用稀疏体素实现高精度表面重建，速度与精度兼备。
SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
- 基于符号距离函数，用稀疏体素建模几何结构
- 在多个基准上实现高精度重建并快速收敛
- 适合需要高效高质量3D重建的场景
我们将近期提出的稀疏体素光栅化范式扩展至高保真表面重建任务，提出SVRecon方法，融合符号距离函数（SDF）。与3D高斯不同，稀疏体素在空间上与邻近体素解耦且边界清晰，优化时易陷入局部最小值。尽管SDF提供自然平滑连续的几何场，但在独立参数化的稀疏体素间保持平滑性仍具挑战。为此，我们通过（1）利用视觉几何模型进行鲁棒几何初始化，以及（2）引入空间平滑损失，强制父-子及兄弟体素组间关系一致，提升结构连贯性。大量实验表明，该方法在多个基准上均实现优异重建精度，并具备稳定快速的收敛性能。代码将公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。