/Towards deterministic 3D Object Detection though structured geometric annotation

Towards deterministic 3D Object Detection though structured geometric annotation

Master internship - Brussel | Just now

Beyond bounding boxes — annotate the world as it really is.
2D labels flatten a 3D world. This internship explores structured geometric annotation as a richer signal for 3D object detection, leveraging primitives, parts, and spatial relationships to train models that truly understand shape and pose. You'll design annotation schemas, experiment with state-of-the-art detection architectures, and benchmark how geometric structure boosts accuracy, generalization, and data efficiency.

Type of internship: Master internship

Duration: 12 Weeks

Required educational background: Electromechanical engineering, Electrotechnics/Electrical Engineering, Computer Science

Supervising scientist(s): For further information or for application, please contact Hamed Firouzipouyaei (Hamed.Firouzipouyaei@imec.be)

The reference code for this position is 2026-INT-169. Mention this reference code in your application.

Only for self-supporting students.


Applications should include the following information:

  • resume
  • motivation
  • current study

Incomplete applications will not be considered.
Who we are
Accept analytics-cookies to view this content.
imec's cleanroom
Accept analytics-cookies to view this content.

Send this job to your email