Expressive 3D Modeling: User-centered models for seamless creation through gestures
Could digital media be turned into a tool, even more expressive and simpler to use than a pen, to convey and refine both static and dynamic 3D shapes? This would make shape design directly possible in virtual form, from early drafting to progressive refinement and finalization of an idea.
To this end, models for shape and motion need to be redefined from a user-centered perspective, and in particular embed the necessary knowledge to make them respond in an intuitive way to users actions.
In this talk, I will illustrate this methodology in three use cases: the creation of 3D models from 2D sketches, transfer operations that automatically adapt objects to another context, and virtual sculpture systems enabling to progressively edit and refine 3D content.
Marie-Paule Cani is a Professor of Computer Science at Grenoble University & Inria. She contributed over the years to a number of models for shapes and motion, such as implicit surfaces, multi-resolution physically-based animation methods and hybrid representations for real-time natural scenes. Following a long lasting interest for virtual sculpture, she has been recently searching for more efficient ways to create 3D contents such as combining sketch-based interfaces with user-centered 3D models. She received the Eurographics outstanding technical contributions award in 2011, an advanced grant from the ERC and a silver medal from CNRS in 2012 for this work. She was elected at Academia Europaea in 2013 and was granted the Informatics and Computational Sciences chair at Collège de France in 2014-2015. She represented Computer Graphics in the ACM Publication Board from 2011 to 2014 and is Associate editor of ACM Transactions on Graphics. Fellow of Eurographics since 2005, she is currently Vice-chair of the Eurographics association.