Sciweavers

171 search results - page 1 / 35
» Accurate Real-Time Disparity Estimation with Variational Met...
Sort
View
ISVC
2009
Springer
14 years 5 months ago
Accurate Real-Time Disparity Estimation with Variational Methods
Estimating the disparity field between two stereo images is a common task in computer vision, e.g., to determine a dense depth map. Variational methods currently are among the mos...
Sergey Kosov, Thorsten Thormählen, Hans-Peter...
IJCV
2006
227views more  IJCV 2006»
13 years 11 months ago
A Multigrid Platform for Real-Time Motion Computation with Discontinuity-Preserving Variational Methods
Variational methods are among the most accurate techniques for estimating the optic flow. They yield dense flow fields and can be designed such that they preserve discontinuities, ...
Andrés Bruhn, Joachim Weickert, Timo Kohlbe...
PCM
2005
Springer
179views Multimedia» more  PCM 2005»
14 years 4 months ago
Real-Time Stereo Using Foreground Segmentation and Hierarchical Disparity Estimation
Abstract. We propose a fast disparity estimation algorithm using background registration and object segmentation for stereo sequences from fixed cameras. Dense background disparit...
Hansung Kim, Dong Bo Min, Kwanghoon Sohn
CVPR
2009
IEEE
15 years 3 months ago
Real-Time Learning of Accurate Patch Rectification
Recent work [5, 6] showed that learning-based patch rectification methods are both faster and more reliable than affine region methods. Unfortunately, their performance improveme...
Stefan Hinterstoisser, Oliver Kutter, Nassir Navab...
DAGM
2005
Springer
14 years 4 months ago
Optic Flow Goes Stereo: A Variational Method for Estimating Discontinuity-Preserving Dense Disparity Maps
We present a novel variational method for estimating dense disparity maps from stereo images. It integrates the epipolar constraint into the currently most accurate optic flow met...
Natalia Slesareva, Andrés Bruhn, Joachim We...