SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
This work addresses surface reconstruction for 3D modeling applications, presenting an incremental improvement over existing sparse voxel methods.
The paper tackles the problem of high-fidelity surface reconstruction by extending sparse voxel rasterization with Signed Distance Functions (SDFs), achieving strong reconstruction accuracy and consistently speedy convergence in experiments.
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.