3D new shape synthesis - Astraea-Software Co. LTD

3D new shape synthesis

Here we will introduce the 3D new shape synthesis technology developed by our company, a pioneer in the world.

What is 3D new shape synthesis?

3D new shape synthesis means that a properly trained 3D AI model blends feature vectors extracted from multiple shapes and automatically generates new shapes. We have developed a 3D AI model that can synthesize new 3D shapes.

Mechanism of 3D new shape synthesis

For example, you can create a new car body by blending their tastes well with multiple existing car bodies.

For the new shape synthesis, a network using Variational Autoencoder (VAE), a type of deep learning, is built to create new car body data, with multiple timings for adding feature expressions to the Decoder part of the VAE system to flavor the generated results.

First, get the features from each of the two body meshes. When creating a new car body, you can change the composition ratio and create a car body with a new taste.

Introducing a demo site for 3D new shape synthesis

We have a demo site for 3D new shape synthesis.

You can experience the new shape synthesis function of the car body on the demo site. Twelve car body models are prepared on the demo site, and you can choose the base and style respectively and synthesize a new car body. You can also specify the composition ratio of the base and style.

For example, select a family car as the base and a sports car as the style, and consider the concept design of the family car with a sports taste.

We will search for the style that users like while changing the composition ratio of the style car such as 20%, 40%, 60%, 80%.

Or change your style car to a classic car, for example, and consider which taste your users prefer. The left is a classic taste and the right is a sports taste.

It takes only a few seconds to synthesize these shapes, and you can study the design as the designer thinks. Because AI is able to recognize the 3D shape of the car body, it become possible to instantly synthesize the shape.