About the Project
The goal of this project is to capture the real world and recreate its appearance for new, previously unseen views, to enable more immersive virtual reality video experiences. To do this, the project aims to develop novel-view synthesis techniques using deep learning (like Flynn et al., 2019) that are capable of producing high-quality, temporally-coherent, time-varying VR video of dynamic real-world environments from one or more standard or 360-degree video cameras. Particularly important are the convincing reconstruction of visual dynamics, such as moving people, cars and trees. This experience will provide improved motion parallax and depth perception to the viewer (like Bertel et al., 2019) to ensure unparalleled realism and immersion.
Candidates should normally have a very good undergraduate degree (equivalent to First Class), or a Master’s degree in visual computing, computer science, 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, deep learning and image processing is highly desirable. Non-UK applicants must meet our English language entry requirement: http://www.bath.ac.uk/study/pg/apply/english-language/.
Informal enquiries are welcome and should be directed to Dr Christian Richardt ([Email Address Removed]).
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/
Formal applications should be made via the University of Bath’s online application form:
Please ensure that you quote the supervisor’s name and project title in the ‘Your research interests’ section.
More information about applying for a PhD at Bath may be found here:
Anticipated start date: 28 September 2020.
Flynn, Broxton, Debevec, DuVall, Fyffe, Overbeck, Snavely and Tucker, “DeepView: View Synthesis With Learned Gradient Descent”. CVPR 2019
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.