Worldwide Sites

You have been detected as being from . Where applicable, you can see country-specific product information, offers, and pricing.

Change country/language X

  • United States

    We have redirected you to an equivalent page on your local site where you can see local pricing and promotions and purchase online.

    Stay on our U.S. site

Keyboard ALT + g to toggle grid overlay

Exploring Generative 3D Shapes Using Autoencoder Networks

Nobuyuki Umetani

ACM SIGGRAPH Asia - Technical Briefs Program
2017

Exploring Generative 3D Shapes Using Autoencoder Networks (1:24 min.)

Video title (x:xx min.)

Abstract

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.

Related Publications

Related Projects

Heading

Descriptive text. Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt magna aliqua in reprehenderit.

Heading

Descriptive text. Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt magna aliqua in reprehenderit.

Heading

Descriptive text. Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt magna aliqua in reprehenderit.