Ruben Wiersma, MSc

I am a third-year PhD student at the Computer Graphics and Visualization group at the University of Technology Delft. In my research I seek to connect computer graphics- and geometry processing techniques to applications in machine learning and painting analysis. I am advised by Dr. Klaus Hildebrandt and supervised by Prof. Dr. Elmar Eisemann and Prof. Dr. Joris Dik.

Personal webpage »

Master projects

I’m open to supervising Master students. Contact me (or one of my supervisors) if you’re interested in the following subjects:

  • Geometric Deep Learning: fundamentals and applications on meshes and point clouds
  • Graphics and Art: synthesis, analysis, rendering for paintings.
mark

PhD student
Room 5.W.740, Building 28
E-mail: <R.T.Wiersma_AT_tudelft.nl>

Publications

Publications in group repository »

DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

ACM Transactions on Graphics 41(4) (SIGGRAPH 2022)
[preprint][code][project page][doi]

Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D data. In this paper, we aim to construct anisotropic convolution layers that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce DeltaConv, a convolution layer that combines geometric operators from vector calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and match or improve on state-of-the-art approaches on several benchmarks, while also speeding up training and inference.

CNNs on Surfaces using Rotation-Equivariant Features

ACM Transactions on Graphics 39(4) (SIGGRAPH 2020)
[preprint][code][project page][doi]

This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a rotational ambiguity, which prevents a uniform alignment of these kernels on the surface. We propose a network architecture for surfaces that consists of vector-valued, rotation-equivariant features. The equivariance property makes it possible to locally align features, which were computed in arbitrary coordinate systems, when aggregating features in a convolution layer. The resulting network is agnostic to the choices of coordinate systems for the tangent spaces on the surface. We implement our approach for triangle meshes. Based on circular harmonic functions, we introduce convolution filters for meshes that are rotation-equivariant at the discrete level. We evaluate the resulting networks on shape correspondence and shape classifications tasks and compare their performance to other approaches.

Revealing unique inscriptions of a Nazi collaborator in Doodencel 601 of the Oranjehotel

Heritage Science (July 2020)
[doi]

During the Second World War the German occupants of the Netherlands made ample use of the Scheveningen prison near The Hague, popularly nicknamed the Oranjehotel. One former death cell in this infamous prison (Doodencel 601) has been preserved in its original condition, showing wartime inscriptions on the cell walls. Interestingly, a small section of the wall has been given an additional plaster layer, presumably covering inscriptions. Here, we report on the visualization of this enigmatic text, which so far had escaped the reach of historians.