Sciweavers

ICCV
2003
IEEE
15 years 1 months ago
Linear Multi-View Reconstruction of Points, Lines, Planes and Cameras using a Reference Plane
This paper presents a new linear method for reconstructing simultaneously 3D features (points, lines and planes) and cameras from many perspective views by solving a single linear...
Carsten Rother
ICCV
2003
IEEE
15 years 1 months ago
Unsupervised Image Translation
Rómer Rosales, Kannan Achan, Brendan J. Fre...
ICCV
2003
IEEE
15 years 1 months ago
Efficient, Robust and Accurate Fitting of a 3D Morphable Model
3D Morphable Models, as a means to generate images of a class of objects and to analyze them, have become increasingly popular. The problematic part of this framework is the regis...
Sami Romdhani, Thomas Vetter
ICCV
2003
IEEE
15 years 1 months ago
A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence
This paper presents a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multi-frame point correspondence is NP ...
Khurram Shafique, Mubarak Shah
ICCV
2003
IEEE
15 years 1 months ago
Learning a Classification Model for Segmentation
We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly m...
Xiaofeng Ren, Jitendra Malik
ICCV
2003
IEEE
15 years 1 months ago
A Bayesian Network Framework for Relational Shape Matching
A Bayesian network formulation for relational shape matching is presented. The main advantage of the relational shape matching approach is the obviation of the non-rigid spatial m...
Anand Rangarajan, James M. Coughlan, Alan L. Yuill...
ICCV
2003
IEEE
15 years 1 months ago
View-invariant Alignment and Matching of Video Sequences
In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. 3D epipolar geometry is used to eliminate the distortion generated ...
Cen Rao, Alexei Gritai, Mubarak Shah, Tanveer Fath...
ICCV
2003
IEEE
15 years 1 months ago
Using Temporal Coherence to Build Models of Animals
This paper describes a system that can build appearance models of animals automatically from a video sequence of the relevant animal with no explicit supervisory information. The ...
Deva Ramanan, David A. Forsyth
ICCV
2003
IEEE
15 years 1 months ago
Phenomenological Eigenfunctions for Image Irradiance
We present a framework for calculating low-dimensional bases to represent image irradiance from surfaces with isotropic reflectance under arbitrary illumination. By representing t...
Peter Nillius, Jan-Olof Eklundh