Fraunhofer IIS

Student Assistants Convolution Neural Networks for estimating Optical Flow

Online seit
08.07.2020 - 11:00


For the »Moving Picture Technologies« department in Erlangen, the Fraunhofer Institute for Integrated Circuits IIS is currently seeking

Student Assistants Convolution Neural Networks for estimating Optical Flow

The »Moving Picture Technologies« department is part of the »Audio and Media Technologies« division of Fraunhofer IIS, which constitutes one of the world’s largest organizations dedicated to audio, speech and media processing. It has been an innovator in sound and vision for over 25 years and repeatedly won international competitions in the audio and media field: e.g. with mp3 and codecs of the AAC-family. Over 200 engineers and scientists develop first-rate technology, which is sold worldwide, in Europe, USA, China, Korea and Japan.


Being able to estimate movements in subsequent images can significantly improve video compression efficiency. In recent years, Convolution Neural Networks (CNN) are used to improve those estimations and to further improve video coding techniques. Part of this project is to compare latest, CNN-based State of the Art networks and to develop new ideas how to improve existing solutions.

    What you can expect from us

    • An open and cooperative working environment
    • Collaboration in interesting and innovative projects
    • Many opportunities to gain practical experience and attend seminars
    • Flexibility concerning your working hours

    The weekly working time is determined by agreement, but you should be available for at least 12 hours per week.


    Please apply for this position using the following link:

    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 53362-AME. Address your application to Nina Wörlein.

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

    Additional information is available on our website:


    Your profile: You …

    • are studying electrical engineering, computer science, information and communication technologies or a related field
    • have experience in programming languages such as C++, Python or MATLAB
    • are familiar and have hands-on experience with CNNs
    • have experience with deep learning frameworks such as TensorFlow, PyTorch, Caffe or Theano
    • are familiar with concepts of computer vision
    • have basic knowledge in the area of image and video processing

    Firmen- und Kontaktdaten

    Fraunhofer IIS
    Frau Nina Wörlein
    Am Wolfsmantel
    91058 Nürnberg
    +49 9131 7761684

    Art der Beschäftigung


    Weitere Informationen

    Zeitraum der Beschäftigung
    nach Vereinbarung