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.
翻译:以多视图图像为基础的神经表面重建旨在重建精确的 3D 表面。 以往基于神经体积的方法, 主要是对 MLP 进行完全隐含的模型培训, 通常需要一个场景需要几个小时的培训。 最近的努力探索了明确的体积代表, 以学习的 voxel 网格来通过记忆化重要信息来加速优化。 然而, 现有的基于 voxel 的基于 voxel 的地表重建方法往往在重建精细测的几何方法中挣扎, 即使与基于 SDF 的体积配置计划相结合。 我们发现, 这是因为:(1) voxel 电网往往打破色色地测量依赖性, 从而有利于精细地测量学学习, 和 2 受控制不足的 voxel 电网缺乏空间一致性, 易受本地迷你的伤害。 在这项工作中, 我们介绍了Voxurfer 的基于 voxel 地表重建方法, 既高效又准确。 Voxurf 解决上述问题的关键设计, 包括 (1) 一种两阶段培训程序, 获得一致的cofs 形状, 并连续恢复精细细节, 2 高级的颜色测量测量测量结构网络, 2) 和双重的更高精密性网络, 2, 一个在高质的系统化的系统化的系统测量测量测量测量测量测试中, 上, 和高质变式的测量测量测量测量测量测, 上, 上, 和高基 的测量测量测量测量测量测量测量测量测量测量测量系的基 3。