Section: Other Grants and Activities
ANR project ROM
This is an ANR-funded "pre-industrial" project running for two years (2009-11). The coordinator is Duran Duboi, one of the leading French companies in (post-) production for movies and advertisement. The two academic partners are IRI Toulouse and PERCEPTION. The goal of the project is to develop tools for aiding the preparation of shooting sequences in complex settings, especially concerning a film camera that is moving during the shooting. A standard vision-based technique for generating special effects and other augmentations, is match-moving, with or without artificial markers. An important practical issue is that match-moving is typically performed off-line and if it fails, cumbersome manual work or even re-shooting becomes necessary. The tools we will develop will allow an efficient preparation of a shooting, by analyzing the scene before the shooting and automatically judging the feasibility of match-moving; if the feasibility is judged as too low, a tool will suggest to the operator where to augment the scene with artificial markers that will help the match-moving.
ANR project FLAMENCO
FLAMENCO is a 3-year project that has started on January 1, 2007. This project deals with the challenges of spatio-temporal scene reconstruction from several video sequences, i.e. from images captured from different viewpoints and at different time instants. This project tackles the following three important factors which limit the major problems in computer vision so far:
the computational time / the poor resolution of the models: the acquisition of video sequences from multiple cameras generates a very large amount of data, which makes the design of efficient algorithms very important. The high computational cost of existing methods has limited the spatial resolution of the reconstruction and has allowed to handle video sequences of a few seconds only, which is prohibitive in real applications.
the lack of spatio-temporal coherence: to our knowledge, none of the existing methods has been able to reconstruct coherent spatio-temporal models: Most methods build threedimensional models at each time step without taking advantage of the continuity of the motion and of the temporal coherence of the model. This issue requires elaborating new mathematical and algorithmic tools dedicated to four-dimensional representations (three space dimensions plus the time dimension).
the simplicity of the models: the information available in multiple video sequences of a scene are not restricted to geometry and motion. Most reconstruction methods disregard such information as the illumination of the scene, and the reflectance, the materials and the textures of the objects. Our goal is to build more exhaustive models, by automatically estimating these parameters concurrently to geometry and motion. For example, in augmented reality, reflectance properties allow to synthesize novel views with higher photo-realism.
In this project, we are collaborating with the CERTIS laboratory (Ecole Nationale des Ponts et Chaussees) and the PRIMA group (INRIA Rhone-Alpes) via Frederic Devernay.
The team members directly involved in this project are Peter Sturm, Emmanuel Prados (INRIA researchers) and Amael Delaunoy (PhD thesis).
GrimDev is an ADT (Action de Developpement Technologique) proposed in the context of the Grimage interactive and immersive platform. The objective of GrimDev is to organize and manage software developements around the Grimage platform in order to ensure their reusabilities and durations. GrimDev was proposed by the Perception team and involves the following teams from INRIA Grenoble Rhône-Alpes: Perception, Evasion, Moais and SED.