Sciweavers

CVPR
2006
IEEE
13 years 10 months ago
Depth from Familiar Objects: A Hierarchical Model for 3D Scenes
We develop an integrated, probabilistic model for the appearance and three-dimensional geometry of cluttered scenes. Object categories are modeled via distributions over the 3D lo...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
CVPR
2006
IEEE
13 years 10 months ago
Nonlinear Mean Shift for Clustering over Analytic Manifolds
The mean shift algorithm is widely applied for nonparametric clustering in Euclidean spaces. Recently, mean shift was generalized for clustering on matrix Lie groups. We further e...
Raghav Subbarao, Peter Meer
CVPR
2006
IEEE
13 years 10 months ago
Combined Depth and Outlier Estimation in Multi-View Stereo
In this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes:...
Christoph Strecha, Rik Fransens, Luc J. Van Gool
CVPR
2006
IEEE
13 years 10 months ago
Globally Optimal Grouping for Symmetric Boundaries
Many natural and man-made structures have a boundary that shows certain level of bilateral symmetry, a property that has been used to solve many computer-vision tasks. In this pap...
Joachim S. Stahl, Song Wang
CVPR
2006
IEEE
13 years 10 months ago
Fast Variational Segmentation using Partial Extremal Initialization
In this paper we consider region-based variational segmentation of two- and three-dimensional images by the minimization of functionals whose fidelity term is the quotient of two...
Jan Erik Solem, Niels Chr. Overgaard, Markus Perss...
CVPR
2006
IEEE
13 years 10 months ago
Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
CVPR
2006
IEEE
13 years 10 months ago
A Generalized EM Approach for 3D Model Based Face Recognition under Occlusions
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3...
Michael De Smet, Rik Fransens, Luc J. Van Gool
CVPR
2006
IEEE
13 years 10 months ago
Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation
Part-based tree-structured models have been widely used for 2D articulated human pose-estimation. These approaches admit efficient inference algorithms while capturing the import...
Leonid Sigal, Michael J. Black
CVPR
2006
IEEE
13 years 10 months ago
Video Completion by Motion Field Transfer
Existing methods for video completion typically rely on periodic color transitions, layer extraction, or temporally local motion. However, periodicity may be imperceptible or abse...
Takaaki Shiratori, Yasuyuki Matsushita, Xiaoou Tan...
CVPR
2006
IEEE
13 years 10 months ago
Shape from Dynamic Texture for Planes
We propose a method for recovering the affine geometry of a dynamically textured plane from a video sequence taken by an uncalibrated, fixed, perspective camera. Some instances ...
Yaser Sheikh, Niels C. Haering, Mubarak Shah