A Curvature and Density‐based Generative Representation of Shapes
Open Access
- 12 October 2020
- journal article
- research article
- Published by Wiley in Computer Graphics Forum
- Vol. 40 (1) , 38-53
Abstract
This paper introduces a generative model for 3D surfaces based on a representation of shapes with mean curvature and metric, which are invariant under rigid transformation. Hence, compared with existing 3D machine learning frameworks, our model substantially reduces the influence of translation and rotation. In addition, the local structure of shapes will be more precisely captured, since the curvature is explicitly encoded in our model. Specifically, every surface is first conformally mapped to a canonical domain, such as a unit disk or a unit sphere. Then, it is represented by two functions: the mean curvature half‐density and the vertex density, over this canonical domain. Assuming that input shapes follow a certain distribution in a latent space, we use the variational autoencoder to learn the latent space representation. After the learning, we can generate variations of shapes by randomly sampling the distribution in the latent space. Surfaces with triangular meshes can be reconstructed from the generated data by applying isotropic remeshing and spin transformation, which is given by Dirac equation. We demonstrate the effectiveness of our model on datasets of man‐made and biological shapes and compare the results with other methods.Keywords
Funding Information
- Core Research for Evolutional Science and Technology (JPMJCR17A1)
- Deutsche Forschungsgemeinschaft (SFB/TRR 109)
This publication has 25 references indexed in Scilit:
- FLASH: Fast Landmark Aligned Spherical Harmonic Parameterization for Genus-0 Closed Brain SurfacesSIAM Journal on Imaging Sciences, 2015
- Robust fairing via conformal curvature flowACM Transactions on Graphics, 2013
- Algorithms to automatically quantify the geometric similarity of anatomical surfacesProceedings of the National Academy of Sciences, 2011
- Spin transformations of discrete surfacesACM Transactions on Graphics, 2011
- Open Access Series of Imaging Studies: Longitudinal MRI Data in Nondemented and Demented Older AdultsJournal of Cognitive Neuroscience, 2010
- Highly accurate inverse consistent registration: A robust approachNeuroImage, 2010
- A Concise and Provably Informative Multi‐Scale Signature Based on Heat DiffusionComputer Graphics Forum, 2009
- Centroidal Voronoi Tessellations: Applications and AlgorithmsSIAM Review, 1999
- Bonnet pairs and isothermic surfacesDuke Mathematical Journal, 1998
- Regular homotopy classes of immersed surfacesTopology, 1985