W e address an open and hitherto neglected problem in computer vision, how to reconstruct the geometry of objects with arbitrary and possibly anisotropic bidirectional reflectance...
Sebastian Magda, David J. Kriegman, Todd Zickler, ...
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
We investigate the use of quasi-interpolating approximation schemes, to construct an estimate of an unknown function from its given discrete samples. We show theoretically and wit...
This paper reviews areas of active research in color image processing. Several open problems are mentioned and future directions for research are suggested.
We present a new method for compact representation of large image datasets. Our method is based on treating small patches from an image as matrices as opposed to the conventional ...