Abstract. We address the problem of large scale place-of-interest recognition in cell phone images of urban scenarios. Here, we go beyond what has been shown in earlier approaches ...
We present an image guided pen-based suggestive interface for sketching 3D wireframe models. Rather than starting from a blank canvas, existing 2D images of similar objects serve ...
Steve Tsang, Ravin Balakrishnan, Karan Singh, Abhi...
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to i...
When constructing 3D geometry for use in cel animation, the reference drawings of the object or character often contain various view-specific distortions, which cannot be captured...
We introduce an approach to accurately detect and segment partially occluded objects in various viewpoints and scales. Our main contribution is a novel framework for combining obj...