News
Prof. Matthias Nießner received the German Pattern Recognition Award 2020!
Sept 29 2020
One paper accepted to NeurIPS 2020!
Sept 26 2020
One paper accepted to Siggraph Asia 2020!
Aug 20 2020
ScanNet won the SGP'2020 Dataset award!
July 9 2020
Luisa Verdoliva was awarded with an IAS Hans Fischer Fellowships and will be joining us as a visiting Professor!
July 7 2020
Five papers accepted to ECCV 2020 Glasgow, Zoom!
July 3 2020
Eight papers accepted to CVPR 2020 in Seattle, WA!
Feb 24 2020
Presenting our research to the Fed. German Gov., chancellor Merkel at Digital Summit Meseberg, Germany!
Nov 18 2019
Five papers accepted to ICCV 2019 Seoul, South Korea!
July 23 2019
Prof. Matthias Nießner wins Eurographics 2019 Young Researcher Award!
May 8 2019
Two papers accepted to Siggraph 2019!
March 28 2019
Five orals and one poster accepted to CVPR 2019!
March 2 2019
We have several PhD and PostDoc openings! Get in touch :)
Jan 30 2019
Face2Face featured as a research highlight in Communications of the ACM on the front cover in January 2019!
January 25 2019
Two papers accepted to ICLR 2019 on learning geometric features!
Dec 19 2018
Prof. Matthias Nießner was awarded the ERC 2018 Starting Grant for Scan2CAD, receiving 1.5 million Euro in Funding!
July 27 2018
Two papers accepted to ECCV 2018, including one oral presentation
July 25 2018
Prof. Matthias Nießner received the Nvidia Professor Partnership Award!
July 10 2018
Leonidas Guibas and Angel Chang were awarded with IAS Hans Fischer Fellowships! They are joining us as Vist. Professors!
Apr 2 2018
We have several PhD and PostDoc openings! Get in touch :)
Mar 24 2018
Prof. Matthias Nießner was awarded the Google Faculty Award for Machine Perception!
Mar 20 2018
Announcing the Robust Vision Challenge 2018 at CVPR - Watch out for the chicken!
Feb 12 2018
Dr. Justus Thies was nominated for the GI 2017 Thesis Award :)
Dec 04 2017

Research Agenda

The Visual Computing & Artificial Intelligence Lab at TUM is a group of research enthusiasts pushing the state of the art at the intersection of computer vision, computer graphics, and machine learning. Our research mission is to obtain high-quality digital models of the real world, which include detailed geometry, surface texture, and material in both static and dynamic environments. In our research, we heavily exploit the capabilities of RGB-D and range sensing devices that are now widely available. However, we ultimately aim to achieve both 3D and 4D recordings from monocular sensors - essentially, we want to record holograms with a simple webcam or mobile phone. We further employ our reconstructed models for specific use cases, such as video editing, immersive AR/VR, semantic scene understanding, and many others. Aside from traditional convex and non-convex optimization techniques, we see great potential in modern artificial intelligence, mainly deep learning, in order to achieve these goals.

Keywords: Visual Computing, 3D Vision, Machine Learning, Artificial Intelligence 3D Reconstruction, Scene Understanding, Semantics, Optimization, GPGPU Programming
Our lab is located at the research campus in Garching. Inside the Faculty of Computer Science, the slide enables both students and visitors to make the journey down from the fourth floor a little quicker than might be expected.