We develop a local image-correspondence algorithm which performs well near occluding boundaries. Unlike traditional robust methods, our method can find correspondences when the on...
Matrix factorization has many applications in computer vision. Singular Value Decomposition (SVD) is the standard algorithm for factorization. When there are outliers and missing ...
This paper presents a new algorithm for the problem of robust subspace learning (RSL), i.e., the estimation of linear subspace parameters from a set of data points in the presence...
Robust integration of range images is an important task for building high-quality 3D models. Since range images, and in particular range maps from stereo vision, may have a substa...
Model-based image interpretation extracts high-level information from images using a priori knowledge about the object of interest. The computational challenge in model fitting is...