Sciweavers

ECCV
2002
Springer
14 years 6 months ago
Class-Specific, Top-Down Segmentation
In this paper we present a novel class-based segmentation method, which is guided by a stored representation of the shape of objects within a general class (such as horse images). ...
Eran Borenstein, Shimon Ullman
ECCV
2002
Springer
14 years 6 months ago
Robust Computer Vision through Kernel Density Estimation
Abstract. Two new techniques based on nonparametric estimation of probability densities are introduced which improve on the performance of equivalent robust methods currently emplo...
Haifeng Chen, Peter Meer
ECCV
2002
Springer
14 years 6 months ago
Constrained Flows of Matrix-Valued Functions: Application to Diffusion Tensor Regularization
Nonlinear partial differential equations (PDE) are now widely used to regularize images. They allow to eliminate noise and artifacts while preserving large global features, such as...
Christophe Chefd'Hotel, David Tschumperlé, ...
ECCV
2002
Springer
14 years 6 months ago
A Probabilistic Theory of Occupancy and Emptiness
This paper studies the inference of 3D shape from a set of ? noisy photos. We derive a probabilistic framework to specify what one can infer about 3D shape for arbitrarily-shaped, ...
Rahul Bhotika, David J. Fleet, Kiriakos N. Kutulak...
ECCV
2002
Springer
14 years 6 months ago
Computing the Physical Parameters of Rigid-Body Motion from Video
Abstract. This paper presents an optimization framework for estimating the motion and underlying physical parameters of a rigid body in free flight from video. The algorithm takes ...
Kiran S. Bhat, Steven M. Seitz, Jovan Popovic
ECCV
2002
Springer
14 years 6 months ago
Linear Pose Estimation from Points or Lines
Estimation of camera pose from an image of n points or lines with known correspondence is a thoroughly studied problem in computer vision. Most solutions are iterative and depend o...
Adnan Ansar, Konstantinos Daniilidis
ECCV
2002
Springer
14 years 6 months ago
Audio-Video Sensor Fusion with Probabilistic Graphical Models
Abstract. We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it...
Matthew J. Beal, Hagai Attias, Nebojsa Jojic
ECCV
2002
Springer
14 years 6 months ago
Symmetrical Dense Optical Flow Estimation with Occlusions Detection
Traditional techniques of dense optical flow estimation don't generally yield symmetrical solutions: the results will differ if they are
Javier Sánchez, Luis Álvarez, Rachid...