Learning and Inverse Procedural Modeling for Authoring Large virtual worlds – AMPLI

Virtual worlds are increasingly used in the entertainment industry to provide users with a unique and extraordinary experience, in which the quality and the extent of the world is central. This quality is usually obtained by resorting massively to artists, which is expensive and has obvious limitations. The goal of the project is to propose high-level techniques to help artists author and create virtual worlds by using a novel data-driven and machine learning approach. This will be done by high-level tools that will support users in their tasks, without any trade-off in the creative pipeline. The project will rely on machine learning methods and will cover a large variety of scene elements (terrains, vegetation, materials). The data will come from various origins (GIS data, from games, simulation, automatic segmentation). The consortium is composed of academics experts in virtual worlds modeling (LIRIS), a video game company (Ubisoft) and experts in vegetation modeling (CIRAD).