In this paper, we present a novel learning based framework for performing super-resolution using multiple images. We model the image as an undirected graphical model over image patches in which the compatibility functions are represented as non-parametric kernel densities which are learnt from training data. The observed images are translation rectified and stitched together onto a high resolution grid and the inference problem reduces to estimating unknown pixels in the grid. We solve the inference problem by using an extended version of the non-parametric belief propagation algorithm. We show experimental results on synthetic digit images and real face images from the ORL face dataset.
Non-parametric image super-resolution using multiple images
01.01.2005
137365 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Non-Parametric Image Super-Resolution using Multiple Images
British Library Conference Proceedings | 2005
|Super-Resolution Image Restoration from Blurred Low-Resolution Images
British Library Online Contents | 2005
|Super-Resolution from Multiple Views Using Learnt Image Models
British Library Conference Proceedings | 2001
|