Results 11  20
of
11,762
Recovering 3D Human Pose from Monocular Images
"... We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body parts in the image. Instead, it recovers pose by direct nonlinear regression against shape descrip ..."
Abstract

Cited by 261 (0 self)
 Add to MetaCart
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body parts in the image. Instead, it recovers pose by direct nonlinear regression against shape
Orientifolds and Mirror symmetry
, 2003
"... We study parity symmetries and crosscap states in classes of N = 2 supersymmetric quantum field theories in 1+1 dimensions, including nonlinear sigma models, gauged WZW models, LandauGinzburg models, and linear sigma models. The parity anomaly and its cancellation play important roles in many of t ..."
Abstract

Cited by 271 (11 self)
 Add to MetaCart
We study parity symmetries and crosscap states in classes of N = 2 supersymmetric quantum field theories in 1+1 dimensions, including nonlinear sigma models, gauged WZW models, LandauGinzburg models, and linear sigma models. The parity anomaly and its cancellation play important roles in many
Nonlinear Anisotropic Filtering Of MRI Data
, 1992
"... Despite significant improvements in image quality over the past several years, the full exploitation of magnetic resonance image (MRI) data is often limited by low signal to noise ratio (SNR) or contrast to noise ratio (CNR). In implementing new MR techniques, the criteria of acquisition speed and i ..."
Abstract

Cited by 198 (16 self)
 Add to MetaCart
. In contrast to acquisitionbased noise reduction methods we propose a postprocess based on anisotropic diffusion. Extensions of this new technique support 3D and multiecho MRI, incorporating higher spatial and spectral dimensions. The procedure overcomes the major drawbacks of conventional filter methods
Recovering 3D Shape and Motion from Image Streams using NonLinear Least Squares
, 1993
"... The simultaneous recovery of 3D shape and motion from image sequences is one of the more difficult problems in computer vision. Classical approaches to the problem rely on using algebraic techniques to solve for these unknowns given two or more images. More recently, a batch analysis of image stream ..."
Abstract

Cited by 215 (33 self)
 Add to MetaCart
The simultaneous recovery of 3D shape and motion from image sequences is one of the more difficult problems in computer vision. Classical approaches to the problem rely on using algebraic techniques to solve for these unknowns given two or more images. More recently, a batch analysis of image
A Toolkit for Analyzing Nonlinear Dynamic Stochastic Models Easily
"... Often, researchers wish to analyze nonlinear dynamic discretetime stochastic models. This chapter provides a toolkit for solving such models easily, building on loglinearizing the necessary equations characterizing the equilibrium and solving for the recursive equilibrium law of motion with the me ..."
Abstract

Cited by 216 (2 self)
 Add to MetaCart
Often, researchers wish to analyze nonlinear dynamic discretetime stochastic models. This chapter provides a toolkit for solving such models easily, building on loglinearizing the necessary equations characterizing the equilibrium and solving for the recursive equilibrium law of motion
The Relaxation Schemes for Systems of Conservation Laws in Arbitrary Space Dimensions
 Comm. Pure Appl. Math
, 1995
"... We present a class of numerical schemes (called the relaxation schemes) for systems of conservation laws in several space dimensions. The idea is to use a local relaxation approximation. We construct a linear hyperbolic system with a stiff lower order term that approximates the original system with ..."
Abstract

Cited by 250 (21 self)
 Add to MetaCart
with a small dissipative correction. The new system can be solved by underresolved stable numerical discretizations without using either Riemann solvers spatially or a nonlinear system of algebraic equations solver temporally. Numerical results for 1D and 2D problems are presented. The second order
Autocalibration and the absolute quadric
 in Proc. IEEE Conf. Computer Vision, Pattern Recognition
, 1997
"... We describe a new method for camera autocalibration and scaled Euclidean structure and motion, from three or more views taken by a moving camera with fixed but unknown intrinsic parameters. The motion constancy of these is used to rectify an initial projective reconstruction. Euclidean scene structu ..."
Abstract

Cited by 248 (7 self)
 Add to MetaCart
structure is formulated in terms of the absolute quadric — the singular dual 3D quadric ( rank 3 matrix) giving the Euclidean dotproduct between plane normals. This is equivalent to the traditional absolute conic but simpler to use. It encodes both affine and Euclidean structure, and projects very simply
Generalization Of An Inequality By Talagrand, And Links With The Logarithmic Sobolev Inequality
 J. Funct. Anal
, 2000
"... . We show that transport inequalities, similar to the one derived by Talagrand [30] for the Gaussian measure, are implied by logarithmic Sobolev inequalities. Conversely, Talagrand's inequality implies a logarithmic Sobolev inequality if the density of the measure is approximately logconcave, ..."
Abstract

Cited by 244 (12 self)
 Add to MetaCart
. Main results 5 3. Heuristics 11 4. Proof of Theorem 1 18 5. Proof of Theorem 3 24 6. An application of Theorem 1 30 7. Linearizations 31 Appendix A. A nonlinear approximation argument 35 References 36 1. Introduction Let M be a smooth complete Riemannian manifold of dimension n, with the geodesic
A Pyramid Approach to SubPixel Registration Based on Intensity
, 1998
"... We present an automatic subpixel registration algorithm that minimizes the mean square intensity difference between a reference and a test data set, which can be either images (2D) or volumes (3D). It uses an explicit spline representation of the images in conjunction with spline processing, and ..."
Abstract

Cited by 237 (18 self)
 Add to MetaCart
, and is based on a coarsetofine iterative strategy (pyramid approach). The minimization is performed according to a new variation (ML*) of the MarquardtLevenberg algorithm for nonlinear leastsquare optimization. The geometric deformation model is a global 3D affine transformation that can be optionally
Fast Computation of Generalized Voronoi Diagrams Using Graphics Hardware
, 1999
"... We present a new approach for computing generalized 2D and 3D Voronoi diagrams using interpolationbased polygon rasterization hardware. We compute a discrete Voronoi diagram by rendering a three dimensional distance mesh for each Voronoi site. The polygonal mesh is a boundederror approximation of ..."
Abstract

Cited by 234 (26 self)
 Add to MetaCart
of a (possibly) nonlinear function of the distance between a site and a 2D planar grid of sample points. For each sample point, we compute the closest site and the distance to that site using polygon scanconversion and the Zbuffer depth comparison. We construct distance meshes for points, line
Results 11  20
of
11,762