Capturing a scene with a camera array instead of a single camera enables a wide range of possibilities during post-production as not only a single intensity image is acquired but a so-called light-field is recorded. With this light-field, for instance, the scene depth can be estimated, intermediate views necessary for VR applications can be rendered, virtual camera movements can be created, or the depth of field can be changed retrospectively. However, achieving these goals requires computational imaging algorithms to be applied on the captured data.
In recent years, deep learning techniques have developed to be popular and effective tools for many tasks in the field of image and video processing. Especially convolutional neural networks have proven to achieve high image quality in many a different task. Furthermore, generative adversarial networks are applied to various image processing tasks and lead to visually very appealing results.
Your task would be to implement and evaluate novel concepts based on deep learning methods for light-field applications. Therefore, this work might involve – but is not limited to – improving the quality of geometric calibration, disparity estimation, view rendering, or filtering. The overall goal is to generate visually appealing view rendering results.
For more information about our light-field research, please refer to
- You are studying electronic engineering, computer science, information and communication technologies, or a related field
- You have experience in programming languages such as Python, MATLAB, or C++
- You have experience with deep learning frameworks such as TensorFlow, PyTorch, Caffe, or Theano
- You have good knowledge in the area of image and video processing
- You are available from now on (as a student assistant: 10-12 hours a week or as an intern: for a period of at least three months)
- An interesting application-oriented field of research with innovative projects and a state-of-the-art laboratory environment
- Extensive professional support from scientific mentors
- Flexible hours, that allow you to balance your studies and on-the-job experience
- An open and friendly work environment
- Sufficient opportunity to improve your own interests and skills
If you have any questions about this opening, please contact:
- Michel Bätz (email@example.com), phone: +49 (0) 9131 776-5166
- M. Shahzeb Khan Gul (firstname.lastname@example.org), phone: +49 (0) 9131 776-5159
Please submit your application (PDF: including a cover letter, your CV and your latest transcripts of records) to: Nina Wörlein, via our career portal, quoting reference number
42931. We look forward to receiving your application in English or German!
Please let us know how you learned about this job opportunity.