Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene. Recent efforts explore the explicit volumetric representation to accelerate the optimization via memorizing significant information with learnable voxel grids. However, existing voxel-based methods often struggle in reconstructing fine-grained geometry, even when combined with an SDF-based volume rendering scheme. We reveal that this is because 1) the voxel grids tend to break the color-geometry dependency that facilitates fine-geometry learning, and 2) the under-constrained voxel grids lack spatial coherence and are vulnerable to local minima. In this work, we present Voxurf, a voxel-based surface reconstruction approach that is both efficient and accurate. Voxurf addresses the aforementioned issues via several key designs, including 1) a two-stage training procedure that attains a coherent coarse shape and recovers fine details successively, 2) a dual color network that maintains color-geometry dependency, and 3) a hierarchical geometry feature to encourage information propagation across voxels. Extensive experiments show that Voxurf achieves high efficiency and high quality at the same time. On the DTU benchmark, Voxurf achieves higher reconstruction quality with a 20x training speedup compared to previous fully implicit methods. Our code is available at https://github.com/wutong16/Voxurf.
翻译:神经表面重建旨在基于多视图图像重建精确的三维表面。之前的基于神经体积渲染的方法通常使用MLP训练完全隐式模型,其典型需要花费数小时才能完成单个场景的训练。最近的工作探索了显式体积表示,通过可学习的体素网格记忆重要信息来加速优化。然而,现有的基于体素的方法通常在重构细粒度几何时遇到困难,即使与基于SDF的体积渲染方案相结合也是如此。我们揭示了这是因为,首先体素网格往往会破坏便于学习细粒度几何的色彩 - 几何依赖关系,其次不受约束的体素格缺乏空间一致性,并容易陷入局部最小值。在本文中,我们提出了Voxurf,一种既高效又准确的基于体素的表面重建方法。 Voxurf通过多个关键设计来解决上述问题,包括1)采用两阶段训练过程,分别达到一致的粗糙形状和细节恢复,2)采用双色彩网络来保持色彩-几何依赖关系,以及3)采用分层几何特征来鼓励体素之间的信息传播。大量实验证明Voxurf同时实现了高效和高质量。在DTU基准测试中,Voxurf相对于之前的完全隐式方法具有20倍的训练加速比,并且具有更高的重建质量。我们的代码可以在https://github.com/wutong16/Voxurf找到。