Our work Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture has been accepted at the 2026 International Conference on 3D Vision (3DV).
Our work "HiMAP: History-aware Map-occupancy Prediction with Fallback" has been accepted at IEEE International Conference on Robotics and Automation (ICRA) . This is a joint work with the Institute of Cartography and Geoinformatics.
Several abstracts with tnt participation on a range of topics combining AI and MR physics for medical imaging have been accepted for ISMRM 2026 in Cape Town! - 4 oral presentations, 3 power pitches and multiple posters - congrats to all!
Our work on "Air Compressor Control Optimization in Commercial Vehicles Using Reinforcement Learning" has been accepted at IEEE International Conference on Robotics and Automation (ICRA) . This is a joint work with the Hochschule Hannover (Timo v. Macard) and ZF (Hannover). Details will follow
Our work on Grouping Nodes with known Value Differences: A lossless UCT-based Abstraction Algorithm has been accepted at The Fourteenth International Conference on Learning Representations (ICLR) .
Our proposed Special Session on Safety integration in neural networks for sensor systems in critical applications (NNiS) has been accepted and will be part of the 2026 IEEE World Congress on Computational Intelligence (WCCI). The session introduces a novel perspective by addressing the regulatory and safety integration of neural networks within sensor network environments.
The “Institut für Informationsverarbeitung” (Institute of Information Processing) is the home of machine learning at the Leibniz University Hannover. We focus on three main research directions, namely (I) computer vision & representation learning, (II) signal processing & -coding and (III) automated machine learning. Our methods range from deep learning, automated machine learning, reinforcement learning, image analysis, remote sensing and compression of audio, image, video as well as DNA to biomedical data. Our efforts are directed towards making efficient use of multi-modal and high dimensional data for reliable predictions, ultimately supporting end-users, developers and decision makers in a vast range of applications.
Since the foundation in 1973, the institute holds a strong tradition of cultivating connections to industry partners and jointly developing solutions to automatically process and harness information. Some of the developed methodology were successfully spun-off commercially as for instance with driver assistance modules, cochlear implants or component testing. The institute is also well known for being actively involved in the standardization of MP3, MPEG-2, AVC (H.264), HEVC (H.265) as well as MPEG-G.
Do you want to join us? We have open positions.
