Hi!^1000 I'm Christian
Hi!^500 I'm a Research Scientist at Beyond Presence
Hi!^500 I'm working on conversational human avatars
Hi!^1000 I'm Christian
Hi!^500 I'm a Research Scientist at Beyond Presence
Hi!^500 I'm working on conversational human avatars
I am a Research Scientist at Beyond Presence, working on the next generation of conversational real-time human avatars. I received my Ph.D. from TU Munich, supervised by Prof. Angela Dai at the 3D AI Lab. My research is focused on advancing generative modeling of realistic human avatars and their spatial environments.
You can find more about my research on modeling 3D human behavior here and here and on how to model human-object interactions here. I also worked on real-time spatial capture (see my implementation of KinectFusion), and completion approaches of such captures.
During my time at Meta Reality Labs, I worked with Federica Bogo, Buğra Tekin, and Bharat Bhatnagar on modeling human motion using large language models (LLMs). I also worked with Minh Vo and Aayush Bansal on reconstruction and object detection approaches using neural rendering techniques (NeRF).
Prior to that, I completed my M.Sc. degree in Informatics at TU Munich supervised by Prof. Matthias Nießner, and my B.Sc. Informatics and Multimedia at the University of Augsburg, working with Christoph Lassner and Prof. Rainer Lienhart.
News
I joined Beyond Presence as a Research Scientist to build the next generation of conversational real-time human avatars 🚀
I successfully defended my Ph.D. thesis 3D Human Behavior Generation through Action and Interaction Synthesis. Many thanks to my supervisor, Prof. Angela Dai, and second examiner, Prof. Michael Black 🎓
I am joining Meta Reality Labs Research in Zürich, Switzerland this summer to work on 3D human motion generation with Federica Bogo.
Two papers accepted to CVPR 2024: CG-HOI: Contact-Guided 3D Human-Object Interaction Generation and FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations. See you in Seattle 🙂
I am joining Meta Reality Labs Research in Seattle for the summer and will work on 3D neural rendering approaches with Minh Vo.
Forecasting Characteristic 3D Poses of Human Actions was accepted to CVPR 2022! See you in New Orleans ✈️
Research
I am interested in creating 3D human avatars that move and interact realistically with their environment. This includes generating 3D human motion alongside explicit human-object and human-scene interactions.
In the past I also worked on 3D scene reconstruction such as KinectFusion, deep-learning-based refinement of such reconstructions, and applications thereof in a medical context.
CG-HOI: Contact-Guided 3D Human-Object Interaction Generation
FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations
Forecasting Characteristic 3D Poses of Human Actions
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
Theses
3D Human Behavior Generation through Action and Interaction Synthesis
Learning how to share a common space between autonomous systems and humans requires the capability to understand, generate, and forecast human actions and interactions.
30 Dec 2024
3D Shape Completion from Sparse Point Clouds Using Deep Learning
We tackle the problem of generating dense representations from sparse and partial point clouds. We achieve this with a data-driven approach which learns to complete incoming sets of 3D points in a fully-supervised manner.
15 Jul 2019
Misc. Projects
BundleACeres - Structure from Motion using Bundle Adjustment with the Ceres Solver
An implementation of Bundle Adjustment with the Ceres Solver as optimizer. It matches a chain of incoming RGB images using ORB keypoints and BRISK descriptors in order to find 3D points. The Ceres Solver is then used to jointly solve for the locations of 3D points and camera poses of the frames. It is implemented in modern C++14 and utilizes OpenCV 3, Ceres, PCL and others.
KinectFusionLib - Modern Implementation of the KinectFusion Approach
Implementation of the KinectFusion approach to generating three-dimensional models from depth image scans. Here, the original method has been extended with the MarchingCubes algorithm to allow exporting the model as a dense surface mesh. Realized in modern C++14 and CUDA to allow real-time reconstruction. Developed in the context of an interdisciplinary project in cooperation with the Chair for Computer Aided Medical Procedures and Augmented Reality and Dynamify GmbH.
VideoMagnification - Magnify motions and detect heartbeats
This application allows the user to magnify motion and detect heartbeats from videos and webcam video streams. It is an implementation of Wu, Hao-Yu, et al.: “Eulerian video magnification for revealing subtle changes in the world”. You can find out more about motion magnification on the project homepage. My implementation can be found here. It makes use of modern C++11, the open-source vision library OpenCV 3.1 and the UI framework QT 5.
Spatial Pyramid Pooling as an additional layer in caffe
An implementation of the concept proposed in He, Kaiming, et al. “Spatial pyramid pooling in deep convolutional networks for visual recognition“. It adds a new custom layer to the AlexNet architecture which performs spatial pyramid pooling in order to remove the network’s need for fixed-size input images. This was part of my Bachelor’s Thesis which I wrote at the Multimedia Computing and Computer Vision Lab, University of Augsburg under the supervision of...
Training methods for the decision forest library fertilized forests
Worked with Christoph Lassner on his library fertilized forests and implemented several boosted training methods like AdaBoost and SAMME. You can have a look at the project homepage or read the paper which received an honorable mention at the ACM MM OSSC 2015.
Photography
I enjoy photography so here are some of the pictures I have taken:
Check out my 500px page for more pictures.