We present an algorithm for color classification with explicit illuminant estimation and compensation. A Gaussian classifier is trained with color samples from just one training im...
Color is known to be highly discriminative for many object recognition tasks, but is difficult to infer from uncontrolled images in which the illuminant is not known. Traditional...
Trevor Owens, Kate Saenko, Trevor Darrell, Ayan Ch...
We present a novel method for inferring three-dimensional shape from a collection of defocused images. It is based on the observation that defocused images are the null-space of ce...
We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem a...
We describe a learning-based method for low-level vision problems--estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, m...