Semi-automated texture synthesis from multi-scale inputs

As virtual worlds grow larger and more detailed, complex content generation is becoming a key issue for media production industries. Creating and populating these virtual scenes with various and detailed 3D entities coherent with their environment is a difficult and time-consuming task mainly based on manual authoring. Developing novel tools that are able to scale up to the increased demand is of central importance for media production industries e.g. video (serious) games, motion pictures industry, etc.
As pointed out by many artistic directors in the computer graphics industry, there is a strong demand for providing efficient computer algorithms to reduce manual editing tasks, that are directly linked to production costs. The goal of this project is to devise new algorithmic procedural tools for the semi-automatic generation of complex objects in real-time applications, tailored for rapid and large content authoring while maintaining a high level of artistic control over the result.

Faculty Supervisor:

Guillaume Gilet

Student:

Partner:

Ubisoft Toronto

Discipline:

Computer science

Sector:

Information and cultural industries; Manufacturing

University:

Université de Sherbrooke

Program: