Accéder directement au contenu

Rémi Ronfard

6
Documents

Présentation

I am a research director at Inria, and the scientific leader of the Imagine team. I graduated from Mines Paris Tech in 1986, where I also got my PhD in 1991. I have conducted research in a variety of domains, from geometric design to 3D animation and computer vision. This includes work on non-manifold topology in CATIA (Dassault Systèmes, 1991), mesh LODs (IBM Research, 1992), digital cartoon storyboarding (INA, 1995), aesthetic surface design (IBM Research and Dassault Systèmes, 2000), video indexing (INA, 2000), action recognition and statistical analysis of image and film styles (INRIA 2002-2007). I was an expert in the international MPEG group from 1997 to 2000. In 2007, I joined Xtranormal Technologies in Montreal, where I became R&D director for virtual cinematography. My team created the patented “magicam” system, which was used to produce two million user-generated animation movies. I came back to INRIA in 2009 with a new research program devoted to “directing virtual worlds”. I helped to create the IMAGINE team in 2012, where I now lead the “narrative design” part of the project. Towards this goal, I investigate computational models of visual storytelling and movie-making. This leads to inspiring collaborations with the national film school (ENS Louis Lumière), Célestins Theatre in Lyon, University of Geneva, Bernard Stiegler’s Institut de Recherche et d’Innovation, and with companies UBICAST, Thalès-Angénieux and Binocle 3D. I have co-chaired international workshops on modeling people and human interaction (Beijing, 2005), 3-D cinematography (New York City, 2006; Banff, 2008; Providence, 2012), intelligent cinematography and editing (Quebec, 2014; Zurich, 2015) and computational models of narratives (Atlanta, 2015). I served as head of the “Geometry and Image” Department at Laboratoire Jean Kuntzmann, University of Grenoble from 2012 to 2016.
I am a Computer Science researcher with a rich experience in industry and academia in France and North America. I graduated from Mines Paris Tech in 1986, where I also got my PhD in 1991. I have conducted research in a variety of domains, from geometric design to 3D animation and computer vision. This includes work on non-manifold topology in CATIA (Dassault Systèmes, 1991), mesh LODs (IBM Research, 1992), digital cartoon storyboarding (INA, 1995), aesthetic surface design (IBM Research and Dassault Systèmes, 2000), video indexing (INA, 2000), action recognition and statistical analysis of image and film styles (INRIA 2002-2007). I was an expert in the international MPEG group from 1997 to 2000. In 2007, I joined Xtranormal Technologies in Montreal, where I became R&D director for virtual cinematography. My team created the patented “magicam” system, which was used to produce two million user-generated animation movies. I came back to INRIA in 2009 with a new research program devoted to “directing virtual worlds”. I helped to create the IMAGINE team in 2012, where I now lead the “narrative design” part of the project. Towards this goal, I investigate computational models of visual storytelling and movie-making. This leads to inspiring collaborations with the national film school (ENS Louis Lumière), Célestins Theatre in Lyon, University of Geneva, Bernard Stiegler’s Institut de Recherche et d’Innovation, and with companies UBICAST, Thalès-Angénieux and Binocle 3D. I have co-chaired international workshops on modeling people and human interaction (Beijing, 2005), 3-D cinematography (New York City, 2006; Banff, 2008; Providence, 2012), intelligent cinematography and editing (Quebec, 2014; Zurich, 2015) and computational models of narratives (Atlanta, 2015). I am currently serving as head of the “Geometry and Image” Department at Laboratoire Jean Kuntzmann, University of Grenoble.

Publications

edmond-boyer
Image document

Action Recognition from Arbitrary Views using 3D Exemplars

Daniel Weinland , Edmond Boyer , Rémi Ronfard
ICCV 2007 - 11th IEEE International Conference on Computer Vision, Oct 2007, Rio de Janeiro, Brazil. pp.1-7, ⟨10.1109/ICCV.2007.4408849⟩
Communication dans un congrès inria-00544741v1
Image document

Automatic Discovery of Action Taxonomies from Multiple Views

Daniel Weinland , Rémi Ronfard , Edmond Boyer
IEEE Conference on Computer Vision and Pattern Recognition (CVPR '06), Jun 2006, New York, United States. pp.1639--1645, ⟨10.1109/CVPR.2006.65⟩
Communication dans un congrès inria-00590216v1
Image document

Motion History Volumes for Free Viewpoint Action Recognition

Daniel Weinland , Rémi Ronfard , Edmond Boyer
Workshop on modeling People and Human Interaction (PHI'05), Oct 2005, Beijing, China
Communication dans un congrès inria-00590197v1