We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible. We have devised an optimization strategy that makes our method robust to noise and global motions, without a priori correspondences or pre-alignment steps. As a result, our approach outperforms state-of-the-art ones on several challenging datasets. The code is available at https://github.com/bednarikjan/temporally_coherent_surface_reconstruction.
翻译:我们建议了一种方法,从一个时间变化点云的序列中重建一个不受监督的、时间一致的表层序列。 它在各框架之间产生密度大、语义上有意义的对应关系。 我们把重建后的表层作为由神经网络计算的地图册来代表,这使我们能够在各框架之间建立对应关系。 使这些对应关系在语义上具有意义的关键在于保证在相应的点上计算到的数以万计的数值尽可能相似。 我们已经设计了一个优化战略,使我们的方法在没有先验对应或预先调整步骤的情况下,对噪音和全球运动具有活力。 结果,我们的方法超越了几个挑战性数据集的艺术状态。 代码可以在 https://github.com/bednarikjan/temporally_coherent_boom_rebuilding上查阅。