Generation of Hilarious Animated Characters using GAN

Abstract

Now a days creating cartoon characters having animated features is quite interesting and challenging. It takes a lot of effort to sketch animated features to bring it to live. It takes time and requires specialized knowledge. It takes a lot of effort to build a cartoon character from scratch, and the end result is usually an ungainly design with low polygon intensity. This process can be simplified with the use of generative adversarial network (GAN) architecture, GAN can be trained using a library of cartoon images. GANs are made up of two networks: a generating network and a discriminator network. GANs have a lot of potential in the field of image processing due to deep networks' proclivity to create realistic images and the competitiveness of the training approach. This strategy appears to be a powerful tool for improving fuzzy photos. The basic concept underlying GAN is that it consists of a discriminator and a generator, two neural networks that compete in a zero-sum game.