Creating light field content from existing images and videos

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.

Light field displays for the first time offer the viewer more than two views of an object from different perspectives, and they can thus reproduce the appearance of real-world objects which previously unachieved fidelity. This has been demonstrated by first research prototype displays, and commercial light field displays will become available within the next few years. However, cameras for capturing light field images or videos are not yet readily available, which is why this project aims to create light field content from existing imagery, which is readily available. To achieve this goal, the 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.

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 highly desirable.

Informal enquires are welcomed and should be directed to Dr Christian Richardt ([Email Address Removed]). Formal applications should be submitted via the University of Bath’s website: http://www.bath.ac.uk/science/graduate-school/research-programmes/how-to-apply/.

For more general information on studying for a PhD in computer science at Bath, see:
http://www.bath.ac.uk/science/graduate-school/research-programmes/phd-computer-science/

Anticipated start date: 2 October 2017.

Applications may close earlier than the advertised deadline if a suitable candidate is found; therefore, early application is recommended.