Master Thesis AI-Based Keypoint Refinement for Autonomous Driving

JobsCloseBy Editorial Insights

Bosch Group is seeking a Master thesis candidate to research and develop deep learning methods to improve keypoint matching for autonomous driving, designing a unified architecture for correspondence refinement, outlier rejection and uncertainty estimation, with sub-pixel precision and robustness tests against state-of-the-art matchers. The six month, on-site position in Hildesheim starts by prior agreement and requires enrollment at university, proficiency in Python and PyTorch, and a strong background in computer vision and deep learning; knowledge of feature matching, multi-view geometry or SLAM is highly desirable. Important traits include ownership, self-driven, structured research, and ability to communicate technically in English. To apply, attach CV, transcript, exam regulations, and if required work permit; contact Matthias Neuwirth-Trapp.

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

• During your thesis, you will research and develop advanced deep learning methods to improve keypoint matching accuracy for autonomous driving applications.
• You will design a unified neural network architecture that jointly addresses correspondence refinement, outlier rejection, and uncertainty estimation, aiming to replace complex conventional post-processing chains.
• Furthermore, you will investigate novel approaches to achieve sub-pixel precision and handle ambiguous image textures within the feature matching pipeline.
• You will implement and train these models, focusing on efficiency and the potential for distilling the architecture into a fast, real-time capable solution.
• Finally, you will benchmark your approach against current state-of-the-art matchers (e.g., in Visual Odometry scenarios) to demonstrate improvements in robustness and accuracy.

Qualifications

• Education: Master studies in the field of Computer Science, Robotics, Mathematics, Physics or comparable
• Experience and Knowledge: strong background in Computer Vision and Deep Learning; proficiency in Python and PyTorch; specific knowledge of feature matching, multi-view geometry, or SLAM is highly desirable
• Personality and Working Practice: you excel at taking ownership of your research topic with a self-driven, independent, and structured approach, developing your own creative ideas, and engaging in mature, professional technical discussions
• Work Routine: your on-site presence is required
• Enthusiasm: passionate about solving fundamental problems in geometric computer vision and AI
• Languages: very good in English

Additional Information

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?
Matthias Neuwirth-Trapp (Functional Department)
[email protected]

Work #LikeABosch starts here: Apply now!

#LI-DNI