30 Credit - 3D Dense Reconstruction From Images

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 research groups EEARA & EEARP, which develops the algorithms that are used in the scene perception for autonomous driving. 

Objective:
Deep neural networks are outperforming many classical approaches for computer vision in tasks such as semantic segmentation and object detection. The inverse graphics problem - retrieving the 3D geometry of a scene and its appearance from given images and camera poses - is also now addressed by deep learning. The recent emergence of Neural Radiance Fields (NeRF) techniques has shown promising results in this 3D reconstruction task. Additionally, 3D Gaussian Splatting techniques have more lately arise and offer a more realistic rendering approach. 

These technologies could help us in many use cases, such as training 3D occupancy neural networks or similar models. Our goal is to investigate these advanced 3D reconstruction techniques using multi-camera images (possibly LiDAR point clouds also) to develop models that can be applied to the field of autonomous driving. 

Job description:  

This master’s thesis will focus on investigating the ability of NeRF and 3D Gaussian Splatting techniques to generate realistic and geometrically accurate 3D reconstructions from images in an offline manner and this work will most certainly entail the following steps: 

-Get familiar with NeRF and 3D Gaussian Splatting  
-Conduct literature review by considering the specifications of the autonomous vehicle domain (dynamic scene, outdoor environment, etc...) 
-Select one approach, experiment it on our in-house dataset and identify the relevant metrics to assess the performance of the method. 

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 dynamic and experienced 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 

Time plan:
The project is planned for 20 weeks and can be started any time in early Spring 2025. 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  

Joakim Lilja, Senior Development Engineer, Scania Autonomous Transport Solutions, joakim.lilja@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.