Many previous works on photometric stereo have shown how to recover the shape and reflectance properties of an object using multiple images taken under a fixed viewpoint and variab...
Abstract. We are aiming at extending the basic digital camera functionalities to the ability to simulate the flattening of a document, by virtually acting like a flatbed scanner....
The artificial neural networks that are used to recognize shapes typically use one or more layers of learned feature detectors that produce scalar outputs. By contrast, the comput...
Abstract. Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In t...
What methods can we use to help understand why users adopt certain use strategies, and how can we evaluate designs to anticipate and perhaps positively modify how users are likely...