We present a novel method for solving the challenging problem of generating 3D models of generic object categories from just one single un-calibrated image. Our method leverages t...
Min Sun, Shyam Sunder Kumar, Gary R. Bradski, Silv...
We address the structure-from-motionproblem in the context of head modeling from video sequences for which calibration data is not available. This task is made challenging by the ...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Efficient and accurate fitting of Active Appearance Models (AAM) is a key requirement for many applications. The most efficient fitting algorithm today is Inverse Compositiona...
This paper brings a novel method for three-dimensional reconstruction of surfaces that takes advantage of the symmetry resulting from alternating the positions of a camera and a l...