Sciweavers

140 search results - page 15 / 28
» Discrete-Continuous Optimization for Large-scale Structure f...
Sort
View
ICCV
2009
IEEE
15 years 20 days ago
Bayesian selection of scaling laws for motion modeling in images
Based on scaling laws describing the statistical structure of turbulent motion across scales, we propose a multiscale and non-parametric regularizer for optic-flow estimation. R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
ICIP
2005
IEEE
14 years 1 months ago
Higher order polynomials, free form deformations and optical flow estimation
In this paper, we propose a novel technique to represent and recover optical flow through free form deformations. Such a technique is based on representing the motion field usin...
Konstantinos Karantzalos, Nikos Paragios
ICRA
2010
IEEE
142views Robotics» more  ICRA 2010»
13 years 6 months ago
Learning and planning high-dimensional physical trajectories via structured Lagrangians
— We consider the problem of finding sufficiently simple models of high-dimensional physical systems that are consistent with observed trajectories, and using these models to s...
Paul Vernaza, Daniel D. Lee, Seung-Joon Yi
NIPS
2001
13 years 9 months ago
Unsupervised Learning of Human Motion Models
This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatic...
Yang Song, Luis Goncalves, Pietro Perona
CVPR
2004
IEEE
14 years 9 months ago
Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences
In this paper, we propose a face reconstruction technique that produces models that not only look good when texture mapped, but are also metrically accurate. Our method is designe...
Miodrag Dimitrijevic, Slobodan Ilic, Pascal Fua