{flike}
{fshare}
PhD position in Image Processing - Perceptual Preferences Applied To Massive Super-Resolution and Image Editing
Firma | University College London (UCL) |
Kraj | Great Britain (UK) |
Miasto | London |
Sektor | biomedical engineering |
Obszar |
image processing |
Typ | full time / PhD |
Applications are invited for an Engineering Doctorate (EngD) in the Department of Computer Science at the University College London (UCL) in conjunction with Anthropics Technology Ltd. This is a 4-year studentship, leading to the award of an Engineering Doctorate, which offers the opportunity to conduct research within an industrial context. This EPSRC (UK Research Council) funded studentship is available to UK citizens and EU nationals if a relevant connection with the UK has been established (usually by being resident for a period of three years immediately before the EngD). Applicants must fulfil EPSRC eligibility criteriaand the normal academic requirements for admission to study in the Department. This studentship will pay a tax-free stipend of approximately ?18,000 per year, plus tuition fees. EU students without a relevant connection to the UK can receive an award to cover tuition fees only.
The EngD post in this project will be based at both UCL (central London) and Anthropics Technology Ltd. (15 min away by Tube). The post is offered under the Virtual Environments, Imaging and Visualization programme, which is run by the EngD VEIV Centre, UCL Computer Science.
Project
This project aims at looking between the pixels: many image-editing operations require values sampled between pixel centres, let it be simple resizing operations, content-sensitive image enhancement or alpha matting. Usually, such values are determined using interpolation. The field of super-resolution, however, aims at inferring content between the pixel samples. Super-resolution of single images is an ill-posed problem. This project should research meaningful ways to infer, or to "hallucinate", inter-pixel content, by drawing from principles of human perception. A key component of the work shall investigate preferences of many human observers to crowd source a model of the additional details people would expect to appear when massively up-scaling an image. Such human-sourced image understanding may facilitate other novel image editing operations. The work is conducted in collaboration with Anthropics Technology Ltd., London, who are experts in putting powerful, high-level image operations at the fingertips of inexperienced users.
Applicants are required to have
- A bachelor degree (1st or 2.1 honours) or an MSc in Computer Science or related field;
- Good knowledge of computer graphics, image processing and mathematics;
- Strong programming skills, particularly C++, C, and Matlab;
- Good communication and presentation skills.
Informal enquiries on the project can be made to Dr Tim Weyrich (http://www.cs.ucl.ac.uk/staff/T.Weyrich/). For further information on the EngD Programme, see http://web4.cs.ucl.ac.uk/teaching/engd/ or contact Dr Jamie O'Brien ( Adres poczty elektronicznej jest chroniony przed robotami spamującymi. W przeglądarce musi być włączona obsługa JavaScript, żeby go zobaczyć. ).
To be considered, you must fill in the general UCL application form. Please see http://www.ucl.ac.uk/prospective-students/graduate-study/application-admission/, where you can download the forms and guidelines. Make sure you specify Supervisor (Tim Weyrich), and EngD (?Perceptual Preferences?) on the ?Research Subject Area? part of the form. Please send the completed form to Dr Jamie O?Brien, Department of Computer Science, University College London, Gower Street, London WC1E 6BT.
If you need further assistance regarding our application process, please contact the EngD Centre Manager Dr Jamie O?Brien (
Adres poczty elektronicznej jest chroniony przed robotami spamującymi. W przeglądarce musi być włączona obsługa JavaScript, żeby go zobaczyć.
)