Gunther Notni

About

Gunther Notni is a leading researcher in optical 3D measurement, robotic perception, and intelligent manufacturing. His work centers on developing advanced sensor systems and algorithms for real-time 3D reconstruction, human-robot interaction, and automated quality inspection. Notni’s major contributions include pioneering deep learning approaches for detecting weld seam discontinuities in laser beam butt welding (18 citations), and creating multimodal imaging systems that fuse RGB, thermal, and 3D point cloud data for safe robotic object handover (16 citations). He developed the BICOS algorithm for fast correspondence search in statistical pattern projection-based active stereo sensors (12 citations), enabling real-time 3D scanning for automation tasks. His research on multi-view planning for simultaneous coverage and accuracy optimization (12 citations) has advanced autonomous 3D reconstruction. Notni has also introduced interactive robot teaching methods using finger trajectory analysis with multimodal RGB-D-T data, and the Triangle-Mesh-Rasterization-Projection algorithm for consistent 2D raster image generation from point clouds. His work on the OHO multimodal dataset supports safe human-robot object handover. With over 90 citations across his top papers, Notni’s innovations are driving the next generation of intelligent, sensor-rich manufacturing systems.

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
   Point Cloud Hand–Object Segmentation Using Multimodal Imaging with Thermal and Color Data for Safe Robotic Object Handover

   16 citations · 2021
3. 3
   BICOS—An Algorithm for Fast Real-Time Correspondence Search for Statistical Pattern Projection-Based Active Stereo Sensors

   12 citations · 2019
4. 4
   Multi-View Planning for Simultaneous Coverage and Accuracy Optimisation

   12 citations · 2010
5. 5
   Interactive robot teaching based on finger trajectory using multimodal RGB-D-T-data

   8 citations · 2023
6. 6
   Triangle-Mesh-Rasterization-Projection (TMRP): An Algorithm to Project a Point Cloud onto a Consistent, Dense and Accurate 2D Raster Image

   8 citations · 2023
7. 7
   View Planning for 3D Reconstruction Using Time-of-Flight Camera Data

   8 citations · 2009
8. 8
   OHO: A Multi-Modal, Multi-Purpose Dataset for Human-Robot Object Hand-Over

   4 citations · 2023
9. 9
   The concept of virtual landmarks in 3D multi-view fringe projection

   4 citations · 2007
10. 10
    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