Deep understanding of mesh geometries for shape design
- Typ: Seminar (S)
- Lehrstuhl: KIT-Fakultäten - KIT-Fakultät für Informatik - Institut für Visualisierung und Datenanalyse - IVD Prautzsch
- Semester: WS 22/23
-
Ort:
Geb. 50.34
Raum 301
Mi. -
Zeit:
mittwochs 11:30 - 13:00
14-tägig
Beginn
02.11.2022
End
08.02.2023
Mi 02.11.2022
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
Mi 16.11.2022
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
Mi 30.11.2022
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
Mi 14.12.2022
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
Mi 11.01.2023
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
Mi 25.01.2023
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
Mi 08.02.2023
11:30 - 13:00
50.34 Raum 301
50.34 INFORMATIK, Kollegiengebäude am Fasanengarten (3. Obergeschoss)
-
Dozent:
Prof. Dr. Hartmut Prautzsch
Yijun Xu - LVNr.: 2400157
Point clouds and meshes (triangular, quadrilateral,...) are used to
model and to represent three-dimensional objects. Obtaining suitable
mesh representations and working with them in various applications
requires geometric knowledge of surface and shape properties. Recently
deep learning methods have been developed to achieve such tasks and the
new field of geometric deep learning has emerged.
In this seminar, papers from the field of geometric deep learning are
discussed as well as papers focusing on geometric properties needed for
example in architecture or fabrication of auxetic material that gives
predefined shapes from planar sheets.
Selected References for the seminar:
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Veličković
https://arxiv.org/abs/2104.13478 - Extracting Triangular 3D Models, Materials, and Lighting From Images
Jacob Munkberg, Jon Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, Thomas Müller, Sanja Fidler
https://arxiv.org/abs/2111.12503,
https://nvlabs.github.io/nvdiffrec/ - Learning Direction Fields for Quad Mesh Generation
Alexander Dielen, Isaak Lim, Max Lyon, Leif Kobbelt
Eurographics Symposium on Geometry Processing 2021
https://www.graphics.rwth-aachen.de/publication/03337/ - Mina Konakovic Lukovic: Turning Planar Materials Into Curved Structures
https://www.youtube.com/watch?v=hTalw-LuzB0 - Designing asymptotic geodesic hybrid gridshells
E. Schling, H. Wang, S. Hoyer, and H. Pottmann
Computer Aided Design 152 (2022)
https://www.geometrie.tuwien.ac.at/geom/ig/publications/asymgeogridshell/asymgeogridshell.pdf - Shape-morphing mechanical metamaterials
Caigui Jiang, Florian Rist, Hui Wang, Johannes Wallner, Helmut Pottmann
Computer Aided Design 143 (2022)
https://www.geometrie.tuwien.ac.at/geom/ig/publications/geommaterials/geommaterials.pdf - Computational design and optimization of quad meshes based on diagonal meshes
C. Jiang, C. Wang, E. Schling and H. Pottmann
Advances in Architectural Geometry 2020
https://www.geometrie.tuwien.ac.at/geom/ig/publications/aagdiagonalmeshes/aagdiagonalmeshes.pdf - Smooth polyhedral surfaces
F. Günther, C. Jiang, and H. Pottmann
Advances in Mathematics, 363, (2020)
http://arxiv.org/abs/1703.05318
Registration : yijun.xu@kit.edu
Please submit the following information:
- Seminar
- Name
- Matrikelnummer