From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians

TL;DR

This paper introduces a novel surface reconstruction method from 3D Gaussian Splatting that produces accurate, watertight meshes with a new occupancy field, normal estimation, and improved evaluation protocols.

Contribution

It derives a principled occupancy field for Gaussian Splatting, introduces learnable oriented normals, and develops a complete surface extraction pipeline with rigorous evaluation methods.

Findings

Sets new state-of-the-art on DTU and Tanks and Temples datasets.

Produces complete, watertight meshes at a fraction of the size of previous methods.

Effectively reconstructs thin structures like bicycle spokes.

Abstract

3D Gaussian Splatting (3DGS) has revolutionized fast novel view synthesis, yet its opacity-based formulation makes surface extraction fundamentally difficult. Unlike implicit methods built on Signed Distance Fields or occupancy, 3DGS lacks a global geometric field, forcing existing approaches to resort to heuristics such as TSDF fusion of blended depth maps. Inspired by the Objects as Volumes framework, we derive a principled occupancy field for Gaussian Splatting and show how it can be used to extract highly accurate watertight meshes of complex scenes. Our key contribution is to introduce a learnable oriented normal at each Gaussian element and to define an adapted attenuation formulation, which leads to closed-form expressions for both the normal and occupancy fields at arbitrary locations in space. We further introduce a novel consistency loss and a dedicated densification strategy to enforce Gaussians to wrap the entire surface by closing geometric holes, ensuring a complete shell of oriented primitives. We modify the differentiable rasterizer to output depth as an isosurface of our continuous model, and introduce Primal Adaptive Meshing for Region-of-Interest meshing at arbitrary resolution. We additionally expose fundamental biases in standard surface evaluation protocols and propose two more rigorous alternatives. Overall, our method Gaussian Wrapping sets a new state-of-the-art on DTU and Tanks and Temples, producing complete, watertight meshes at a fraction of the size of concurrent work-recovering thin structures such as the notoriously elusive bicycle spokes.