Publication | ACM SIGGRAPH Asia – Technical Briefs Program 2017
Exploring Generative 3D Shapes Using Autoencoder Networks
Abstract
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 publicationRelated Resources
2024
XLB: A Differentiable Massively Parallel Lattice Boltzmann Library in PythonThis research introduces the XLB library, a scalable Python-based…
2014
Position-based Elastic RodsWe present a novel method to simulate complex bending and twisting of…
2011
Medusa: A Proximity-Aware Multi-touch TabletopWe present Medusa, a proximity aware multi-touch tabletop…
1993
A Marking Based Interface for Collaborative WritingWe describe a system to support a particular model of document…
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