This paper describes a novel algorithm for the efficient synthesis of high-quality virtual views from only two input images. The emphasis is on the recovery of continuity of objec...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any t...
This paper presents a novel method for reconstructing complex 3D objects with unknown topology using silhouettes extracted from image sequences. This method exploits the duality p...
Hand-drawn diagrams present a complex recognition problem. Elements of the diagram are often individually ambiguous, and require context to be interpreted. We present a recognitio...