- GenLit: Reformulating Single-Image Relighting as Video Generation, SIGGRAPH Asia 2025
- St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World, ICCV 2025
- ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness, ICCV 2025
- InterDyn: Controllable Interactive Dynamics with Video Diffusion Models, CVPR 2025
Research Experience
Since Autumn 2024, visiting Berkeley AI Research, advised by Angjoo Kanazawa; spent a wonderful summer with Marc Levoy's group at Adobe in 2023, hosted by Cecilia Zhang.
Education
Ph.D.: Max Planck Institute for Intelligent Systems (MPI-IS), advised by Michael J. Black; M.Sc. and B.Sc. in Physics at the University of Tübingen, researched disentangled representation learning with Wieland Brendel and Matthias Bethge at Tübingen AI Center during master's, worked on 3D face reconstruction with Timo Bolkart and Michael J. Black at MPI-IS during bachelor's.
Background
Research interests: machine learning, computer vision, and computer graphics, particularly in how to recreate the visual world. Research explores essential structures in visual data—from 3D geometry, group symmetries to symbolic abstractions, physical priors, and beyond—to develop steerable and scalable learning systems.