PhD - Neural 3D Scene Representations for the Automotive Cabin
Bosch•3h ago
Hildesheim, NDS, deOnsiteFull-timeIntern Level0-1 yrs exp
- 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
- we inspire each other. Welcome to Bosch. The Robert Bosch GmbH is looking forward to your application!
- At Bosch Research, we are driving the next generation of Physical AI, intelligent systems capable of perceiving, reasoning about
- acting robustly in real-world environments. As vehicles become increasingly shared, automated
- software-defined, understanding what happens inside the cabin is becoming as important as understanding the road ahead. The ability to detect occupant position, posture
- movement is evolving into both a regulatory requirement and a key enabler of future safety and comfort functions. However, current perception systems largely treat the vehicle interior and exterior as separate domains, limiting their ability to form a coherent three-dimensional understanding of the cabin from the small number of cameras that can realistically be deployed in a vehicle. In this PhD project, you will investigate neural 3D scene representations, including neural radiance fields, Gaussian splatting
- implicit occupancy models
- adapt them to the unique challenges of in-cabin perception. Unlike exterior environments
- a moving sensor observes a largely static scene, the vehicle cabin presents the opposite scenario: the structure is fixed and known
- occupants are the primary source of motion, exhibiting articulated, deformable
- continuously changing behavior. You will leverage this asymmetry as an advantage by using the known cabin geometry as built-in supervision and by incorporating modern 3D-aware diffusion models as learned priors. Your research will focus on reliably reconstructing occupants from as few as one to three fixed camera viewpoints. A key objective of the project is to create a unified representation of the vehicle interior and exterior, enabling future end-to-end ADAS systems to be trained and validated while simultaneously reasoning about passengers and the surrounding traffic environment. As part of Bosch Research, you will work at the forefront of AI innovation while contributing to real-world industrial applications. You will help develop an emerging capability that bridges interior and exterior scene understanding
- collaborating closely with leading experts from academia and industry to bring these advances into future safety-critical products. Your work will combine fundamental research in 3D computer vision and generative modeling with the practical goal of making vehicles safer for everyone on board.
- Education: excellent Master’s degree in Computer Science or a comparable field of study Experience and Knowledge: experience in machine learning using PyTorch ideally with vision-based models and neural scene representation good programming skills in Python and solid foundations in computer vision and 3D geometry, including camera models, projective geometry
- multi-view constraints familiarity with 3D scene representations (e.g., NeRF, Gaussian splatting, implicit/occupancy networks) or depth/3D estimation methods is strongly preferred prior exposure to differentiable rendering or articulated human pose estimation is a plus Personality and Working Practice: you combine a proactive and highly motivated mindset with the ability to confidently navigate complex technical environments Languages: good English skills, both written and spoken
- https://www.bosch-ai.com www.bosch.com/research The final Ph.D. topic is subject to the supervising university. Start: October 2026 Please submit all relevant documents (incl. curriculum vitae, certificates). 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 support during your application? Celina Dannecker (Human Resources) +49 711 811 21346 Need further information about the job? Matthias Wacker (Functional Department) +49 5121 49 2129 Work #LikeABosch starts here: Apply now!
Required skills
PythonPyTorch3D computer visionneural scene representationcamera modelsprojective geometrymulti-view constraints3D scene representationsdepth estimationdifferentiable renderingarticulated human pose estimation