The Visual Computing & Artificial Intelligence Group has a variety of job offers, including PostDoc / PhD positions and Master / Bachelor theses. Candidates should be strongly interested in performing cutting edge research in very active and exciting areas, such as deep learning, 3D modeling, and many more.


Please read carefully: Due to a high humber of applications, we ignore incomplete applications that fail to submit all application documents (CV, recommendation letters, transcript of records, etc.). We also cannot respond to vague templatized applications that are unrelated to our research. IMPORTANT details can be found in the PDF-Flyer!

Unfortunately, we do not have any openings for undergraduate students. If you are interested working with us please apply to the TUM Master program.

If you are invited for an interview, you are expected to prepare a 15 minutes presentation (50% about existing work; 50% about your future research). Expect your coding skills to be tested during the interview!

PhD Positions


PhD Positions (TV-L E13, 100%)
Neural Rendering, 3D Reconstruction, SLAM / Pose Tracking, Semantic Scene Understanding, Face/Body Tracking, Non-Linear Optimization, Media Forensics / Fake News Detection
Qualification Masters degree; expert level coding skills; strong background in numerical optimization; good english skills are essential; some set of vision / graphics / ML lectures; knowledge in scripting languages that are used by modern deep learning frameworks (e.g., Lua or Python) is a plus; extremely high motivation and dedication
Description We are looking for outstanding PhD candidates who are enthusiastic about cutting edge research in computer vision, computer, graphics, and machine learning. The Visual Computing Group focuses on digitizing of real-world environments and semantic scene understanding. This area is heavily inspired by the rapid progress of range sensing technology, such as the Microsoft Kinect and LIDAR systems, as well as the availability of large data collections. In addition to this newly-available sensor technology, algorithmic advances in deep learning and convolutional neural networks open up a wide range of opportunities for cutting-edge research in static and dynamic 3D capture; for instance, targeting applications in virtual and augmented reality.
Contact Via Application Form  
Extra
DocumentsCV; Transcripts (BA & MA); Short Research Statement; ask two references for recommendation letters to support your application

PostDoc Positions


PostDoc Positions (TV-L E13/14, 100%)
Neural Rendering, 3D Reconstruction, SLAM / Pose Tracking, Semantic Scene Understanding, Face/Body Tracking, Non-Linear Optimization, Media Forensics / Fake News Detection
Qualification PhD degree; track record at top-tier venues (CVPR, SIGGRAPH, ECCV, ICCV, NIPS); expert level coding skills; profound knowledge of numerical optimization; extremely high motivation and dedication
Description We are looking for exceptional PostDocs in computer vision, computer, graphics, and machine learning. The Visual Computing Group focuses on digitizing real-world environments and semantic scene understanding. This area is heavily inspired by the rapid progress of range sensing technology, such as the Microsoft Kinect and LIDAR systems, as well as the availability of large data collections. In addition to this newly-available sensor technology, algorithmic advances in deep learning and convolutional neural networks open up a wide range of opportunities for cutting-edge research in static and dynamic 3D capture; for instance, targeting applications in virtual and augmented reality.
Contact Prof. Dr. Matthias Nießner  
Extra
DocumentsCV; Transcripts (BA & MA); Short Research Statement; ask two references to directly email recommendation letters to support your application

Master/Bachelor Theses


Master Theses
Deep Learning, 3D Reconstruction, and Visual Computing
Qualification only for TUM students; expert level coding skills; strong background in numerical optimization; knowledge in scripting languages that are used by modern deep learning frameworks (e.g., Lua or Python) is a plus; extremely high motivation and dedication
Description We offer a variety of master theses, including "Semantic Understanding of 3D Scenes with Deep Learning", "Robust 3D Reconstructions with Commodity RGB-D Sensors", "Face Tracking and Facial Reenactment", "A Language for Non-Linear Least Squares Optimization in Graphics and Vision". If you are interested and highly-motivated to work at the intersection of computer vision, computer, graphics, and machine learning, please send us an email!
Contact Prof. Dr. Matthias Nießner  
Extra
DocumentsCV; Transcripts (BA & MA)