From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians
This addresses the challenge of surface reconstruction for 3DGS users, enabling high-fidelity mesh extraction from fast novel view synthesis methods, though it is incremental as it builds on existing 3DGS and Objects as Volumes frameworks.
The paper tackles the problem of extracting accurate watertight meshes from 3D Gaussian Splatting (3DGS), which lacks a global geometric field, by introducing a learnable oriented normal and adapted attenuation formulation to define occupancy and normal fields, resulting in state-of-the-art performance on DTU and Tanks and Temples datasets with complete meshes and recovery of thin structures like bicycle spokes.
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.