We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
Modeling free-form shapes in 3D spaces based on strict physical laws require a considerable amount of computation time. Previous experiences with Cellular Automata demonstrated sub...
Abstract. In this paper, we present novel image-derived, invariant features that accurately capture both the geometric and color properties of an imaged object. These features can ...
Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations....
In this paper, we present a new approach to high quality 3D object reconstruction. Starting from a calibrated sequence of color images, the algorithm is able to reconstruct both t...