Master Thesis - Road-Surface Reconstruction with LiDAR-Camera Gaussian Splatting (m/f/d)
Master Thesis - Road-Surface Reconstruction with LiDAR-Camera Gaussian Splatting (m/f/d)
Mönsheim, DE, 71297
Master Thesis - Road-Surface Reconstruction with LiDAR-Camera Gaussian Splatting (m/f/d)
We are CARIAD, the automotive software company of the Volkswagen Group. Our teams build automotive software platforms and digital customer functions for iconic brands like Audi, Volkswagen, and Porsche – supporting the Volkswagen Group in becoming the leading automotive technology company. With CARIDIANS in Germany, the USA, China, Estonia, and India, we are transforming automotive mobility for everyone.
Join us and be part of this exciting journey!
YOUR TEAM
To support our Vehicle Motion & Chassis team, we are offering a master-thesis project on next-generation 3-D scene understanding. Working with our in-house sensor platform (dual LiDARs, stereo cameras, and vehicle signals). You will refine the research question, implement state-of-the-art neural rendering (3D Gaussian Splatting), and validate the pipeline on real driving data. The goal is to deliver efficient 3D road-surface model that feeds straight into our chassis-control, boosting ride comfort and safety functions, while giving you the freedom, hardware access and mentoring needed to publish your results.
WHAT YOU WILL DO
- Literature review on state-of-the-art 3D Gaussian Splatting, neural point / Gaussian fields, and related real-time scene representations
- Design and implement a complete pipeline that fuses dual-LiDAR depth + stereo/RGB imagery into a 3D Gaussian splats focused on the drivable surface
- Develop, fine-tune, and benchmark the Gaussian-splatting pipeline in Python/PyTorch
- Evaluation Qualitative and quantitative evaluation on reconstruction accuracy and runtime for the approach
WHO YOU ARE
- Enrolled student in Computer Science, Robotics, Mechatronics or a related field
- Solid grounding in 3-D geometry / multiple-view geometry
- Strong Python programming skills and practical experience with PyTorch
- Familiar with core Computer-Vision & point-cloud libraries (OpenCV, NumPy, Open3D)
- Hands-on exposure to deep-learning architectures
- Self-driven, team-minded, communicative, and eager to publish
- Ideally, previous work with LiDAR and/or camera, such as autonomous driving datasets
- Prior publishing experience is a plus
NICE TO KNOW
- Remote work options within Germany
- Duration: 6 months
- 35-hour week
At CARIAD, we embrace individuality and diversity because we believe our differences make us stronger. We actively seek to build teams with a variety of backgrounds, perspectives, and experiences. Our goal is to create an environment where everyone feels valued and empowered to contribute. If you need assistance with your application due to a disability, please reach out to us at careers@cariad.technology - we are happy to support you.
We are CARIAD, the automotive software company of the Volkswagen Group. Our teams build automotive software platforms and digital customer functions for iconic brands like Audi, Volkswagen, and Porsche – supporting the Volkswagen Group in becoming the leading automotive technology company. With CARIDIANS in Germany, the USA, China, Estonia, and India, we are transforming automotive mobility for everyone.
Join us and be part of this exciting journey!
YOUR TEAM
To support our Vehicle Motion & Chassis team, we are offering a master-thesis project on next-generation 3-D scene understanding. Working with our in-house sensor platform (dual LiDARs, stereo cameras, and vehicle signals). You will refine the research question, implement state-of-the-art neural rendering (3D Gaussian Splatting), and validate the pipeline on real driving data. The goal is to deliver efficient 3D road-surface model that feeds straight into our chassis-control, boosting ride comfort and safety functions, while giving you the freedom, hardware access and mentoring needed to publish your results.
WHAT YOU WILL DO
- Literature review on state-of-the-art 3D Gaussian Splatting, neural point / Gaussian fields, and related real-time scene representations
- Design and implement a complete pipeline that fuses dual-LiDAR depth + stereo/RGB imagery into a 3D Gaussian splats focused on the drivable surface
- Develop, fine-tune, and benchmark the Gaussian-splatting pipeline in Python/PyTorch
- Evaluation Qualitative and quantitative evaluation on reconstruction accuracy and runtime for the approach
WHO YOU ARE
- Enrolled student in Computer Science, Robotics, Mechatronics or a related field
- Solid grounding in 3-D geometry / multiple-view geometry
- Strong Python programming skills and practical experience with PyTorch
- Familiar with core Computer-Vision & point-cloud libraries (OpenCV, NumPy, Open3D)
- Hands-on exposure to deep-learning architectures
- Self-driven, team-minded, communicative, and eager to publish
- Ideally, previous work with LiDAR and/or camera, such as autonomous driving datasets
- Prior publishing experience is a plus
NICE TO KNOW
- Remote work options within Germany
- Duration: 6 months
- 35-hour week
At CARIAD, we embrace individuality and diversity because we believe our differences make us stronger. We actively seek to build teams with a variety of backgrounds, perspectives, and experiences. Our goal is to create an environment where everyone feels valued and empowered to contribute. If you need assistance with your application due to a disability, please reach out to us at careers@cariad.technology - we are happy to support you.
Mönsheim, DE, 71297