Geodesic Convolutional Shape Optimization
By Pierre Baqué, Edoardo Remelli, Franccois Fleuret, Pascal Fua. 2018
93 citations recorded by the source corpus.
Aerodynamic shape optimization has many industrial applications. Existing methods, however, are so computationally demanding that typical engineering practices are to either simply try a limited number of hand-designed shapes or restrict oneself to shapes that can be parameterized using only few degrees of freedom. In this work, we introduce a new way to optimize complex shapes fast and accurately. To this end, we train Geodesic Convolutional Neural Networks to emulate a fluidynamics simulator. The key to making this approach practical is remeshing the original shape using a polycube map, which makes it possible to perform the computations on GPUs instead of CPUs. The neural net is then used to formulate an objective function that is differentiable with respect to the shape parameters, which can then be optimized using a gradient-based technique. This outperforms state- of-the-art methods by 5 to 20% for standard problems and, even more importantly, our approach applies to cases that previous methods cannot handle.
Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Andreas Geiger
- L. Zampieri
- Julian Straub
- J. Park
- Nathanael Perraudin
- Tomasz Kacprzak
- Steven J. Lovegrove
- Michaël Defferrard
In Computer Graphics and Computer-Aided Design
- Andreas Geiger
- L. Zampieri
- Julian Straub
- J. Park
- Steven J. Lovegrove
- Peter R. Florence
- Richard A. Newcombe
- Michael Niemeyer
Citations in the corpus
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (2019, methodology): “Other recent works [3] use poly-cube mapping [51] for shape optimization.”
- Geometric Deep Learning for Volumetric Computational Fluid Dynamics (2019, methodology): “We rely on previous work by Baqué et al.[8] and follow-up developments in the context of EPFL’s DeepShape project.”
- DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications (2018, methodology): “Thanks to their versatility, graph neural networks have been used in a variety of tasks, such as identifying diseases from brain connectivity networks [61] or population graphs [62], designing drugs using molecular graphs [63], segmenting 3D point clouds [64], optimizing shapes to be aerodynamic [65”