A step towards procedural terrain generation with GANs
arXiv:1707.03383v126 citations
AI Analysis
This work addresses terrain generation for video game developers, but it is incremental as it only presents a preliminary step without demonstrated outcomes.
The authors tackled procedural terrain generation for video games by proposing a first step using deep generative models trained on NASA satellite imagery, but no concrete results or numbers are provided.
Procedural terrain generation for video games has been traditionally been done with smartly designed but handcrafted algorithms that generate heightmaps. We propose a first step toward the learning and synthesis of these using recent advances in deep generative modelling with openly available satellite imagery from NASA.