We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constel...
This paper proposes a new approach to 3D reconstruction of piecewise planar objects based on two image regularities, connectivity and perspective symmetry. First, we formulate the...
We present a system that constructs "implicit shape models" for classes of rigid 3D objects and utilizes these models to estimating the pose of class instances in single...
Graph cut image segmentation with intensity information alone is prone to fail for objects with weak edges, in clutter, or under occlusion. Existing methods to incorporate shape a...