The goal of the project is to propose high-level techniques to assist artists in authoring and creating virtual worlds. This help will be provided as high-level tools that will support users in their tasks, without introducing any trade-off in the creative pipeline. This means that artists should not be limited by the introduction of such tools, and particularly, they should keep different levels of control. The project will rely on machine learning methods to predict detailed maps from sketches or coarse input maps.
This project has been submitted and funded by the CE23 committee of the ANR AAPG2020. The project number is ANR-20-CE23-0001.
The LIRIS lab (UMR5205), Origami and Imagine teams, has an internationally recognized expertise in virtual worlds modeling and generation. People involved: Eric Guérin, Eric Galin, Adrien Peytavie, Christian Wolf.
CIRAD is an EPIC specialized in agronomy and development. AMAP is a unit of CIRAD, recognized in the domain of aerial/satellite images analysis and segmentation up to plant and plant communities structure modeling. Peaple involved: Frédéric Borne, Marc Jaeger.
The industrial partner Ubisoft is a world-leading video games company that produces AAA games (Watch dogs, Ghost Recon). They will provide their know-how on the expression of industrial needs, the testing of solutions by expert artists and finally they will integrate the research results in their production pipelines. People involved: Thibault Coudeville, Simon Contraires, Benoît Martinez.
The University of Cape Town (UCT) has a history of collaboration with the LIRIS team. Particularly, this partner has a strong expertise in ecosystems simulation. People involved: James Gain, Konrad Kapp.