School of Engineering and Applied Science PhD Studentship (3 years) 3D Reconstruction using high level class-based semantics

Applications are invited for a three year PhD studentship, supported by the School of Engineering and Applied Science to be undertaken within the Computer Science Research Group at Aston University. The successful applicant will join an established experimental group working on 3D Computer Vision and its applications in Computer Graphics and 3D animation. 

The position is available to start in 2013 (subject to negotiation)

Financial Support

This studentship includes a fee bursary to cover the home/EU fees rate plus a maintenance allowance of £13,726. Applicants from outside the EU may apply for this studentship but due to funding restrictions will need to pay the difference between the ‘Home/EU’ and the ‘Overseas’ tuition fees, currently this is £10,300.

Background of the Project

This project will look at the problem of 3d reconstruction from data such as images, video and depth sensors. This is a well-researched field but most existing work focuses on producing a raw geometric model that faithfully describes the 3d scene/object. While useful for certain applications, raw geometry is insufficient for a number of important high level tasks such as CAD/CAM modelling, manufacturing or even just for importing the reconstructed model in a 3d game. In most of these cases the user ends up spending considerable effort to post-process and manually annotate the model with high-level semantic information (i.e. defining what each part of the model is and does, and how different parts are linked and constrained).

Also Read  PhD in Computer Science

This PhD project will look at developing a 3d reconstruction system that automatically generates high-level semantic annotations from the input data. The work will look at applying semantically aware 3d reconstruction in particular domains (e.g. architecture). The main challenge will be to develop probabilistic models for encapsulating prior knowledge about the particular semantic class, and to then be able to infer the most probable semantic structure from the data.

Person Specification

The successful applicant should have a first class or strong upper second-class honours degree or equivalent qualification in Computer Science, Electrical/Information Engineering or Mathematics. Preferred skill requirements include good maths skills, some experience with Bayesian statistics and 3D Computer graphics, as well as good working knowledge of C++ or Matlab/Octave.

For informal enquiries about this and other opportunities within the CS Research Group, contact Dr George Vogiatzis by email

The online application form, reference forms and details of entry requirements, including English language are available by clicking the ‘Apply’ button below

Closing Date: 15 September 2013

Leave a Reply

Your email address will not be published. Required fields are marked *