205 views166 votes16 years 7 months ago CVPR 2005»
Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspond...
169 views173 votes16 years 7 months ago CVPR 2006»
The wide availability of GPS sensors is changing the landscape in the applications of structure from motion techniques for localization. In this paper, we study the problem of est...
196 views152 votes16 years 7 months ago CVPR 2006»
Many computer vision applications, such as scene analysis and medical image interpretation, are ill-suited for traditional classification where each image can only be associated w...
208 views138 votes16 years 7 months ago CVPR 2006»
Illumination inconsistencies cause serious problems for classical computer vision applications such as tracking and stereo matching. We present a new approach to model illuminatio...
155 views153 votes16 years 7 months ago CVPR 2006»
The Fisher Linear Discriminant (FLD) is commonly used in pattern recognition. It finds a linear subspace that maximally separates class patterns according to Fisher's Criteri...
210 views148 votes16 years 7 months ago CVPR 2008»
Histograms represent a popular means for feature representation. This paper is concerned with the problem of exhaustive histogram-based image search. Several standard histogram co...
178 views166 votes16 years 7 months ago CVPR 2008»
We present a theoretical analysis for characterizing the shadows cast by a point light source given its relative position to the camera. In particular, we analyze the epipolar geo...
169 views160 votes16 years 7 months ago CVPR 2008»
The goal of image categorization is to classify a collection of unlabeled images into a set of predefined classes to support semantic-level image retrieval. The distance measures ...
171 views170 votes16 years 7 months ago ICCV 2005»
Geometric reconstruction problems in computer vision are often solved by minimizing a cost function that combines the reprojection errors in the 2D images. In this paper, we show t...
162 views156 votes16 years 7 months ago ICCV 2005»
This paper presents a new surface content completion framework that can restore both shape and appearance from scanned, incomplete point set inputs. First, the geometric holes can...