at Universitat Pompeu Fabra
Full TimeCall for a research staff position with an indefinite contract for the realization of scientific and technical activities, for the execution of the scientific and technical service "AI Module for Enhanced Image Super-Resolution and Bokeh Effects”, in accordance with article 23 bis of the Law 14/2011, of June 1, of science, technology and innovation.
The aim of the project is to develop a tool based on deep learning to improve the quality of video in two aspects: increase the resolution and synthesis of bokeh effect (keeping the subject sharp while blurring the background). For this purpose, generative techniques will be investigated (such as adversarial training, autoregressive models, variational autoencoders, diffusion models), which should be capable of generating sharp details in the focus plane that are temporally consistent with the motion in the video. The designed tool must comply with computational cost constraints to ensure its practical implementation.
In the case of an ORD2 researcher, the tasks will be the following:
- Design of data sets (possibly including synthetically generated data) for training and evaluation. Design, implementation and training of generative models for video.
- Tests on simple datasets to evaluate feasibility.
- Adaptation of the models to the complexities of real cases and optimization of the quality of the result.
- Reduction of the computational cost of the solution, affecting the quality of the results as little as possible.
In the case of an ORD3 research, the following tasks are added to the previous tasks:
- Literature study to prepare a report on the state of the art in generative methods forvideo super-resolution and bokeh synthesis.
- Design and implementation of a quantitative and qualitative evaluation protocol.
Requirements that candidates must meet
GENERAL
a) Be in possession of the Doctor's degree
b) Not having been separated through a disciplinary file from the service of any of the public administrations, nor be disqualified by a final judgment for the development of public functions. In the case of being a national of another State, no to be disqualified or in an equivalent situation or to have been subject to disciplinary sanction or equivalent that prevents, in their State, access to jobs in the same terms.
SPECIFIC
a) Research experience in at least one of the following domains: computer vision,image and/or video processing, generative models for image generation, machine learning, deep learning.
b) Excellent programming skills and experience in developing deep learning pipelines using python libraries such as pytorch and tensorflow.
c) Capacity to work individually with autonomy and critical thinking, as well as in teams.
d) Good communication abilities.
e) Fluent level of English, both written as well as spoken.
These participation requirements must be met on the last day of the deadline to submitapplications, must be able to be reliably verified at any time during the selection process and must to continue complying on the date of signing the contract.
Via Interfolio
UPF promotes a diverse and inclusive environment and welcomes applicants regardless of age, disability, gender, nationality, race, religion or sexual orientation.
