Technical University of Munich
School of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany
Fax: +49-89-289-17757
Mail:
Brief Bio
Matthias has joined the Research Group for Computer Vision and Pattern Recognition as a Ph.D. student in June 2013.
In spring 2015 he spent three month at the group of Prof. Alexander Bronstein at Tel Aviv University. From October 2017 until April 2018 Matthias did an internship at the Intel Visual Computing Lab under the supervision of Vladlen Koltun and René Ranftl. From April until Oktober 2018 he did an internship at Apple.
Research Interests
Non-Rigid Shape Analysis, Reconstruction, (Discrete) Differential Geometry, Variational Methods, Functional Analysis, Machine (possibly deep) Learning on non-euclidean data
Publications
Export as PDF, XML, TEX or BIB
Book Chapters
2016
[] Applying Random Forests to the Problem of Dense Non-rigid Shape Correspondence , Chapter in Perspectives in Shape Analysis, Springer, 2016.
Preprints
2016
[] Bayesian Inference of Bijective Non-Rigid Shape Correspondence , In arXiv preprint arXiv:1607.03425, 2016. ([slides])
Conference and Workshop Papers
2019
[] Shape Correspondence with Isometric and Non-Isometric Deformations , In 12th Eurographics Workshop on 3D Object Retrieval, 3DOR@Eurographics 2019, Genoa, Italy, May 5-6, 2019 (S Biasotti, G Lavoué, RC. Veltkamp, eds.), Eurographics Association, 2019.
2017
[] Efficient Deformable Shape Correspondence via Kernel Matching , In International Conference on 3D Vision (3DV), 2017. ([arxiv],[Code])
Oral Presentation [] Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space , In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. ([Code], also check the related github repository)
2014
[] Optimal Intrinsic Descriptors for Non-Rigid Shape Analysis , In British Machine Vision Conference (BMVC), 2014.
[] Dense Non-Rigid Shape Correspondence Using Random Forests , In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
Teaching
Lectures and Seminars
Winter 2018 - Seminar
Shape Analysis and Optimization (IN2107)
Seminar for computer science master students and mathematics master students (2h / 4 ECTS).
Summer 2017 - Lecture
Analysis of Three-Dimensional Shapes (IN2238)
Lecture for computer science master students (4h + 2h / 8 ECTS).
Winter 2016 - Seminar
Recent Advances in the Analysis of 3D Shapes (IN2107)
Seminar for computer science master students and mathematics bachelor and master students (2h / 4 ECTS).
Summer 2016 - Lecture
Analysis of Three-Dimensional Shapes (IN2238)
Lecture for computer science master students (4h + 2h / 8 ECTS).
Summer 2016 - Seminar
Recent Advances in the Analysis of 3D Shapes (IN2107)
Seminar for computer science master students and mathematics bachelor and master students (2h / 4 ECTS).
Summer 2015 - Lecture
Analysis of Three-Dimensional Shapes (IN2238)
Lecture for computer science master students (4h + 2h / 8 ECTS).
Summer 2015 - Seminar
Recent Advances in the Analysis of 3D Shapes (IN2107)
Seminar for computer science master students and mathematics bachelor and master students (2h / 4 ECTS).
Summer 2014 - Lecture (tutorials)
Analysis of Three-Dimensional Shapes (IN2238)
Lecture for computer science master students (2h + 1h / 4 ECTS).
Summer 2014 - Seminar
Recent Advances in the Analysis of 3D Shapes (IN2107)
Seminar for computer science master students and mathematics bachelor and master students (2h / 4 ECTS).
Winter 2013/2014 - Lecture (tutorials)
Machine Learning for Robotics and Computer Vision (IN3200)
Lecture for computer science master students (2h + 1h / 4 ECTS).
Bachelor/Master's Theses and Interdisciplinary Projects (IDP)
I offer Bachelor's and Master's theses as well as IDPs for Mathematics and Computer Science students on topics related to 3D Shape Analysis. I highly recommend to attend our yearly (Summer semester) lecture and/or seminar on 3D shape analysis before starting the thesis. Possible topics include
- Intrinsic symmetry detection
- Shape Analysis on point clouds
- Comparison of discrete representations of shapes
- Partial similarity between shapes
- Analysis of shape collections
- Global description of 3D shapes
- Discrete representations of 3D shapes
- Partial Differential Equations on 3D shapes
- Image processing on manifolds
- Interpreting correspondences as maps between function spaces
- Applying Machine Learning Techniques to 3D shape analysis
You are of course invited to propose your own topic.
Successfully defended works include:
| | 29.04.2016 Thomas Ströhle (Mathematics, MS) "Discrete Laplace-Beltrami Operators on Point Clouds" |
| | 23.10.2015 Zorah Lähner (Computer Science, MS) "The Space of Functional Maps" |
| | 07.10.2015 Thorsten Philipp (Mathematics, MS) "Learning Descriptors for Non-Rigid 3D Shapes" |