[visionlist] PhD Scholarship for research in visual quality metrics

[BERTALMIO BARATE, MARCELO JOSÉ]

PhD Scholarship for research in visual quality metrics

At the Department of Information and Communication Technologies,
Universitat Pompeu Fabra, Barcelona, Spain, there is a PhD scholarship
available for research on visual quality metrics. This position is
associated with the ERC Starting Grant "Image processing for enhanced
cinematography”, led by Marcelo Bertalmío,
http://www.dtic.upf.edu/~mbertalmio/, and which is described below.
This work would be done under my supervision, over a 4-year period, and the
PhD thesis should be completed within this timeframe. The scholarship
covers tuition fees, does not require teaching, and the monthly wage is
1,300€. The admission requirements are: to have completed 300 ECTS credits,
60 of which have to correspond to an official, research-oriented Master's
program.
Scholarships and admission are very competitive, and a strong background in
math, image processing, computer vision, neuroscience or related
disciplines are a plus.
Contact: please send application with CV, contact information of three
references, and an intention letter to: marcelo DOT bertalmio AT upf DOT
edu . We will start evaluating applications in early July and the position
will be open until filled.
Universitat Pompeu Fabra (UPF, http://www.upf.edu/en/) is a public
university located in Barcelona. It is the best Spanish university
according to the London Times higher education index, 2011, and it's the
number one Spanish university in number of ERC grants. The Information and
Communication Technology department (ICT, http://www.upf.edu/dtic/en/) is
the best in Computer Science in Spain, according to the Shanghai index
2009.

Description of the project
The objective of this ERC Starting Grant project is to develop image
processing algorithms for cinema that allow people watching a movie on a
screen to see the same details and colors as people at the shooting
location can. It is due to camera and display limitations that the shooting
location and the images on the screen are perceived very differently. We
want to be able to use common cameras and displays (as opposed to highly
expensive hardware systems) and work solely on processing the video so that
our perception of the scene and of the images on the screen match, without
having to add artificial lights when shooting (other than for artistic
purposes) or to manually correct the colors to adapt to a particular
display device. In terms of sensing capabilities cameras are in many
regards better than human photoreceptors, but human vision performs better
processing, carried out in the retina and visual cortex. Therefore, rather
than working on the hardware, improving lenses and sensors, we will instead
use, whenever possible, existing knowledge on visual neuroscience and
models on visual perception to develop software methods mimicking neural
processes in the human visual system, and apply these methods to images
captured with a regular camera. We will also use variational methods
coupled with perceptual metrics to optimize the final outputs. From a
technological standpoint, reaching our goal will be a remarkable
achievement which will impact how movies are made (in less time, with less
equipment, with smaller crews, with more artistic freedom) but also which
movies are made (since good-visual-quality productions will become more
affordable.) We also anticipate a considerable technological impact in the
realm of consumer video. From a scientific standpoint, this will imply
finding solutions for several challenging open problems in image processing
and computer vision, but it also has a strong potential to bring
methodological advances to other domains like experimental psychology and
visual neuroscience.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist/attachments/20120629/55bffacb/attachment.htm>