We propose statistical learning methods for approximating implicit surfaces and computing dense 3D deformation fields. Our approach is based on Support Vector (SV) Machines, which...
We present a method for calculating the boundary of objects from Discrete Indicator Functions that store 2material volume fractions with a high degree of accuracy. Although Marchi...
This paper describes an efficient approach to pose invariant object recognition employing pictorial recognition of image patches. A complete affine invariance is achieved by a rep...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
Most previous motion deblurring methods restore the degraded image assuming a shift-invariant linear blur filter. These methods are not applicable if the blur is caused by spatial...