University College London Featured PhD Programmes
Norwich Research Park Featured PhD Programmes
FindA University Ltd Featured PhD Programmes
University of Kent Featured PhD Programmes
University of Reading Featured PhD Programmes

Deep View Synthesis for VR Video

  • Full or part time
  • Application Deadline
    Sunday, December 08, 2019
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

To feel truly immersed in virtual reality, one needs to be able to freely look around within a virtual environment and see it from the viewpoints of one’s own eyes. Full immersion requires that viewers see the correct views of an environment at all times. As viewers move their heads, the objects they see should move relative to each other, with different speeds depending on their distance to the viewer. This is called motion parallax and is a vital depth cue for the human visual system that is entirely missing from existing 360° VR video.

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 ().

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:
https://samis.bath.ac.uk/urd/sits.urd/run/siw_ipp_lgn.login?process=siw_ipp_app&code1=RDUCM-FP01&code2=0014

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:
http://www.bath.ac.uk/guides/how-to-apply-for-doctoral-study/

Anticipated start date: 28 September 2020.

Funding Notes

UK and EU candidates applying for this project will be considered for a University Research Studentship which will cover UK/EU tuition fees, a training support fee of £1,000 per annum and a tax-free maintenance allowance at the UKRI Doctoral Stipend rate (£15,009 in 2019-20) for a period of up to 3.5 years.

References

Bertel, Campbell and Richardt, “MegaParallax: Casual 360° Panoramas with Motion Parallax”, IEEE Transactions on Visualization and Computer Graphics 2019

Flynn, Broxton, Debevec, DuVall, Fyffe, Overbeck, Snavely and Tucker, “DeepView: View Synthesis With Learned Gradient Descent”. CVPR 2019

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2019
All rights reserved.