Advancing Structured Priors for Sparse-Voxel Surface Reconstruction

TL;DR

This paper combines 3D Gaussian Splatting and sparse-voxel rasterization for improved surface reconstruction, introducing a novel voxel initialization and depth supervision to enhance accuracy and convergence speed.

Contribution

It presents a new voxel initialization method and depth supervision technique that leverage the strengths of both explicit representations for better surface reconstruction.

Findings

Improved geometric accuracy over prior methods

Enhanced fine-structure recovery and surface completeness

Maintained fast convergence in experiments

Abstract

Reconstructing accurate surfaces with radiance fields has progressed rapidly, yet two promising explicit representations, 3D Gaussian Splatting and sparse-voxel rasterization, exhibit complementary strengths and weaknesses. 3D Gaussian Splatting converges quickly and carries useful geometric priors, but surface fidelity is limited by its point-like parameterization. Sparse-voxel rasterization provides continuous opacity fields and crisp geometry, but its typical uniform dense-grid initialization slows convergence and underutilizes scene structure. We combine the advantages of both by introducing a voxel initialization method that places voxels at plausible locations and with appropriate levels of detail, yielding a strong starting point for per-scene optimization. To further enhance depth consistency without blurring edges, we propose refined depth geometry supervision that converts multi-view cues into direct per-ray depth regularization. Experiments on standard benchmarks demonstrate improvements over prior methods in geometric accuracy, better fine-structure recovery, and more complete surfaces, while maintaining fast convergence.