Publication | ACM SIGGRAPH Asia – Technical Briefs Program 2017

Exploring Generative 3D Shapes Using Autoencoder Networks


Exploring Generative 3D Shapes Using Autoencoder Networks

Nobuyuki Umetani

ACM SIGGRAPH Asia – Technical Briefs Program 2017

We 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



A Multi-cellular Developmental Representation for Evolution of Adaptive Spiking Neural Microcircuits in an FPGA

It has been shown that evolutionary and developmental processes can be…



Magic Desk: Bringing Multi-Touch Surfaces into Desktop Work

Despite the prominence of multi-touch technologies, there has been…



Development of Discrete Event System Specification (DEVS) Building Performance Models for Building Energy Design

The discrete event system specification (DEVS) is a formalism for…



Social Affordances: Understanding Technology Mediated Social Networks at Work

Computer-mediated communication (CMC) technology includes messaging…

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