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
2016
ExoSkin: On-Body FabricationThere is a long tradition for crafting wearable objects directly on…
2008
ViewCube: A 3D Orientation Indicator and ControllerLiterally hundreds of thousands of users of 2D computer-aided design…
1996
Ray Tracing in Non-Constant MediaIn this paper, we explore the theory of optical deformations due to…
2021
Collective Transport of Unconstrained Objects via Implicit Coordination and Adaptive ComplianceWe present a decentralized control algorithm for robots to aid in…
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