh faces.

Contribution

It presents a new method that handles complex topology changes in dynamic scenes by adaptively managing Gaussians, enabling accurate tracking and reconstruction.

Findings

Effective tracking of dynamic surfaces with topology changes.

Accurate surface reconstruction in complex scenes.

Robust scene flow initialization for frame-to-frame tracking.

Abstract

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/.