DDGan project, Digital Design Generative Adversarial Networks

We are proud to present the result of the collaboration between AIRI, AImageLab and Digital Design: the DDGan project, Digital Design Generative Adversarial Networks, a patented artificial intelligence system for the creation of digital images for surface printing.

The system, during the training phase, analyzes fragments of scans of different natural materials (selected by designers), such as marble or precious woods, understanding their specific characteristics and distinctive elements. At the end of this phase, the neural network is able to generate new images, highly realistic and indistinguishable from the real materials. Starting from the image of a material, therefore, it is possible to obtain many other images very similar, but never equal to each other by composing a potentially infinite set of graphics.

This type of system represents a breakthrough for the industry, as it is able to operate images in a creative way opening the door to new incredible scenarios. Not only that, this also allows much less material to be scanned, making the graphics capture process much more environmentally friendly.

Here is it possible to see a short video of the project.