ECCV
2002
Springer
14 years 10 months ago
2002
Springer
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. This paper presents a theory for constructing and computing velocity-adapted scale-space filters for spatio-temporal image data. Starting from basic criteria in terms of ...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Specular reflections present difficulties for many areas of computer vision such as stereo and segmentation. To separate specular and diffuse reflection components, previous approa...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. This paper proposes a quasi-dense reconstruction from uncalibrated sequence. The main innovation is that all geometry is computed based on re-sampled quasi-dense correspo...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. Principal Component Analysis (PCA) is one of the most popular techniques for dimensionality reduction of multivariate data points with application areas covering many bra...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. Given the projection of a su cient numberof points it is possible to algebraically eliminate the camera parameters and obtain viewinvariant functions of image coordinates...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. Natural scenes consist of a wide variety of stochastic patterns. While many patterns are represented well by statistical models in two dimensional regions as most image s...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
This paper presents a geometric approach to recognizing smooth objects from their outlines. We define a signature function that associates feature vectors with objects and baseline...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
In this paper we propose an extension to the standard Markov Random Field (MRF) model in order to handle layers. Our extension, which we call a Factorial MRF (FMRF), is analogous t...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. Computing reflective symmetries of 2D and 3D shapes is a classical problem in computer vision and computational geometry. Most prior work has focused on finding the main ...