In this paper, we show how to reconstruct both 3D shape and 2D texture of a class of surfaces from a single perspective image. We consider the so-called the generalized cylindrica...
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting...
Improving coding and spatial pooling for bag-of-words based feature design have gained a lot of attention in recent works addressing object recognition and scene classification. ...
Many vision tasks are posed as either graph partitioning (coloring) or graph matching (correspondence) problems. The former include segmentation and grouping, and the latter inclu...