We consider the problem of recognizing 3-D objects from 2-D images using geometric models and assuming different viewing angles and positions. Our goal is to recognize and localize...
This paper discusses ways of using a single panoramic image (captured by a rotating sensor-line camera having very-high spatial resolution) for the geometric shape recovery of a sh...
Point hierarchies are suitable for creating framecoherent animations of 3D models in non-photorealistic styles such as stippling, painterly and other artistic rendering. In this p...
In this paper, we present a new model-based approach for building 3-D models of vehicles from color video provided by a traffic surveillance camera. We incrementally build 3D mode...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...