Research Assistant

The Computer Vision & Remote Sensing research group at TU Berlin is looking for a research assistant to work on an externally funded project on the automated recording and analysis of passenger compartments in rail vehicles. Video data from several 360° cameras will be used for dynamic three-dimensional modeling of the interior, including passengers and objects they carry with them. Key parameters include the number of people, vacant spaces, and visible soiling. We are particularly interested in candidates who research methods that combine semantic understanding, 3D reconstruction, and spatio-temporal modeling.

Research topics include, for example:

• Novel techniques for integrating geometric and semantic understanding.
• Integration of 3D representations such as point clouds, Gaussian splatting, and generative 3D models with 3D scene graphs.
• Scene reconstruction under challenging conditions, for example 3D reconstruction of dynamic environments observed from opposite directions using 360° cameras.
• Deep learning-based approaches for dynamic and static scene understanding.
• Unsupervised, such as self-supervised or weakly supervised, representation learning from video data.
• Temporal modeling of objects and scenes in 3D spaces.

• Successfully completed scientific university studies (Master, Diplom or equivalent) in Computer Science, Computer Engineering, or related discipline
• Very good programming skills in Python und C/C++
• Intensive up to date knowledge and experiences in computer vision or pattern recognition or applied mathematics
• Interests in cooperation with industrial partners is desirable
• Good knowledge of German and/or English required; willingness to acquire the respective missing language skills.

Please send your application with the reference number and the usual documents only by email (single pdf-file, max. 5 MB) to Heike Herrmann (h.herrmann@tu-berlin.de).

By submitting your application via email you consent to having your data electronically processed and saved. Please note that we do not provide a guaranty for the protection of your personal data when submitted as unprotected file. Please find our data protection notice acc. DSGVO (General Data Protection Regulation) at the TU staff department homepage: https://www.abt2-t.tu-berlin.de/menue/themen_a_z/datenschutzerklaerung/.

To ensure equal opportunities between women and men, applications by women with the required qualifications are explicitly desired. Qualified individuals with disabilities will be favored. The TU Berlin values the diversity of its members and is committed to the goals of equal opportunities. Applications from people of all nationalities and with a migration background are very welcome.