In this work, we propose a new robust and edge-preserving superresolution algorithm to simultaneously estimate all frames of a sequence. The new algorithm is based on the regulari...
We present a modification of the Mumford-Shah functional and its cartoon limit which facilitates the incorporation of a statistical prior on the shape of the segmenting contour. By...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
We consider the problem of image comparison in order to match smooth surfaces under varying illumination. In a smooth surface nearby surface normals are highly correlated. We model...
Margarita Osadchy, Michael Lindenbaum, David W. Ja...
In general, image sensor noise is dominated by Poisson statistics, even at high illumination level, yet most standard denoising procedures often assume a simpler additive Gaussian...