GauSTAR: Gaussian Surface Tracking and Reconstruction

CVPR 2025

We propose GauSTAR, a novel method that (a) enables photo-realistic rendering, surface reconstruction, and 3D tracking for dynamic scenes while handling topology changes. (b) GauSTAR adapts to topology changes through two mechanisms: consistent tracking for stable surfaces (red circles) and dynamic surface generation for newly appearing geometry (orange circles).

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/.

Video

Method Overview

Taking multi-view captures as input, GauSTAR tracks and reconstructs dynamic objects frame by frame. For each frame, GauSTAR first warps the previous frame's result using scene flow. It then reconstructs Gaussian Surfaces (Gaussian-attached mesh) by fixed-topology reconstruction. To handle topology-changing surfaces, GauSTAR detects topology changes, unbinds Gaussians on these surfaces, and adds new Gaussians as needed . Finally, the Gaussian Surfaces are updated through re-meshing.

GauSTAR detects topology changes based on positional gradients and reconstruction errors

GauSTAR generates new faces for new geometry and connects them to the original faces

Mesh faces are dynamically updated when topology changes. (at 0.05 × speed)

Citation