In this paper, a new directionally adaptive, learning based, single image super resolution method using multiple direction wavelet transform, called Directionlets is presented. Th...
In this paper we propose an eigenimage based superresolution reconstruction technique. Eigenimages of a database of several similar low resolution images are obtained and the give...
We formulate the multiframe blind deconvolution problem in an incremental expectation maximization (EM) framework. Beyond deconvolution, we show how to use the same framework to a...
Stefan Harmeling, Suvrit Sra, Michael Hirsch, Bern...
In this paper, we propose a method for recognizing lowresolution characters using a super-resolution technique. Although portable digital cameras can be used for camerabased chara...
A learning-based face hallucination method is proposed in this paper for the reconstruction of a high-resolution face image from a low-resolution observation based on a set of high...