Exploring Generative 3D Shapes Using Autoencoder Networks

AbstractWe propose a new algorithm for converting unstructured triangle meshes into ones with a consistent topology for machine learning applications. We combine the orthogonal depth map computation and the shrink wrapping approach to efficiently and robustly parameterize the triangle geometry regardless of imperfections such as inverted faces, holes, and self-intersections. The converted mesh is consistently and compactly parameterized and thus is suitable for machine learning. We use an autoencoder network to extract the manifold of shapes in the same category to explore and synthesize a variety of shapes. Furthermore, we introduce a direct manipulation interface to navigate the synthesis. We demonstrate our approach with over one thousand car shapes represented in unstructured triangle meshes.

Download publication

Related Resources

See what’s new.



Exploring Additive Manufacturing with Autodesk Research

Exploring the rapidly evolving world of additive manufacturing and how…



As-Killing-as-possible vector fields for planar deformation

Cartoon animation, image warping, and several other tasks in…



The Parametric Human Project: Building a Probabilistic Atlas of Human Anatomy

The Parametric Human Project (PHP) is an academic and industrial…



Position Statement: Design Studio Culture in HCI

In defining a virtual design studio culture (from now I will call it a…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us