Fabian Schenk

Fabian Schenk received his BSc Degree in Biomedical Engineering at Graz University of Technology in 2012 and his MSc degree in 2014. During his Master's study he spent one year at the University Carlos III in Madrid, Spain. He is currently doing his PhD as a research assistant at the Institute for Computer Graphics and Vision (ICG) at Graz University of Technology. Even though he initially started his PhD research in the field of semantic segmentation from aerial images, he later moved to robust real-time RGB-D SLAM and dense 3D reconstruction. Since February 2016 he is working on the KIRAS project “CSI SmartScan 3D” in cooperation with the Ludwig Boltzmann Institute Graz (LBI) and Holistic Imaging. The goal of this work is to improve crime scene investigation and documentation with 3D models generated from robust reconstruction and tracking algorithms from data recorded by modern multi-sensor systems (RGB-D, IMU,...). His research interests are in the field of multi-sensor fusion, RGB-D image data, 3D reconstruction, tracking and SLAM systems.

Selected Publications

 A full list of my publications can be found at Google Scholar or in the PURE system of TU Graz.

  • Globally Consistent Dense Real-Time 3D Reconstruction from RGBD Data (Best Paper Award)
    Weilharter R., Schenk, F., Fraundorfer, F.
    Proceedings of the OAGM Workshop 2018: Medical Image Analysis [pdf]
  • Combining Edge Images and Depth Maps for Robust Visual Odometry
    Schenk, F., Fraundorfer, F.
    British Machine Vision Conference (BMVC) 2017 [pdf]
  • Robust Edge-based Visual Odometry using Machine-Learned Edges
    Schenk, F., Fraundorfer, F.
    2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017 [pdf]
  • Guided Sparse Camera Pose Estimation
    Schenk, F., Mohr, L., Rüther, M., Fraundorfer, F., Bischof, H.
    OAGM & ARW Joint Workshop on "Computer Vision and Robotics", 2016, [pdf]
  • Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation
    Schenk, F., Rüther, M., Bischof, H.
    Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016, [pdf]
  • Automatic high-speed video glottis segmentation using salient regions and 3D geodesic active contours
    Schenk, F. , Aichinger, P.,  Roesner, I., Urschler, M.
    Annals of the British Machine Vision Association, 2015, [pdf]
  • Automatic Glottis Segmentation from Laryngeal High-Speed Videos Using 3D Active Contours
    Schenk, F. , Urschler, M., Aigner, C., Roesner, I., Aichinger, P., Bischof, H.
    MIUA, 2014, [pdf]



+43 (316) 873 - 5018
Office hours
by appointment