Pier Luigi Dragotti
Single-Image Super-Resolution: Coupled-dictionary learning vs model-based processing
Abstract: Single-image super-resolution refers to the problem of obtaining a high-resolution (HR) version of a single low-resolution (LR) image. This problem is highly ill-posed since it is possible to find many high-resolution images that can lead to the same low-resolution one. Thus prior knowledge of the properties of natural images has to be used to regularize the problem.
Strategies to solve the single-image super-resolution problem can be broadly divided into two categories: model-based approaches where some fixed priors are used to regularize the problem and learning-based method where the model that map the LR image to the HR image is learned from external image datasets.
We discuss these two approaches and highlight strengths and weaknesses of both.
A successful learning-based approach is built on the idea that the LR and HR images both admit a sparse representation in proper dictionaries and that the sparsity patterns of the two representations can be shared if the construction of the two dictionaries is properly coupled. We extend this idea of coupled dictionary learning to the case of multi-modal data and present some results on the enhancement of depth images from HR intensity and LR depth images. We then conclude by presenting further applications of coupled dictionary learning in art investigation.
Bio: Pier Luigi Dragotti is Professor of Signal Processing in the Electrical and Electronic Engineering Department at Imperial College London and a fellow of the IEEE. He received the Laurea Degree (summa cum laude) in Electronic Engineering from the University Federico II, Naples, Italy, in 1997; the Master degree in Communications Systems from the Swiss Federal Institute of Technology of Lausanne (EPFL), Switzerland in 1998; and PhD degree from EPFL, Switzerland, in April 2002. He has held several visiting positions. Specifically, he was a visiting student at Stanford University, Stanford, CA in 1996, a summer researcher in the Mathematics of Communications Department at Bell Labs, Lucent Technologies, NJ in 2000 and a visiting scientist at Massachusetts Institute of Technology (MIT) in 2011. Before joining Imperial College in November 2002, he was a senior researcher at EPFL working on distributed signal processing for sensor networks for the Swiss National Competence Center in Research on Mobile Information and Communication Systems.
Dr Dragotti was Technical Co-Chair for the European Signal Processing Conference in 2012, Associate Editor of the IEEE Transactions on Image Processing from 2006 to 2009 and an Elected Member of the IEEE Image, Video and Multidimensional Signal Processing Technical Committee. He was also the recipient of an ERC Consolidator Award for the project RecoSamp. He is currently a member of the IEEE Signal Processing Theory and Methods Technical Committee and a member of the IEEE Special Interest Group on Computational Imaging.
His research interests include sampling theory, wavelet theory and its applications, image super-resolution and image-based rendering.