Discrete Laplace Operator Estimation for Dynamic 3D Reconstruction

Xiangyu Xu, Enrique Dunn; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 1548-1557

Abstract


We present a general paradigm for dynamic 3D reconstruction from multiple independent and uncontrolled image sources having arbitrary temporal sampling density and distribution. Our graph-theoretic formulation models the spatio-temporal relationships among our observations in terms of the joint estimation of their 3D geometry and its discrete Laplace operator. Towards this end, we define a tri-convex optimization framework that leverages the geometric properties and dependencies found among a Euclidean shape-space and the discrete Laplace operator describing its local and global topology. We present a reconstructability analysis, experiments on motion capture data and multi-view image datasets, as well as explore applications to geometry-based event segmentation and data association.

Related Material


[pdf]
[bibtex]
@InProceedings{Xu_2019_ICCV,
author = {Xu, Xiangyu and Dunn, Enrique},
title = {Discrete Laplace Operator Estimation for Dynamic 3D Reconstruction},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}