Know ATS Score
CV/Résumé Score
  • Expertini Resume Scoring: Our Semantic Matching Algorithm evaluates your CV/Résumé before you apply for this job role: Towards More Informative 3D Scene Graphs for Visual Reasoning.
Germany Jobs Expertini

Urgent! Towards More Informative 3D Scene Graphs for Visual Reasoning Position in Munich - Technical University of Munich

Towards More Informative 3D Scene Graphs for Visual Reasoning



Job description

MSc Thesis: Towards More Informative 3D Scene Graphs for Visual Reasoning

07.10., Studentische Hilfskräfte, Praktikantenstellen, Studienarbeiten

The Chair of Robotics, Artificial Intelligence and Real-Time Systems (Prof.

A.

C.

Knoll) offers a Master’s Thesis on structured visual understanding through multi-modal reasoning.

The project explores modern vision–language models to improve spatial and semantic perception for real-world AI and robotic applications.

Recent advances in vision–language models have enhanced our ability to interpret complex visual scenes.

However, these systems often struggle with structured and spatial reasoning.

This project aims to develop methods for improved visual understanding that combine vision and language representations for interpretable, structured perception and reasoning.

You will explore modern foundation models such as,
BLIP-2, PRISM-0, HOV-SG, ROOT, Panoptic Scene Graph Generation, and investigate how their reasoning capabilities can be extended to create more coherent and spatially aware representations for real-world robotic or AI applications.

Start Date: Winter Semester

Location: Technical University of Munich (in-person participation required; occasional remote work possible)

Application Deadline: 24.10.

Requirements:

  • Strong programming skills in Python; experience with PyTorch or similar deep learning frameworks
  • Familiarity with computer vision and visual–language models
  • Interest in multi-modal reasoning, representation learning, or robotic perception
  • Contact:

    Panagiotis Petropoulakis

    Chair of Robotics, Artificial Intelligence and Real-Time Systems

    Technical University of Munich

    Keywords: Visual Reasoning, Multi-Modal AI, Computer Vision, Robotics, Deep Learning, Representation Learning, Vision-Language Models


    Required Skill Profession

    Computer Occupations



    Your Complete Job Search Toolkit

    ✨ Smart • Intelligent • Private • Secure

    Start Using Our Tools

    Join thousands of professionals who've advanced their careers with our platform

    Rate or Report This Job
    If you feel this job is inaccurate or spam kindly report to us using below form.
    Please Note: This is NOT a job application form.


      Unlock Your Towards More Potential: Insight & Career Growth Guide