Geometry Interpolation
Deep Form Finding / AAG 2018
Geometry interpolation - Deep form finding workshop at AAG2018 - Advances in Architectural Geometry. Chalmers University, Gothenburg.
We are witnessing a revolution in the implementation of machine learning, and most specially neural networks, for solving problems of geometrical complexity and data manipulation inherent to pattern recognition of not only 2d images but also various types of manifolds such as 3d geometry and graphs – within a wide variety of geometrical domains.
Beyond the potential applications of tasks such as pattern classification and segmentation, the most promising techniques of neural networks in design disciplines rely on the ability for these type of models to become generative.
On this premise, we imparted a 2-day workshop at the AAG2018 conference, on the interpolation of building types using deep variational autoencoders.
The proceedings of this work are described in our 2019 paper Deep Form Finding. Geometry Interpolation with Variational Autoencoders, ECAADE Porto 2019.
Geometry interpolation (detail) - Deep form finding workshop at AAG2018 - Advances in Architectural Geometry. Chalmers University, Gothenburg.
About us
CV
Structural Engineering Geometry
Image Processing
Geometry Interpolation / AAG 2018
Publications
Contact
Sofia Project