For the »Moving Pictures Technology« department in Erlangen, the Fraunhofer Institute for Integrated Circuits IIS is currently seeking a
Student Assistant / Intern / Thesis Student: Recovering Geometry from Images using Deep Learning

Recovering geometry information from multiple photos of an object is still a challenging task. Recently, many deep learning based approaches have been published, showing a huge potential of this technology for future VR, AR and 3D compositing applications.

To advance our research in this domain, we are looking for you to help us in evaluating the most promising approaches for geometry reconstruction from multiple images using deep learning.

For more information about our research, please refer to
and to

You are interested in 3D reconstruction and would like to develop further in the field of deep learning?

Then we have the right job for you! Your tasks:

  • Using existing source code, you train deep neural networks that are able to deliver geometry and color information of an object or a scene
  • You evaluate the results using objective quality metrics
  • You compare various approaches in terms of processing time, memory consumption and achievable quality

Was du mitbringst

  • You are currently studying electronics 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
  • You have good knowledge in the area of multi-view image processing

Was du erwarten kannst

  • 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 develop your interests and skills

Applications are possible in German and English. Please include a cover letter, your CV and your latest transcripts of records (as PDF) and quote ID number 62285-AME. Address your application to Nina Wörlein.

Please let us know how you learned about this job opportunity.

Kennziffer: 62285-AME Bewerbungsfrist: