30hp - 3D Reconstruction for Autonomous Driving

Introduction:

Thesis work is an excellent way to get closer to Scania and build relationships for the future. Many of today's employees began their Scania career with their degree project.

Background:

Scania is now undergoing a transformation from being a supplier of trucks, buses and engines to a supplier of complete and sustainable transport solutions.

This thesis work will lie under the supervision of the Scania research group AI Technologies, which develops the algorithms that are used in the scene perception for autonomous driving.

Objective:

Advances in 3D reconstruction are opening new opportunities for autonomous driving, particularly in representing complex outdoor environments that include both static scenes and dynamic objects. This thesis aims to investigate cutting-edge methods such as Gaussian Splatting and Transformer-based 3D Reconstruction.

The goal is to evaluate how these approaches can be applied to in-house real-world datasets and how they may support use cases such as sensor simulation across vehicle configurations, adaptation of data for perception models, and robust scene reconstruction for autonomous transport.

Job description:

This master’s thesis will explore state-of-the-art 3D reconstruction techniques for autonomous driving. Depending on the student’s interest and background, the focus can be placed on one of the following directions:

• Gaussian Splatting for handling moving objects and rendering from sensor modalities including LiDAR and cameras
• Transformer-based 3D Reconstruction methods that enable flexible large-scale scene understanding without requiring fixed sensor setups

The project will entail the following steps:

• Conduct a literature review on state-of-the-art methods in 3D reconstruction relevant to autonomous driving (dynamic scene, outdoor environment, etc...)
• Select and implement one of these approaches and test it using our in-house datasets
• Define metrics and evaluate reconstruction quality, adaptability and suitability for downstream applications

The successful applicant will have the opportunity to apply state-of-the-art methods to real world scenarios and gain hands-on experience on our in-house rich datasets, the latest sensors, computing platforms, and Scania’s concept autonomous vehicles. The applicant will also collaborate with researchers and developers working at Scania’s Autonomous Transport Solutions Pre-Development & Research department.

Qualifications:

• Currently enrolled in a Master program in Computer Science, Electrical Engineering or related field
• Good understanding of computer vison, machine learning and practice thereof
• Sufficient software development knowledge to be able to implement/analyse mathematical concepts
• Proficiency in programming languages such as Python and/or C++
• Prior experience with deep learning, computer graphics or 3D data processing is a plus
• Able to work in a diverse environment and communicate effectively in English
• Excellent problem-solving skills and the ability to work independently

Number of students: 1 or 2

Time plan:

The project is planned for 20 weeks and can be started any time in early Spring 2026. Applicants will be assessed on a continuous basis until the position is filled.

Contact persons and supervisors:

Thibault Fourcaud, Software Engineer, AI Technologies, Autonomous Transport Solutions,
thibault.fourcaud@scania.com

John Dahlberg, Software Engineer, AI Technologies, Autonomous Transport Solutions,
john.dahlberg@scania.com

Johan Haraldson, Software Engineer, AI Technologies, Autonomous Transport Solutions,
johan.haraldson@scania.com

Application:

Your application must include a CV, personal letter and transcript of grades

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.