Sciweavers

ECCV
1994
Springer
16 years 4 months ago
Pose refinement of active models using forces in 3D
A new algorithm is described for refining the pose of a model of a rigid object, to conform more accurately to the image structure. Elemental 3D forces are considered to act on the...
Anthony D. Worrall, Geoffrey D. Sullivan, Keith D....
ECCV
1994
Springer
16 years 4 months ago
Stability and Likelihood of Views of Three Dimensional Objects
Daphna Weinshall, Michael Werman, Naftali Tishby
ECCV
1994
Springer
16 years 4 months ago
Active 3D Object Recognition using 3D Affine Invariants
Sven Vinther, Roberto Cipolla
ECCV
1994
Springer
16 years 4 months ago
Parameterfree Information-Preserving Surface Restoration
Abstract. In this paper wepresent an algorithm for parameterfree informationpreserving surface restoration. The algorithm is designed for 2.5D and 3D surfaces. The basic idea is to...
Uwe Weidner
104
Voted
ECCV
1994
Springer
16 years 4 months ago
Independent motion segmentation and collision prediction for road vehicles
This paper presents a method for doing motion segmentation for autonomous vehicles which drive on planar surfaces. There are two distinct types of independent motion that may occu...
David Sinclair, Boubakeur Boufama
113
Voted
ECCV
1994
Springer
16 years 4 months ago
Visual Tracking of High DOF Articulated Structures: an Application to Human Hand Tracking
Passive sensing of human hand and limb motion is important for a wide range of applications from human-computer interaction to athletic performance measurement. High degree of free...
James M. Rehg, Takeo Kanade
ECCV
1994
Springer
16 years 4 months ago
On the Enumerative Geometry of Aspect Graphs
Most of the work achieved thus far on aspect graphs has concentrated on the design of algorithms for computing the representation. After reviewing how the space of viewpoints can b...
Sylvain Petitjean
ECCV
1994
Springer
16 years 4 months ago
Face Recognition: the Problem of Compensating for Changes in Illumination Direction
A face recognition system must recognize a face from a novel image despite the variations between images of the same face. A common approach to overcoming image variations because...
Yael Moses, Yael Adini, Shimon Ullman
103
Voted
ECCV
1994
Springer
16 years 4 months ago
Canonic Representations for the Geometries of Multiple Projective Views
We show how a special decomposition of a set of two or three general projection matrices, called canonic enables us to build geometric descriptions for a system of cameras which a...
Quang-Tuan Luong, Thierry Viéville