Showing papers by "Edmond Boyer published in 2009"

Surface feature detection and description with applications to mesh matching

Abstract: In this paper we revisit local feature detectors/descriptors developed for 2D images and extend them to the more general framework of scalar fields defined on 2D manifolds. We provide methods and tools to detect and describe features on surfaces equiped with scalar functions, such as photometric information. This is motivated by the growing need for matching and tracking photometric surfaces over temporal sequences, due to recent advancements in multiple camera 3D reconstruction. We propose a 3D feature detector (MeshDOG) and a 3D feature descriptor (MeshHOG) for uniformly triangulated meshes, invariant to changes in rotation, translation, and scale. The descriptor is able to capture the local geometric and/or photometric properties in a succinct fashion. Moreover, the method is defined generically for any scalar function, e.g., local curvature. Results with matching rigid and non-rigid meshes demonstrate the interest of the proposed framework.

Efficient Polyhedral Modeling from Silhouettes

Abstract: Modeling from silhouettes is a popular and useful topic in computer vision. Many methods exist to compute the surface of the visual hull from silhouettes, but few address the problem of ensuring good topological properties of the surface, such as manifoldness. This article provides an efficient algorithm to compute such a surface in the form of a polyhedral mesh. It relies on a small number of geometric operations to compute a visual hull polyhedron in a single pass. Such simplicity enables the algorithm to combine the advantages of being fast, producing pixel-exact surfaces, and repeatably yield manifold and watertight polyhedra in general experimental conditions with real data, as verified with all datasets tested. The algorithm is fully described, its complexity analyzed and modeling results given.

Human Motion Tracking by Registering an Articulated Surface to 3D Points and Normals

Abstract: We address the problem of human motion tracking by registering a surface to 3-D data. We propose a method that iteratively computes two things: Maximum likelihood estimates for both the kinematic and free-motion parameters of an articulated object, as well as probabilities that the data are assigned either to an object part, or to an outlier cluster. We introduce a new metric between observed points and normals on one side, and a parameterized surface on the other side, the latter being defined as a blending over a set of ellipsoids. We claim that this metric is well suited when one deals with either visual-hull or visual-shape observations. We illustrate the method by tracking human motions using sparse visual-shape data (3-D surface points and normals) gathered from imperfect silhouettes.

Iterative mesh deformation for dense surface tracking

Abstract: In this paper we present a new method to capture the temporal evolution of a surface from multiple videos. By contrast to most current methods, we introduce an algorithm that uses no prior of the nature of tracked surface. In addition, it does not require sparse features to constrain the deformation but only relies on strictly geometric information : a target set of 3D points and normals. Our approach is inspired by the Iterative Closest Point algorithm but handles large deformations of non-rigid surfaces. To this end, a mesh is iteratively deformed while enforcing local rigidity with respect to the reference model. This rigidity is preserved by diffusing it on local patches randomly seeded on the surface. The iterative nature of the algorithm combined with the softly enforced local rigidity allows to progressively evolve the mesh to fit the target data. The proposed method is validated and evaluated on several standard and challenging surface data sets acquired using real videos.

Virtualization gate

Abstract: The virtual reality community developed solutions for immersion based on advanced display technologies, mainly head-mounted displays (HMDs) and immersive multi-projector environments like Caves. Though these environments provide an impressive sense of immersion, users are usually limited in the way they can interact with virtual objects. Their influence on the 3D world, including users appearance, is very limited, impairing the immersion experience. Limitations come from the ability to perceive data from the users. Usually in 3D environments, interactions rely on a 3D tracker providing the position, velocity and identification of a limited set of markers the user is equipped with. Avatars can be used to enforce the sense of presence, but they lack to provide detailed information about the actual user body position or visual appearance.

Remote and collaborative 3D interactions

Abstract: We present a framework for new 3D tele-immersion applications that allows collaborative and remote 3D interactions. This framework is based on a multiple-camera platform that builds, in real-time, 3D models of users. Such models are embedded into a shared virtual environment where they can interact with other users or purely virtual objects. 3D models encode geometric information that is plugged into a physical simulation for interactive purposes. They also encode photometric information through the use of mapped textures to ensure a good sense of presence. Experiments were conducted with two multiple-camera platforms, and the preliminary results demonstrate the feasibility of such environments.

Suivi de Surfaces par Déformations Itératives

Abstract: Dans cet article, nous nous interessons au suivi dans le temps d'une surface observee par plusieurs cameras. Nous proposons une nouvelle methode qui ne repose sur aucune hypothese a priori quant a la nature de la surface ou de ces deformations. La methode considere des donnees purement geometriques : les positions et les orientations sur la surface, et ne necessite donc pas d'informations photometriques qui s'averent parfois ambigues. Elle s'inspire de l'algorithme ICP qu'elle adapte au cas des deformations non rigides. Le principe est de deformer la surface de maniere iterative, d'un instant au suivant, tout en preservant la rigidite locale. Dans cet objectif, la surface est divisee en regions dont l'agencement sur la surface est contraint par la pose a l'instant precedent ainsi que par une pose de reference. Les resultats experimentaux sur plusieurs sequences reelles standard du domaine demontrent l'efficacite de cette approche a suivre des surfaces complexes.