We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstructed surface as an atlas, using a neural network. Using canonical correspondences defined via the atlas, we encourage the reconstruction to be as isometric as possible across frames, leading to semantically-meaningful reconstruction. Through experiments and comparisons, we empirically show that our method achieves results that exceed that state of the art in the accuracy of unsupervised correspondences and accuracy of surface reconstruction.
翻译:我们提出一种方法,从一个时间变化点云的顺序中,从一个时间变化的云层序列中,以不受监督地重建一个时间一致的表层序列,在所有关键框架之间产生密集的、具有语义意义的对应关系。我们用神经网络将重建后的表层作为地图集来代表。我们利用地图集定义的卡通式对应关系,鼓励重建尽可能做到跨框架的测量,从而导致具有象征意义的重建。通过实验和比较,我们的经验显示,通过实验和比较,我们的方法所取得的结果超过了未经监督的对应关系的准确性以及地面重建的准确性。