Christina Junger

About

Christina Junger is a researcher at the forefront of intelligent manufacturing and computer vision, specializing in the intersection of deep learning, laser material processing, and 3D imaging. Her work addresses critical challenges in automated production, particularly in laser beam butt welding of thin high-alloy steel sheets. Her most cited paper (2022, 18 citations) introduces a deep learning framework for the automatic detection and prediction of weld discontinuities caused by joint gaps—a problem traditionally solved with inflexible, costly clamping systems. This contribution offers a path toward more adaptive, sensor-driven quality control in industrial welding. Junger also advances 3D perception with the Triangle-Mesh-Rasterization-Projection (TMRP) algorithm (2023, 8 citations), which enables consistent, dense projection of point clouds onto 2D images for multimodal data fusion and robotic scene analysis. Additionally, she has optimized stereo image analysis using deep learning stereo matching frameworks to densify disparity maps for robot-assisted manufacturing. With a growing citation record and a focus on practical, real-time solutions, Junger is establishing herself as a key contributor to the digital transformation of production engineering.

Research Focus

Key Achievements

Top Papers

1. 1
   Automatic detection and prediction of discontinuities in laser beam butt welding utilizing deep learning

   18 citations · 2022
2. 2
   Triangle-Mesh-Rasterization-Projection (TMRP): An Algorithm to Project a Point Cloud onto a Consistent, Dense and Accurate 2D Raster Image

   8 citations · 2023
3. 3
   Optimisation of a stereo image analysis by densify the disparity map based on a deep learning stereo matching framework

   3 citations · 2022

Key Collaborators

Contact & Links