曲面重建
人工智能
迭代重建
计算机科学
计算机视觉
曲面(拓扑)
模式识别(心理学)
地质学
数学
几何学
作者
Jan Bednařík,Noam Aigerman,Vladimir G. Kim,Siddhartha Chaudhuri,Shaifali Parashar,Mathieu Salzmann,Pascal Fua
标识
DOI:10.1109/tpami.2025.3538776
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI