20230045937. GENERATIVE SYSTEM FOR THE CREATION OF DIGITAL IMAGES FOR PRINTING ON DESIGN SURFACES simplified abstract (DIGITAL DESIGN S.R.L.)

From WikiPatents
Jump to navigation Jump to search

GENERATIVE SYSTEM FOR THE CREATION OF DIGITAL IMAGES FOR PRINTING ON DESIGN SURFACES

Organization Name

DIGITAL DESIGN S.R.L.

Inventor(s)

Rita Cucchiara of Fiorano Modenese (IT)

Simone Calderara of Fiorano Modenese (IT)

Fabio Lanzi of Fiorano Modenese (IT)

Andrea Mariani of Fiorano Modenese (IT)

Elena Pellesi of Fiorano Modenese (IT)

GENERATIVE SYSTEM FOR THE CREATION OF DIGITAL IMAGES FOR PRINTING ON DESIGN SURFACES - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230045937 titled 'GENERATIVE SYSTEM FOR THE CREATION OF DIGITAL IMAGES FOR PRINTING ON DESIGN SURFACES

Simplified Explanation

The abstract describes a system for generating digital images for printing on design surfaces. It includes a training dataset of sample images, a generative adversarial network (GAN) with a generator and a discriminator. The generator takes in noise as input and is trained to produce new images suitable for printing on design surfaces. The discriminator is trained to compare and distinguish the new images generated by the generator with the sample images in the training dataset.

  • A training dataset of sample images is used to train the generative system.
  • The generative adversarial network (GAN) consists of a generator and a discriminator.
  • The generator takes in noise as input and learns to generate new images for printing on design surfaces.
  • The discriminator is trained to differentiate between the new artificially generated images and the sample images in the training dataset.

Potential Applications

  • Customized printing on design surfaces such as fabrics, wallpapers, or other materials.
  • Rapid generation of unique and visually appealing designs for various products.
  • Streamlining the design process by automating the creation of digital images for printing.

Problems Solved

  • Manual creation of digital images for printing on design surfaces can be time-consuming and labor-intensive.
  • Difficulty in generating unique and visually appealing designs consistently.
  • Lack of automation in the design process can limit creativity and productivity.

Benefits

  • Efficient and automated generation of digital images for printing on design surfaces.
  • Ability to create a wide variety of unique and visually appealing designs.
  • Streamlined design process, saving time and effort for designers.


Original Abstract Submitted

a generative system for the creation of digital images for printing on design surfaces comprises a training dataset comprising a plurality of sample images for printing on design surfaces, a generative adversarial network comprising a generator and a discriminator, wherein the generator receives noise at input and is trained to generate at output starting from the noise a new artificially generated image adapted to be used for printing on design surfaces, and wherein the discriminator receives at input the new artificially generated image and is trained to compare and distinguish the new image generated by the sample images of the training dataset.