We present a robust method for 3D reconstruction of closed surfaces from sparsely sampled parallel contours. A solution to this problem is especially important for medical segment...
Recognition of specular objects is particularly difficult because their appearance is much more sensitive to lighting changes than that of Lambertian objects. We consider an appr...
Abstract. In this paper, we address the problem of computing a canonical representation of an n-dimensional combinatorial map. To do so, we define two combinatorial map signatures...
In this paper a computational model called dynamic medial axis (DMA) is proposed to describe the internal evolution of planar shapes. To define the DMA, a symbolic representation ...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...