Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Wadim Kehl



Wadim Kehl, M.Sc.

Fakultät für Informatik, I-16
Technische Universität München
Boltzmannstraße 3
85748 Garching b. München, Germany

New Email: wadim.kehl@tri.global

Phone: +49 (89) 289-19417
Room: MI 03.13.037

Research Interests

  • 2D/3D segmentation & scene understanding
  • LIDAR & RGB-D sensing
  • GPGPU applicatons
  • Machine learning methods


  • 2007-2010: B.Sc. in Computer Science from University of (lovely ol') Bonn. Thesis: Classification of sequential 3D LIDAR data using CRFs (PDF, German)
  • 2010-2013: M.Sc. in Computer Science from TUM. Thesis: Interactive Image Segmentation using spatially-varying Color and Texture Distributions. (PDF)
  • Since February 2013: Doctoral student of the CAMP Vision Group in cooperation with Toyota, Inc.



We are always providing theses topics for prospective students. Drop by and ask!

Object reconstruction

Given a sequence of images without pose information, create a 3D CAD representation

Object detection and pose estimation

Given a synthetic 3D CAD model of an object, detect it and estimate its pose in 2D/3D data


W. Kehl, F. Tombari, S. Ilic, N. Navab
Real-Time 3D Model Tracking in Color and Depth on a Single CPU Core
Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, July 2017 (bib)
W. Kehl, F. Manhardt, F. Tombari, S. Ilic, N. Navab
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
International Conference on Computer Vision (ICCV), Venice, Italy, October 2017 [oral].
The first two authors contributed equally to this paper.
S. Zakharov, W. Kehl, B. Planche, A. Hutter, S. Ilic
3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin
International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 2017 (bib)
W. Kehl, T. Holl, F. Tombari, S. Ilic, N. Navab
An Octree-Based Approach towards Efficient Variational Range Data Fusion
British Machine Vision Conference (BMVC), York, UK, September 2016 (bib)
W. Kehl, F. Milletari, F. Tombari, S. Ilic, N. Navab
Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
European Conference On Computer Vision (ECCV), Amsterdam, The Netherlands, October 2016 (bib)
M. Slavcheva, W. Kehl, N. Navab, S. Ilic
SDF-2-SDF: Highly Accurate 3D Object Reconstruction
European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, October 2016 (supplementary) (bib)
W. Kehl, F. Tombari, N. Navab, S. Ilic, V. Lepetit
Hashmod: A Hashing Method for Scalable 3D Object Detection
British Machine Vision Conference (BMVC), Swansea, UK, September 2015 (bib)
S. Habert, Ma Meng, W. Kehl, Xiang Wang, F. Tombari, P. Fallavollita, N. Navab
Augmenting mobile C-arm fluoroscopes via Stereo-RGBD sensors for multimodal visualization
International Symposium on Mixed and Augmented Reality (ISMAR), 2015 (bib)
F. Milletari, W. Kehl, F. Tombari, S. Ilic, A. Ahmadi, N. Navab
Universal Hough dictionaries for object tracking
British Machine Vision Conference (BMVC), Swansea, UK, September 2015 (bib)
W. Kehl, N. Navab, S. Ilic
Coloured signed distance fields for full 3D object reconstruction
British Machine Vision Conference (BMVC), Nottingham, UK, September 2014 (bib)

Teaching Assistance

Title: M.Sc.
Circumference of your head (in cm):  
Firstname: Wadim
Lastname: Kehl
Birthday: 30.03.1986
Nationality: Germany
Languages: English, German
Groups: Computer Vision, Machine Learning for Medical Applications
Expertise: Segmentation, Computer Vision, Sensing
Position: Scientific Staff
Status: Active
Emailbefore: kehl
Emailafter: in.tum.de
Room: MI 03.13.037
Telephone: +49 89 289 19400

Edit | Attach | Refresh | Diffs | More | Revision r1.38 - 06 Aug 2017 - 00:51 - WadimKehl

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif