Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
This addresses the challenge of creating dense, semantically meaningful correspondences in dynamic 3D reconstruction, which is incremental but improves specific metrics.
The paper tackles the problem of reconstructing temporally-coherent surfaces from time-evolving point clouds, achieving state-of-the-art results in unsupervised correspondence accuracy and surface reconstruction accuracy.
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.