10.80624/FK2/9WRHOH Sassen, Josua Josua Sassen https://orcid.org/0000-0002-8069-4713 University of Bonn Hildebrandt, Klaus Klaus Hildebrandt https://orcid.org/0000-0002-9196-3923 TU Delft Rumpf, Martin Martin Rumpf https://orcid.org/0000-0001-6049-9390 University of Bonn Wirth, Benedikt Benedikt Wirth https://orcid.org/0000-0003-0393-1938 University of Münster bonndata-sandbox 2023 Computer and Information Science Mathematical Sciences Sassen, Josua Josua Sassen University of Bonn 2023-06-26 2023-06-26 /forum?id=F_EhNDSamN 3748 49152128 8128 32128 8128 12939 49152128 49152128 10435 396 683806 49152128 16128 20131 210552 213488 text/markdown application/octet-stream application/octet-stream application/octet-stream application/octet-stream text/x-python application/octet-stream application/octet-stream application/octet-stream application/octet-stream image/png application/octet-stream application/octet-stream text/plain; charset=US-ASCII application/octet-stream application/octet-stream 1.0 Creative Commons Attribution-ShareAlike 4.0 International License. This dataset contains the Python code to compute samples on our shape space Freaky Torus of deformed tori, a synthetic shape space with factors S¹×S¹×T² The first factor, an S¹, controls the deformation of the latitudinal cross-section into a rotated ellipse. The next factor, another S¹, controls the deformation of the longitudinal cross-section into a rotated ellipse. The third factor, a two-dimensional flat torus T², controls the position of a bump on the deformed torus. Above, we visualize our synthetic shape space by demonstrating the effect of moving along the individual factors to the final shape. More details on the construction can be found in the appendix of the ICLR 2023 paper Parametrizing Product Shape Manifolds by Composite Networks. Additional to the code, we also include the exact dataset that we used for the results of our paper in the data folder.