Modeling of Speech and Gesture in Multi-Person dialogue (2023). Kartik Teotia : HQ3D Avatar: High Quality Controllable 3D Head Avatar (2023). Akshay Mundra: LiveHand: Real-time and Photorealistic Neural [...] Simulator for Non-Rigid 3D Tracking (2021) Vikramjit Sidhu, Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints (2020). Tarun Yenamandra, i3DMM: Deep Implicit Morphable 3D Head Model (2020) [...] Animation from a Motion Capture Database (2003). Former Ph.D. Students Soshi Shimada , PhD in VCAI department (graduated 2024 - thesis: Physically plausible 3D human motion capture and synthesis with interactions)
5 Conference paper D2 D4 T. Alldieck, M. A. Magnor, W. Xu, C. Theobalt, and G. Pons-Moll “Detailed Human Avatars from Monocular Video,” in 3DV 2018 , International Conference on 3D Vision, Verona, Italy [...] and Pattern Recognition (CVPR 2020), Seattle, WA, USA (Virtual), 2020. 2019 3 Conference paper D2 D4 T. Alldieck, M. A. Magnor, B. L. Bhatnagar, C. Theobalt, and G. Pons-Moll “Learning to Reconstruct People [...] Magnor, W. Xu, C. Theobalt, G. Pons-Moll International Conference on 3D Vision, 2018 [project page] [arXiv] Video Based Reconstruction of 3D People Models T. Alldieck, M. Magnor, W. Xu, C. Theobalt, G. Pons-Moll
Publications 2025 1 Paper D2 M. Asim, C. Wewer, T. Wimmer, B. Schiele, and J. E. Lenssen “MEt3R: Measuring Multi-View Consistency in Generated Images,” 2025. [Online]. Available: MEt3R: Measuring Multi-View [...] Society %T MEt3R: Measuring Multi-View Consistency in Generated Images : %G eng %U http://hdl.handle.net/21.11116/0000-0010-7934-C %U MEt3R: Measuring Multi-View Consistency in Generated Images %D 2025 %X We [...] Abstract We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly advancing the field of 3D inference from sparse
Challenging Real-World Scenes 3D Scene Analysis 3D Object Detection Markerless Reconstruction of Dynamic Scenes Advanced Video Processing Recognition of Kitchen Activities in Videos 3D Scene Understanding from
how 3D human shape models from computer graphics can be leveraged to obtain synthetic training data suitable for training models in computer vision. We rely on the recent statistical model of 3D human [...] Challenging Real-World Scenes 3D Scene Analysis 3D Object Detection Markerless Reconstruction of Dynamic Scenes Advanced Video Processing Recognition of Kitchen Activities in Videos 3D Scene Understanding from [...] images. Our method is able to generate synthetic images of people either by directly sampling from 3D shape model or by automatically reshaping real images of people. We validate the effectiveness of our
“Graph Neural Networks,” and “3D Representation Learning.” Lenssen completed his doctoral thesis, titled “Differentiable Algorithms with Data-driven Parameterization in 3D Vision,” in 2022 at the Chair [...] data flows for representations in the field of 3D vision and applying it to different 3D vision tasks. In the ECVA’s award citation, it states: “In his PhD work, Jan Eric Lenssen made a large number of [...] deep, and significant contributions in the area of geometric deep learning, graph neural networks, and 3D representation learning. His contributions to efficient GPU message passing algorithms laid the foundation
does not aim to infer 3D eyeball poses, but directly maps 2D pupil positions to 3D gaze directions in scene camera coordinate space. We first provide a detailed discussion of the 3D gaze estimation task [...] mobile eye tracking and pervasive attentive user interfaces. 3D Gaze Estimation from 2D Pupil Positions on Monocular Head-Mounted Eye Trackers 3D gaze information is important for scene-centric attention [...] attention analysis, but accurate estimation and analysis of 3D gaze in real-world environments remains challenging. We present a novel 3D gaze estimation method for monocular head-mounted eye trackers. In contrast
inside the body in a controlled manner. Using a combination of advanced computational methods and 3D printing, objects are produced that dissolve in liquids in a predetermined manner. A group of Computer [...] Davis), produces 3D objects that dissolve in a desired function of time, hence releasing their content in a controlled way. By cleverly combining mathematical modeling, experimental setup, and 3D printing, the [...] important implications for the pharmaceutical industry, which has recently begun focusing sharply on 3D printing. Controlling pharmaceutical drug levels in patients is an important part of medication. In
Challenging Real-World Scenes 3D Scene Analysis 3D Object Detection Markerless Reconstruction of Dynamic Scenes Advanced Video Processing Recognition of Kitchen Activities in Videos 3D Scene Understanding from [...] networks (CNN) and explore two novel research directions: joint estimation of poses of multiple people and 3D human pose estimation from only a few mobile cameras. Detection and pose estimation in multi-person [...] operated by first detecting the people and then independently estimating their body poses. Multi-view 3D human pose estimation We propose a novel method for the accurate marker-less capture of articulated
Software and Datasets humanshape Humanshape Introduction MPII Human Shape is a family of expressive 3D human body shape models and tools for human shape space building, manipulation and evaluation. Human [...] Thomas Helten and Christian Theobalt and Bernt Schiele} title = {Building Statistical Shape Spaces for 3D Human Modeling}, journal = {Pattern Recognition}, year = {2017} } Download MPII Human Shape, Version [...] fitted meshes (364 MB) CAESAR + NH fitted meshes (363 MB) Source code (GitHub) for data pre-processing, 3D human shape modeling, fitting and evaluation. Examples Below we visualize the first 10 PCA components
