DEEP ACCURATE SOLVER FOR THE GEODESIC PROBLEM

Saar Huberman, Ron Kimmel

Keywords: Geodesic distance, Geometric Deep learning.

TL;DR: Deep Local solver for approximating geodesic distances on manifolds.

Abstract: A high order accurate deep learning method for computing geodesic distances on surfaces is introduced. The proposed method exploits a dynamic programming principle which lends itself to a scheme with quasi-linear computational complexity. We consider two main components for computing distances on surfaces; A numerical solver that locally approximates the distance function and an efficient causal ordering scheme by which points are updated. The quality of the distance approximation is determined by the local solver and is the main focus of this paper. A common approach to compute distances on continuous surfaces is by considering a discretized polygonal mesh approximating the surface, and estimating distances on the polygon. With such an approximation, the exact geodesic distances restricted to the polygon are at most second order accurate with respect to the distances on the corresponding continuous surface. Here, by order of accuracy we refer to the rate of convergence as a function of the average distance between sampled points. To improve the rate of convergence, we consider a neural network based local solver which implicitly approximates the structure of the continuous surface. The proposed solver circumvents the polyhedral representation, by directly consuming sampled mesh vertices for approximation of distances on the sampled continuous surfaces. We provide numerical evidence that the proposed update scheme, with appropriate local numerical support, provides better accuracy compared to the best possible polyhedral approximations and previous learning based methods. We introduce a trained solver which is third order accurate, with quasi-linear complexity in the number of sampled points.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning