Robert Boschgmbh

Max-planck-gesellschaft Zur F&#xf6;rderung Der Wissenschaften E. V.

Margret Keuper

Kathrin Skubch

Csaba Domokos

Evgeny Levinkov

Amrutha Saseendran

Andreas Geiger

Bjoern Andres

A method for training a generator network that is configured to generate images with multiple objects. The method includes providing a set of training images, a generator network, and a discriminator network; drawing noise samples and target counts of objects; mapping, by the generator network, the noise samples and target counts of objects to generated images; randomly drawing images from a pool comprising generated images and training images; supplying the randomly drawn images to the discriminator network, thereby mapping them to a combination of: a decision whether the respective image is a training image or a generated image; optimizing discriminator parameters, optimizing generator parameters, and optimizing both the generator parameters and the discriminator parameters with the goal of improving the match between the predicted count of objects on the one hand, and the actual or target count of objects on the other hand.

Generator networks for generating images with predetermined counts of objects

Growing community of inventors

Mannheim, Germany

Margret Keuper