Research Explorer

Your browser does not support JavaScript or JavaScript is not enabled. Without JavaScript some functions of this webapplication may be disabled or cause error messages. To enable JavaScript, please consult the manual of your browser or contact your system administrator.

Project

Differentiable programming for improving and accelerating image processing and computer vision algorithms.

Outputs and Outcomes

Code

01N15619

Duration

01 October 2019 → 31 July 2024

Funding

Regional and community funding: Special Research Fund

Promotor

Bart Goossens

Research disciplines

Natural sciences
- Programming languages and technologies
- Computer vision
- Image processing

Keywords

real-time optimizations image processing computer vision

Project description

Differentiable programming is a new programming paradigm that generalizes many existing “deep learning” techniques. In this project, we develop and investigate a new framework for differentiable programming for image processing. We will generate efficient code for parallel processing
architectures (multicore CPU, GPUs, FPGAs) and apply the framework to relevant problems in the domains of computer vision and sensor fusion.

English

Dutch

English

Cookie settings

In addition to functional cookies which are necessary for the website to function, Ghent University uses non-functional cookies such as statistical cookies and social media cookies. These non-functional cookies can also be placed by third parties, for example to measure the use of the site or to share content on social media. Certain media are only available if you accept the cookies. You can set and modify your cookie preferences yourself. Find out what cookies we use and why in the Cookie Statement.

Analytics

AnalyticsWe'll collect information about your visit to our site. It helps us understand how the site is used – what's working, what might be broken and what we should improve.

Powered by