20230043409. SYSTEMS AND METHODS FOR SYNTHETIC IMAGE GENERATION simplified abstract (THE BOEING COMPANY)

From WikiPatents
Jump to navigation Jump to search

SYSTEMS AND METHODS FOR SYNTHETIC IMAGE GENERATION

Organization Name

THE BOEING COMPANY

Inventor(s)

Amir Afrasiabi of University Place WA (US)

SYSTEMS AND METHODS FOR SYNTHETIC IMAGE GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230043409 titled 'SYSTEMS AND METHODS FOR SYNTHETIC IMAGE GENERATION

Simplified Explanation

The abstract describes an image generation system that can generate synthetic photorealistic images of a target object based on a 3D CAD model. Here are the key points:

  • The system receives a 3D CAD model of a target object.
  • It generates augmented CAD models of the target object, each corresponding to a different attribute class.
  • Each augmented CAD model includes a set of 2D model images.
  • The system uses a generative adversarial network (GAN) with generators and discriminators.
  • The data sets corresponding to the attribute classes are input into the GAN.
  • The generators in the GAN generate synthetic photorealistic images of the target object.
  • The synthetic images include attributes based on the data sets of the attribute classes.
  • The system outputs the synthetic photorealistic images of the target object.

Potential applications of this technology:

  • Product design and visualization: The system can generate realistic images of products based on CAD models, allowing designers to visualize and showcase their designs before manufacturing.
  • Virtual reality and gaming: The synthetic images can be used to create immersive virtual environments or realistic game graphics.
  • Advertising and marketing: The system can generate high-quality images of products for promotional materials, catalogs, or online advertisements.

Problems solved by this technology:

  • Time and cost: Generating photorealistic images manually can be time-consuming and expensive. This system automates the process, saving time and resources.
  • Visualization limitations: CAD models may not accurately represent the final appearance of an object. This system generates realistic images that provide a better visualization of the object.

Benefits of this technology:

  • Realism: The synthetic images generated by the system are photorealistic, providing a high level of realism.
  • Customization: By generating images with different attribute classes, the system allows for customization and exploration of various design options.
  • Efficiency: The automated generation process saves time and resources compared to manual image creation.


Original Abstract Submitted

an image generation system is provided to: receive a 3d cad (computer aided design) model comprising 3d model images of a target object; based on the 3d cad model of the target object, generate augmented cad models of the target object comprising data sets, each data set respectively corresponding to an associated one of a plurality of attribute classes, each data set comprising a plurality of 2d model images; input the data sets into a generative adversarial network comprising generators respectively corresponding to the plurality of attribute classes and discriminators respectively corresponding to the generators; generate synthetic photorealistic images of the target object using the generators, the synthetic photorealistic images including attributes in accordance with the data sets corresponding to the plurality of attribute classes; and output the synthetic photorealistic images of the target object.