Mattull, William A.2020-09-142020-052020-01-082020Mattull, William A. 2020. Toward Improving Procedural Terrain Generation With GANs. Master's thesis, Harvard Extension School.https://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37365041The advance of Generative Adversarial Networks (GANs) are able to create new and meaningful outputs given arbitrary encodings for three dimensional terrain generation. Using a two-stage GAN network, this novel system takes the terrain heightmap as the first processing object, and then maps the real texture image onto the heightmap according to the learned network. The synthetic terrain image results perform well and are realistic. However, improvements can be made to generator stability during training.application/pdfvideo gamesterrain generation, heightmap, texture mapGenerative Adversarial Network, GAN, Artificial Intelligence, AI, Keras, Tensorflow, Neural Network, deep learning, image analysisThesis or Dissertation2020-09-14