A fully-funded PhD studentship is available in the area of visual computing at the University of Bath.

 

Light-field synthesis from existing imagery

 

The goal of this project is to create appealing visual content for upcoming light-field displays from existing imagery, particularly from image and video collections such as historical photos or consumer videos. This project will research and develop image- and video-based rendering approaches for synthesising visually plausible novel views, as well as new data-driven inpainting techniques for filling occlusion holes in a visually consistent manner.

 

Requirements

Candidates should normally have a good first degree (equivalent to a First Class or 2:1 Honours), or a Master’s degree in computer science, visual computing or a related discipline. A strong mathematical background and strong previous programming experience, preferably in C++ and/or Python, is required. Candidates must have a strong interest in visual computing, and previous experience in computer vision, computer graphics and image processing is very desirable. The student will be expected to start on 3rd October 2016.

 

Funding

The successful student will be UK or EU only (overseas applicants are not eligible for this funding). The studentship will cover full Home/EU tuition fees, a training support fee of £1,000/annum and standard tax-free maintenance of £14,296/annum (rate for 2016/2017) for 3.5 years.

 

Additional information

For more general information about studying for a PhD at Bath, please see:

http://www.bath.ac.uk/study/pg/programmes/comp-scie-mphi

 

Informal enquires about the position are welcome and should be directed to Dr Christian Richardt (christian@richardt.name).

Application

The application deadline for this position is Friday, 29 April 2016.

 

Applications can be submitted via FindAPhD (http://master.findaphd.com/search/ProjectDetails.aspx?PJID=73428).

 

Early application is recommended as this position may be filled if a suitable candidate is found before the deadline.