Sciweavers

1512 search results - page 20 / 303
» Learning Object Shape: From Drawings to Images
Sort
View
CORR
2011
Springer
222views Education» more  CORR 2011»
12 years 10 months ago
Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs
Abstract. We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled indep...
Nicolas Heess, Nicolas Le Roux, John M. Winn
ICCV
1998
IEEE
14 years 8 months ago
Wormholes in Shape Space: Tracking Through Discontinuous Changes in Shape
Existing object tracking algorithms generally use some form of local optimisation, assuming that an object's position and shape change smoothly over time. In some situations ...
Tony Heap, David Hogg
CVPR
2008
IEEE
14 years 8 months ago
Sparsity, redundancy and optimal image support towards knowledge-based segmentation
In this paper, we propose a novel approach to model shape variations. It encodes sparsity, exploits geometric redundancy, and accounts for the different degrees of local variation...
Salma Essafi, Georg Langs, Nikos Paragios
SIGGRAPH
1997
ACM
13 years 10 months ago
Object shape and reflectance modeling from observation
An object model for computer graphics applications should contain two aspects of information: shape and reflectance properties of the object. A number of techniques have been deve...
Yoichi Sato, Mark D. Wheeler, Katsushi Ikeuchi
ECCV
2002
Springer
14 years 8 months ago
Learning Shape from Defocus
We present a novel method for inferring three-dimensional shape from a collection of defocused images. It is based on the observation that defocused images are the null-space of ce...
Paolo Favaro, Stefano Soatto