Future Frame Prediction Using Generative Adversarial Networks

Abstract

The ability of a human to anticipate what is going to happen in the near future given the current situation helps in making intelligent decisions about how to react in that situation. In this paper, we have developed multiple Deep Neural Network models, intending to generate the next frame in a sequence given previous frames. In recent years, Generative Adversarial Networks (GAN) have shown promising results in the field of image generation. Hence, in this paper, we aim to create and compare two Generative Adversarial Models created for Future Frame Prediction by combining GANs with convolutional neural networks, Long Short-Term Memory Networks, and Convolutional LSTM networks. Based on the state-of-the-art, we have tried to improve the results of our model both visually and numerically. The paper is summarized by comparing the outputs of our two models and then finally comparing them with previously developed models for this purpose and providing future scope for research. Both the models presented in this work perform well based on certain aspects of future frame prediction. The results presented in this paper are crucial in the field of future prediction, in fields such as robotics, autonomous driving, and autonomous agent development.