Advancing Structured Priors for Sparse-Voxel Surface Reconstruction
This addresses surface reconstruction quality for 3D computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of surface reconstruction from radiance fields by combining strengths of 3D Gaussian Splatting and sparse-voxel rasterization through a voxel initialization method and refined depth supervision, achieving improved geometric accuracy, better fine-structure recovery, and more complete surfaces on standard benchmarks while maintaining fast convergence.
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.