Aberdeen University Featured PhD Programmes
University of Edinburgh Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
University of Dundee Featured PhD Programmes
Cardiff University Featured PhD Programmes

High Quality Facial Synthesis for Digital Humans: Crossing the Uncanny Valley

  • Full or part time
  • Application Deadline
    Sunday, February 02, 2020
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

The Uncanny Valley [Mori] is a term used to describe the challenge of creating human like avatars. Originally applied to robotics, it is a term now commonly applied to computer generated characters. While modern Movies and Video Games offer highly detailed characters there are still challenges in reaching true realism, i.e. where a computer-generated character passes a ‘Turing Test’ of realism. One of the reasons this challenge still exists is that creating realism is still largely an artistic task, and as humans it is difficult to capture and reproduce all the subtle nuances that make people human – from small muscle twitches to the subtle way a person may smile.
Creating truly lifelike digital humans also raises questions of accountability, responsibility and ethical use. In the wrong hands how do we know that the technology we develop will not be used to mislead the public? In an age of ‘fake news’, ‘deep fakes’ and misappropriation of personal data, these questions are now more relevant than ever.

In this project we will attempt to raise the bar in the creation of truly lifelike digital humans. We will do this by learning subtle human movements and use AI to procedurally generate these – taking the task of reproducing these idiosyncracies from the hands of the artist.
However, even though our aim is to create facial animations indistinguishable from real humans, the project will also address ethical issues surrounding this technology. One important aspect of this is studying the reality of technologies such as deep-fakes – how far can we currently go, and how far are we from completely faking the actions of a person in a compelling way? How can we educate the public at large in a responsible way about this technology? How do we detect synthetically generated humans? How do we add provenance to animations created using this technology (e.g. videos or images) so that authors can be held accountable? How might we regulate such technology in the future?

This project is associated with the UKRI CDT in Accountable, Responsible and Transparent AI (ART-AI), which is looking for its second cohort of at least 10 students to start in September 2020. Further details can be found at: http://www.bath.ac.uk/centres-for-doctoral-training/ukri-centre-for-doctoral-training-in-accountable-responsible-and-transparent-ai/.

Desirable qualities in candidates include intellectual curiosity, a strong background in maths and programming experience.

Applicants should hold, or expect to receive, a First or Upper Second Class Honours degree. A master’s level qualification would also be advantageous.

Informal enquiries about the project should be directed to Prof Darren Cosker: .

Enquiries about the application process should be sent to .

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-FP02&code2=0002

Start date: 28 September 2020

Funding Notes

ART-AI CDT studentships are available on a competition basis for UK and EU students for up to 4 years. Funding will cover UK/EU tuition fees as well as providing maintenance at the UKRI doctoral stipend rate (£15,009 per annum in 2019/20, increased annually in line with the GDP deflator) and a training support fee of £1,000 per annum.

We also welcome all-year-round applications from self-funded candidates and candidates who can source their own funding.

References

Mori, M. (2012). Translated by MacDorman, K. F.; Kageki, Norri. "The uncanny valley". IEEE Robotics and Automation. 19 (2): 98–100

How good is research at University of Bath in Computer Science and Informatics?

FTE Category A staff submitted: 24.00

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

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.