Hi! Hallo! ¡Hola! Hej! 你好！
A am currently pursuing a Ph.D. at the 3D AI Lab, supervised by Prof. Angela Dai, at TU Munich, working on generative modeling of human behavior and interactions in 3D indoor environments. You can find more on my work on Characteristic 3D Poses here and here. My work on generating 3D human-object interactions sequences from text can be found here. I am also interested in real-time capture (e.g. KinectFusion) of such environments, and completion approaches of the reconstruction results.
During my research internship at Meta Reality Labs, I worked with Minh Vo and Aayush Bansal on reconstruction and object detection approaches in 3D from monocular 2D camera input.
Prior to that, I completed my M.Sc. degree in Informatics at TU Munich with my Master's thesis "3D Shape Completion from Sparse Point Clouds Using Deep Learning" 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.
Highlights
CG-HOI (CVPR'24)
Contact-Guided 3D Human-Object Interaction Generation
Characteristic 3D Poses (CVPR'22)
Forecasting Characteristic 3D Poses of Human Actions
KinectFusionLib
Modern implementation of the KinectFusion approach by Newcombe et al.
Publications
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
Photos
I enjoy photography so here are some of the pictures I have taken:
Check out my 500px page for more pictures.