Learning Unsigned Distance Fields to Simulate Brittle Fractures in Real-Time

Master Thesis (2026)
Author(s)

L.K. Zimmerhackl (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

P. Kellnhofer – Mentor (TU Delft - Computer Graphics and Visualisation)

L. Uzolas – Mentor (TU Delft - Computer Graphics and Visualisation)

K.A. Hildebrandt – Graduation committee member (TU Delft - Computer Graphics and Visualisation)

T.J. Viering – Graduation committee member (TU Delft - Pattern Recognition and Bioinformatics)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2026
Language
English
Graduation Date
15-01-2026
Awarding Institution
Delft University of Technology
Programme
['Computer Science']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In this thesis, we address the problem of learning mesh-specific, impulse-dependent fracture patterns in real time. Our approach is based on regressing a distance field over the mesh surface, encoding the proximity of each vertex to fracture lines, which is subsequently segmented into distinct pieces using graph-based methods such as watershed segmentation. The goal is to achieve real-time performance, which is something the current approach does not achieve for large meshes.

We evaluate different neural architectures, comparing a multilayer perceptron to DeltaConv, a graph convolutional model, and find that the MLP provides superior performance. In addition, we assess multiple segmentation strategies and identify watershed as the most effective, followed by hierarchical segmentation. We also find that the segmentation algorithms do not achieve real-time performance for large meshes.

These results highlight the potential of machine learning-based fracture simulations, but also indicate that distance field segmentation is not capable of real-time performance using our tested algorithms. This suggests that future work should focus on directly learning the labels rather than relying on distance fields as an intermediary representation in real-time scenarios.

Files

Thesis_file.pdf
(pdf | 12.5 Mb)
License info not available