3D Face modeling is still one of the biggest challenges in computer graphics. In this paper we present a novel framework that acquires the 3D shape, texture, pose and illumination...
Pattern detection problems require a separation between two classes, Target and Clutter, where the probability of the former is substantially smaller compared to that of the latte...
Visual tracking is a key component in many computer vision applications. Linear subspace techniques (e.g. eigentracking) are one of the most popular approaches to align templates ...
Jose Gonzalez-Mora, Nicolas Guil, Emilio L. Zapata...
In this paper we show that Ullman and Basri’s linear combination (LC) representation, which was originally proposed for alignment-based object recognition, can be used for outli...
Linear subspace methods that provide sufficient reconstruction of the data, such as PCA, offer an efficient way of dealing with missing pixels, outliers, and occlusions that often ...