CVPR
2011
IEEE
13 years 9 days ago
2011
IEEE
We present novel approaches for fully automated extraction of tree-like tubular structures from 3-D image stacks. A 4-D Open-Curve Active Contour (Snake) model is proposed for sim...
CVPR
2011
IEEE
13 years 9 days ago
2011
IEEE
CVPR
2011
IEEE
13 years 9 days ago
2011
IEEE
From conventional wisdom and empirical studies of annotated data, it has been shown that visual statistics such as object frequencies and segment sizes follow power law distributi...
CVPR
2011
IEEE
13 years 9 days ago
2011
IEEE
Conventional non-blind image deblurring algorithms involve natural image priors and maximum a-posteriori (MAP) estimation. As a consequence of MAP estimation, separate pre-process...
CVPR
2011
IEEE
13 years 29 days ago
2011
IEEE
Establishing correspondences between two feature sets is a fundamental issue in computer vision, pattern recognition, and machine learning. This problem can be well formulated as g...
164
click to vote
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. Despite of this overflow of visual information, humans are extremely good...
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
We develop a dictionary learning method which is (i) online, (ii) enables overlapping group structures with (iii) non-convex sparsity-inducing regularization and (iv) handles the ...
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
Without specialized sensor technology or custom, multichip cameras, high dynamic range imaging typically involves time-sequential capture of multiple photographs. The obvious down...
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
Many object classes are primarily defined by their functions. However, this fact has been left largely unexploited by visual object categorization or detection systems. We propos...
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
In deflectometry, the shape of mirror objects is recovered from distorted images of a calibrated scene. While remarkably high accuracies are achievable, state-of-the-art methods ...