Retargeting refers to the process by which an image or video is adapted from the display device for which it was meant (target display) to another one (retarget display). The retarget display has different features from the target one such as dynamic range, discretization levels, color gamut, multi-view, and refresh rate spatial resolution. This is a very relevant topic in graphics, given the increasing number of display devices from large, high-contrast screens to small cell phones with limited dynamic range; a lot of techniques are being published in different venues, and it’s hard to keep up. For most cases retargeting can be an ill-posed problem, for example in the process of displaying Low Dynamic Range (LDR) or 8-bit content on High Dynamic Range (HDR) displays. Such a problem requires the retargeting algorithm to generate new content which is missing in the input image/frame. In this course, we will present the latest solutions and techniques for retargeting images along various dimensions such as dynamic range, colors, temporal and spatial resolutions, and for the first time offer a much-needed holistic view of the field. Moreover, we are going to show how to measure and analyze the changes applied to an image or video in terms of quality using both psychophysical experiments (subjective) and computational metrics (objective). The course should be of interest to anyone involved in graphics in a broader sense, given the almost unavoidable need to retarget results to different devices -from developers interested in implementing retargeting techniques, to users that just need an overall perspective. For researchers fully engaged in developing multi-dimensional retargeting techniques, this course will serve as a solid background for future algorithms.

Level
Intermediate

Intended Audience
This course is aimed at an audience interested in using and developing image and video retargeting techniques for modern displays. We expect to draw the attention of people from many fields and believe that graduate students and researchers are likely to be interested in this course as well.

Prerequisites
For best results participants should have a basic understanding of the most commonly used video and image processing techniques, such as filtering (e.g. spatial and temporal), basic video and image operations (e.g. histograms manipulation, bilinear/nearest neighbors downsampling/upsampling), and very basic notions of high dynamic range imaging.

Course Schedule
Session 1: 09:00 - 10:45
09:00-09:05 Francesco Banterle: Welcome and Introduction
09:05-10:00 Rafal Mantiuk: Dynamic Range and Color Retargeting
10:00-10:25 Alessandro Artusi: Dynamic Range and Color Retargeting
10:25-10:45 Francesco Banterle: Dynamic Range and Color Retargeting

Session 2: 11:00 - 12:45
11:00-11:40 Francesco Banterle: Dynamic Range and Color Retargeting
11:40-12:45 Diego Gutierrez: Image Spatial Resolution Retargeting

Session 3: 14:15 - 16:00
14:15-14:50 Karol Myszkowski: Temporal Image Retargeting
14:50-15:25 Elmar Eisemann: Temporal Image Retargeting
15:25-16:00 Tunc O. Aydin: Image and Video Quality Assessment

Session 4: 16:15 - 18:00
16:15-16:50 Tunc O. Aydin: Image and Video Quality Assessment
16:50-17:50 Piotr Didyk: Stereo Content Retargeting
17:50-18:00 Francesco Banterle: Course wrap-up

Presenter(s)
Francesco Banterle is a post-doctoral researcher at the Visual Computing Laboratory at the Italian National Research Council. He received a PhD in Engineering from Warwick University in 2009. For his PhD, he developed Inverse Tone Mapping which bridges the gap between Low Dynamic Range (LDR) Imaging and High Dynamic Range (HDR) Imaging. He holds a BSc and a MSc in Computer Science from Verona University. He is the first co-author of the book "Advanced High Dynamic Range", published by AK Peters in 2011. His main research fields are HDR Imaging, Rendering, and Parallel Processing (Graphics Processing Units and shared memory systems).

Alessandro Artusi is a Research Scientist at CaSToRC. Between 2005 and 2006, he served as Assistant Professor at the University of Nicosia, and from 2006 to 2009 he won a European Research Consortium for Informatics and Mathematics (ERCIM) fellowship and was a research fellow at the Warwick Digital Laboratory. He received his PhD (2004) degree in Computer Science from Vienna University of Technology. His research interests include color science and high dynamic range imaging. Alessandro published and lectured on these topics and a tutorial at Computer Graphics International (CGI) 2003 and Cineca Summer School 2005. He also served as Program Chair at the Symposium on Visual Analytics Science and Technology (VAST) in 2009.

Tunc¸ O. Aydın recently joined Disney Research Zurich as a Post-Doctoral Researcher. His main research interest lies in modelling various aspects of the human visual system, and applying these models to computer graphics and vision problems. He holds a PhD from Max-Planck-Institut für Informatik, an MS from Georgia Institute of Technology (2005), and a BS from Istanbul Technical University (2003). He also has brief industry experience as a C++ developer.

Piotr Didyk is a PhD student at the Max-Planck-Institut für Informatik. He received his MSc in Computer Science from University of Wroclaw. In 2007, he was awarded with a fellowship award from the "Polish Talents'' organization, supported by the Polish Academy of Science. His work focuses on image quality enhancement, which exploits properties of the human visual system. He recently also contributed to the field of stereo-vision by developing a perceptual model for disparity.

Before being Associate Professor at Telecom Paris Tech, Elmar Eisemann was a senior scientist heading a research group in the Cluster of Excellence(Saarland University/Max-Planck-Institut für Informatik) until December 2009. He studied Mathematics in Cologne and Computer Science at the E}ole Normale Superieure Paris (2001). He obtained Master (2004) and PhD. (2008) in Mathematics / Computer Science from Grenoble Universities. He worked at MIT (2003), UIUC (2006), Adobe / Seattle (2007), and Adobe / Boston (2008). His interests include real-time rendering, shadow algorithms, global illumination, and graphics processing unit (GPU) acceleration techniques. He was a local organizer of 21st Eurographics Symposium on Rendering (EGSR) 2010.

Diego Gutierrez is an Associate Professor at the Universidad de Zaragoza. He’s published his research on physically based global illumination, perception and image processing techniques in top journals and conferences (including SIGGRAPH and Eurographics). He is currently the Papers Chair for Applied Perception in Graphics and Visualisation (APGV) 2011, and has held other relevant positions at other conferences. He’s served on many other Program Committees, including SIGGRAPH Asia (2009) and Eurographics (2007, 2010, 2011). He's also an Associate Editor of three journals (Institute of Electrical and Electronics Engineers Computer Graphics and Applications, Association for Computing Machinery Transactions on Applied Perception, Computers & Graphics).

Rafal Mantiuk is a lecturer and Assistant Professor) at Bangor University
(UK). He received his PhD from the Max-Planck-Insitute for Computer
Science (Germany) and was a postdoctoral researcher at the University
of British Columbia (Canada). He is co-chair of the High Dynamic Range Area program at Eurographics 2011. Rafal Mantiuk investigates how the knowledge of the human visual system and perception can be incorporated within computer graphics and imaging algorithms. His recent interests focus on designing imaging algorithms that adapt to human visual performance in order to deliver the best images given limited resources, such as computation time or display contrast.

Karol Myszkowski is a tenured senior researcher at the Max-Planck-Institut für Informatik, Saarbruecken, Germany. In the period from 1993 till 2000 he served as an associate professor in the Department of Computer Software at the University of Aizu, Japan. He received his PhD (1991) and Habilitation (2001) degrees in Computer Science from Warsaw University of Technology (Poland). His research interests include perception issues in graphics, high dynamic range imaging, global illumination and rendering. Karol published and lectured on these topics widely including ACM Siggraph Courses in 2000, 2001, 2003, and 2006. He also co-chaired Eurographics Symposium on Rendering 2001, ACM Symposium on Applied Perception in Graphics and Visualization 2008, and Spring Conference on Computer Graphics 2008.