Affiliation:
1. School of Computer Science and Engineering, Vellore Institute of Technology, India
2. School of Computing, SRM Institute of Science and Technology, India
Abstract
A generative adversarial network (GAN) is a generative model that is able to generate fresh content by using several deep learning techniques together. Due to its fascinating applications, including the production of synthetic training data, the creation of art, style-transfer, image-to-image translation, etc., the topic has gained a lot of attraction in the machine learning community. GAN consists of two networks: the generator and the discriminator. The generator will make an effort to create phony samples in an effort to trick the discriminator into thinking they are real samples. In order to distinguish generated samples from both actual and fraudulent samples, the discriminator will strive to do so. The main motive of this chapter is to make use of several types of GANs like StyleGANs, cycle GANs, SRGANs, and conditional GANs to generate various animated characters of different art styles with optimal attractive scores, which can make a huge contribution in the entertainment and media sector.
Reference32 articles.
1. Secondary attachments and adolescent self concept
2. Learning Feature Representations with K-Means
3. Denton, E., Chintala, S., Szlam, A., & Fergus, R. (2015). Deep generative image models using a laplacian pyramid of adversarial networks.arXiv preprint arXiv:1506.05751.
4. Texture synthesis by non-parametric sampling
5. Example-based super-resolution
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Unlocking Insights;Advances in Computational Intelligence and Robotics;2023-12-01
2. Inferring Personality From Social Media User Behaviors Using Dense Net Convolutional Neural Networks;Advances in Computational Intelligence and Robotics;2023-12-01