Student assistant in the field of analysis of optical material behavior using machine learning

Fraunhofer-Gesellschaft; Darmstadt; Vor Ort; Teilzeit

Zusammenfassung

A leading research institution in Darmstadt is seeking a talented individual to develop classification and segmentation models based on material properties for their 3D scanning technology project. This role emphasizes strong C++ and Python programming skills, along with knowledge of machine learning techniques. The position involves adapting models for larger datasets and integrating solutions into production environments. Flexibility in working hours between 10-20 hours per week enhances the opportunity for meaningful contributions within a dynamic team.

Qualifikationen

• Very good C++ programming skills.
• Very good Python skills.
• Strong knowledge in mathematics and linear algebra.
• Precise, responsible, independent working style.
• Experience with PyTorch and machine-learning approaches.

Aufgaben

• Develop a model for the classification and segmentation of materials.
• Research relevant features for model adaptation.
• Integrate the model into the production environment.

Kenntnisse

C++ programming skills

Python skills

Knowledge in mathematics and linear algebra

Proficient English skills

Experience with PyTorch

Experience with Qt

Experience with OpenCV

Jobbeschreibung

The Competence Center of Autonomous Digitization Technologies at Fraunhofer IGD develops and automates 3D scanning technologies to allow for automatic 3D reconstruction of cultural heritage and industrial objects. Different acquisition devices are used depending on the object properties and quality requirements. We research modern machine-learning methods for the analysis of an object's optical surface behavior. For this purpose, a solution was developed to infer a surface's material composition based on its optical properties.

Be part of change

The core task is to take over the development of a model for the classification and segmentation of various materials based on their optical properties. These material properties are available as Bi-directional Texture Functions (BTF) and are used as training data for a neural network. Python with PyTorch is used for software development.

This project requires expanding the system to larger datasets as well as applying the technology to hyperspectral data, i.e., surface scans captured with more channels than RGB. For this, it must be researched which features are relevant for the given task and based on that, the model must be adapted.

Additionally, the model should be integrated into our production environment to make the execution and results of analyses easily accessible.

What you contribute

• Very good C++ programming skills
• Very good Python skills
• Strong knowledge in mathematics and linear algebra
• Proficient English skills
• Precise, responsible, independent working style
• Experience with PyTorch and machine-learning approaches
• Experience with the frameworks Qt and OpenCV is advantageous

The weekly working time is 10-20 hours. The position is initially limited to three months, an extension is intended.

We value and promote the diversity of our employees' skills and therefore welcome all applications – regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Our tasks are diverse and adaptable – for applicants with disabilities, we work together to find solutions that best promote their abilities. Remuneration according to the general works agreement for employing assistant staff.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Ready for a change? Then apply now and make a difference! Once we have received your online application, you will receive an automatic confirmation of receipt. We will then get back to you as soon as possible and let you know what happens next.

Fraunhofer Institute for Computer Graphics Research IGD

www.igd.fraunhofer.de

Requisition Number: 82455 Application Deadline: 02/15/2026