Thesis - Neural Radiance Fields for Accurate Surface Measurements

In recent years Neural Radiance Fields or NERFs have starter to gain traction. Initially they came with an overwhelming computational cost but have since started to get faster. A NERF provides a way to do novel view synthesis. That is, from a set of pictures of a scene, it can be generate realistic pictures from other views.

Because a NERF has to model the characteristics of the observed scene in a very general way, a NERF also records other properties of a surface or object. Because of this it’s possible to do material detection or surface or reconstruction based on a NERF.

The master thesis work focuses on the following/example of research questions

This thesis would aim to evaluate and compare NERFs to one or more traditional 3D reconstruction methods.

• Are there conditions in industry that would allow for simplifying the problem formulation in a general NERF?
• Are there additional properties of a NERF that can be leveraged in industrial applications?
• How does the overall reconstruction quality compare?

Prerequisites

• Strong image processing background
• Good understanding of 3D transformations and linear algebra
• Fundamental understanding about neural networks

Contact

For more information about the position, contact:

Daniel Rydström, Vision Algorithms, daniel.rydstrom@sick.se

or

Charlotte Axelsson, HR Manager, +46 739 20 99 50.

Welcome with your application 15^th of October at the latest!

SICK is a world-leading supplier of sensors and sensor solutions for industrial applications. We are 11 000 employees in 50 countries and our headquarter is located in Freiburg, Germany. SICK in Linköping is an innovation center for Machine Vision and we are 80 committed employees with a big interest in image processing and visualization. For more than 35 years, our team at SICK Linköping has successfully developed and delivered software for technically leading products within the field of 2D and 3D vision, as well as system solutions for i.e. robot guidance and quality control.

At SICK in Linköping, we are very proud of being a healthy and attractive workplace. For many years, we have been elected as one of the best workplaces in Sweden according to the survey Great Place to Work, the latest award is from 2021. We work actively to reduce our climate footprint and we are active in various ways to contribute to the society and to increase diversity at our workplace.