We propose a family of kernels between images, defined as kernels between their respective segmentation graphs. The kernels are based on soft matching of subtree-patterns of the r...
Scale invariant feature detectors often find stable scales in only a few image pixels. Consequently, methods for feature matching typically choose one of two extreme options: mat...
This paper describes a representation for pen-and-ink illustrations that allows the creation of high-fidelity illustrations at any scale or resolution. We represent a pen-and-ink ...
Michael Salisbury, Corin R. Anderson, Dani Lischin...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
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...