Master Thesis "Material Aware Inline 3D Imaging"

Master Thesis "Material Aware Inline 3D Imaging"

In cooperation with TU Wien - Institute for Photogrammetry and Remote Sensing

AIT Austrian Institute of Technology, Austria's largest research and technology organisation for applied research, invites applications at the Center for Vision, Automation & Control in Vienna for a master's thesis position. The work will be carried out in the Competence Unit High-Performance Vision Systems, which develops advanced vision sensor concepts, scalable embedded vision systems and machine learning methods for industrial high-performance visual quality inspection.

The objective of this master's thesis project is to evaluate the potential of material aware 3D reconstruction methods for industrial fast inline inspection applications. Industrial processes often require object knowledge beyond geometrical dimensions, including color, roughness, reflectance behavior and other optically detectable material properties for robust defect detection and quality control.

The master thesis will be carried out in cooperation with TU Wien, Research Group Photogrammetry, and combines application-oriented research with academic expertise in photogrammetry, remote sensing and advanced 3D reconstruction methods. The specific focus will be adapted depending on the student's skills and interests, for example towards material-aware gaussian splatting representation or multispectral imaging.

Tasks

• Acquire basic skills in inline optical 3D imaging for process control and automation.
• Carry out a literature search and review on optical detection and reconstruction of material properties.
• Explore material aware Gaussian Splatting and related approaches or sensing methods like multispectral imaging for fast inline quality control.
• Use the machine vision lab and a digital-twin Blender model of the lab setup to carry out experiments and collect datasets.
• Depending on the thesis direction, expand the existing lab setup with multispectral sensing capabilities.
• Adapt selected Gaussian Splatting algorithms such as RefGS, 3DGSDR or GShader towards modelling and reconstructing material properties.

Requirements

• Ongoing master's studies at TU Wien in Geodesy and Geoinformation, Computer Vision/Image Processing, Computer Science, Physics, Mathematics or similar.
• Good knowledge in computer vision and/or image processing.
• Interest in machine vision, computer graphics and machine learning.
• Experience in at least one programming language, especially Python or C++.
• CUDA, OpenCV or Blender experience is advantageous.
• Hands-on lab work experience with image acquisition using industrial or digital imaging is advantageous.
• Experience in material aware object representation such as Ref-Gaussian or Material-Informed GS is advantageous.
• High level of commitment, team spirit and very good English skills.

Benefits

• Duration of the master's thesis project: 6 months.
• Start date ideally June 2026, with flexibility depending on availability.
• EUR 1.027,40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.
• Opportunity to work on a real-world research challenge from collaborations with industrial partners.
• Hands-on experience with cutting-edge imaging technologies at the forefront of application-driven research.
• Mentoring and a well-established research setting with joint supervision from AIT and TU Wien.

Please submit application documents including CV, cover letter, relevant certificates, transcript of records and proof of identity online.

Apply now