MrNeRF (@janusch_patas)
2025-01-20 | โค๏ธ 239 | ๐ 38
GSTAR: Gaussian Surface Tracking and Reconstruction
Contributions: โข A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology.
โข A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve.
โข A method for handling large or fast deformations of surfaces between frames using scene flow warping.
Abstract (excerpt): 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 GSTAR, 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, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.
๋ฏธ๋์ด
Tags
domain-vision-3d domain-rendering domain-genai domain-dev-tools