GRAINS: Generative Recursive Autoencoders for INdoor Scenes

Rule-based systems for procedural generation of complex environments such as interiors, cities, and landscapes have been around for a while. Here is a novel data-driven approach to not only learn how objects interact with each other in order to be able to produce new arrangements but also perform conversion of 2D floor plans to 3D…Read More

Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

This is a really great example of not only how data-driven tools of the future might help enhance the creative process but also of how a machine learning problem can be broken down into smaller sub-models in order to aid interactivity and provide greater control. Authoring virtual terrains presents a challenge and there is a…Read More