Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Future Machine Vision applications have to cope with 3D non-rigid objects. One such application is 3D pose estimation of cactus leaves, which is the topic in this paper. We apply ...
Thomas B. Moeslund, Michael Aagaard, Dennis Lerche
Abstract. We present a data-driven shape model for reconstructing human body models from one or more 2D photos. One of the key tasks in reconstructing the 3D model from image data ...
Abstract. This work focuses on characterizing scenery images. We semantically divide the objects in natural landscape scenes into background and foreground and show that the shapes...
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3...