SVRecon: Sparse Voxel Rasterization for Surface Reconstruction

TL;DR

SVRecon introduces a novel sparse voxel rasterization method for high-fidelity surface reconstruction using SDF, emphasizing smoothness and coherence across voxels, resulting in accurate and fast reconstructions.

Contribution

The paper extends sparse voxel rasterization to surface reconstruction with SDF, incorporating a new initialization and smoothness loss to improve coherence and accuracy.

Findings

Achieves high reconstruction accuracy across benchmarks.

Demonstrates speedy convergence in surface reconstruction tasks.

Provides publicly available code for reproducibility.

Abstract

We extend the recently proposed sparse voxel rasterization paradigm to the task of high-fidelity surface reconstruction by integrating Signed Distance Function (SDF), named SVRecon. Unlike 3D Gaussians, sparse voxels are spatially disentangled from their neighbors and have sharp boundaries, which makes them prone to local minima during optimization. Although SDF values provide a naturally smooth and continuous geometric field, preserving this smoothness across independently parameterized sparse voxels is nontrivial. To address this challenge, we promote coherent and smooth voxel-wise structure through (1) robust geometric initialization using a visual geometry model and (2) a spatial smoothness loss that enforces coherent relationships across parent-child and sibling voxel groups. Extensive experiments across various benchmarks show that our method achieves strong reconstruction accuracy while having consistently speedy convergence. The code will be made public.