Intrinsic approaches to learning and computing on curved surfaces

PhD Thesis
R.T. Wiersma

Venue

PhD Thesis

Abstract

This dissertation develops intrinsic approaches to learning and computing on curved surfaces. Specifically, we work on three tasks: analyzing 3D shapes using convolutional neural networks (CNNs), solving linear systems on curved surfaces, and recovering appearance properties from curved surfaces using multi-view capture. We argue that we can find more efficient and better performing algorithms for these tasks by using intrinsic geometry.

Links

[PDF]

Tags

 Geometric Deep Learning  Point Clouds  Surface Networks  Rotation-Equivariance  Shape Classification  Shape Segmentation  Vector Calculus  Geometric Multigrid  Linear Solvers  Numerical methods  Geometry processing

Cite

@PhdThesis{WiersmaIntrinsic2024,
author = {Ruben Wiersma},
title = {Intrinsic approaches to learning and computing on curved surfaces},
school = {Delft University of Technology},
year = {2024},
}