← Search

Klaus Hildebrandt

2 accepted papers

2023

Parametrizing Product Shape Manifolds by Composite Networks

ICLR 2023top-25%

Parametrizations of data manifolds in shape spaces can be computed using the rich toolbox of Riemannian geometry. This, however, often comes with high computational costs, which raises the question if one can learn an efficient neural network approximation. We show that this is indeed possible for s…

2022

Deep Vanishing Point Detection: Geometric Priors Make Dataset Variations Vanish

CVPR 2022poster

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point det…

Cited by 28PDFcodeScholar