论文标题
神经变形金字塔的非刚性点云登记
Non-rigid Point Cloud Registration with Neural Deformation Pyramid
论文作者
论文摘要
非刚性点云注册是许多计算机视觉和计算机图形应用程序中的关键组件。未知的非刚性运动的高复杂性使这项任务成为一个具有挑战性的问题。在本文中，我们通过分层运动分解分解了这个问题。我们称为神经变形金字塔（NDP）的方法代表使用金字塔结构的非刚性运动。每个由多层感知（MLP）表示的金字塔水平，将其视为正弦编码的3D点，并从上一个级别输出其运动增量。正弦函数从低输入频率开始，当金字塔水平下降时逐渐增加。与现有的基于MLP的方法相比，这允许多层刚性进行非辅助运动分解，并加快求解的速度50倍。我们的方法在未经学习和监督的设置下，在4DMatch/4Dlomatch基准的4DMatch/4Dlomatch基准上实现了高级部分非刚性点云注册结果。
Non-rigid point cloud registration is a key component in many computer vision and computer graphics applications. The high complexity of the unknown non-rigid motion make this task a challenging problem. In this paper, we break down this problem via hierarchical motion decomposition. Our method called Neural Deformation Pyramid (NDP) represents non-rigid motion using a pyramid architecture. Each pyramid level, denoted by a Multi-Layer Perception (MLP), takes as input a sinusoidally encoded 3D point and outputs its motion increments from the previous level. The sinusoidal function starts with a low input frequency and gradually increases when the pyramid level goes down. This allows a multi-level rigid to nonrigid motion decomposition and also speeds up the solving by 50 times compared to the existing MLP-based approach. Our method achieves advanced partialto-partial non-rigid point cloud registration results on the 4DMatch/4DLoMatch benchmark under both no-learned and supervised settings.
