This paper proposes a system to estimate the 3D position and velocity of vehicles, from images acquired with a monocular camera. Given image regions where vehicles are detected, Ga...
We present an algorithm to estimate the 3D pose (location
and orientation) of a previously unseen face from low-quality range images. The algorithm generates many pose candidates ...
Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images, attempting to improve accuracy by automatic unsupervised ...
We present a novel method to estimate an approximation of the reflectance characteristics of optically thick, homogeneous translucent materials using only a single photograph as ...
We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled tra...