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.
@article{arxiv.2111.06838,
title = {Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases},
author = {Jan Bednarik and Noam Aigerman and Vladimir G. Kim and Siddhartha Chaudhuri and Shaifali Parashar and Mathieu Salzmann and Pascal Fua},
journal= {arXiv preprint arXiv:2111.06838},
year = {2021}
}
Comments
21 pages. arXiv admin note: substantial text overlap with arXiv:2104.06950