Sciweavers

223 search results - page 24 / 45
» Dealing with Multiple Motions in Optical Flow Estimation
Sort
View
DAGM
2009
Springer
15 years 2 months ago
Video Super Resolution Using Duality Based TV-L1 Optical Flow
Abstract. In this paper, we propose a variational framework for computing a superresolved image of a scene from an arbitrary input video. To this end, we employ a recently proposed...
Dennis Mitzel, Thomas Pock, Thomas Schoenemann, Da...
DAGM
2008
Springer
14 years 11 months ago
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly te...
Werner Trobin, Thomas Pock, Daniel Cremers, Horst ...
ECCV
2004
Springer
15 years 11 months ago
Parallel Variational Motion Estimation by Domain Decomposition and Cluster Computing
We present an approach to parallel variational optical flow computation on standard hardware by domain decomposition. Using an arbitrary partition of the image plane into rectangul...
Timo Kohlberger, Christoph Schnörr, Andr&eacu...
ICIG
2009
IEEE
14 years 7 months ago
Statistical Modeling of Optical Flow
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this...
Dongmin Ma, Véronique Prinet, Cyril Cassisa
CVPR
2005
IEEE
15 years 11 months ago
A Closed Form Solution to Direct Motion Segmentation
We present a closed form solution to the problem of segmenting multiple 2-D motion models of the same type directly from the partial derivatives of an image sequence. We introduce...
Dheeraj Singaraju, René Vidal