Uncertainty in Online Conditional Motion Synthesis

In this project, we aim to study how uncertainty in motion synthesis varies over time when conditioned on sparse AR/VR tracking inputs. Unlike existing approaches that assume uniform uncertainty across frames [1,2], we hypothesize that some motion phases are more predictable than others; for example, a walking cycle is rarely interrupted mid-step. By modeling this temporally varying uncertainty, we aim to improve the efficiency and coherence of interactive virtual experiences.

Project Team

Prof. Olga Sorkine Hornung

Olga Sorkine-Hornung’s research focuses on computer graphics, geometric modeling and geometry processing. She is interested in the theoretical foundations and practical algorithms for digital content creation, such as shape representation and editing, artistic modeling techniques, digital fabricatio, computer animation and image and video processing. She works on fundamental problems in digital geometry processing, including parameterization of discrete surfaces and compression of geometric data. Olga Sorkine leads the Interactive Geometry Lab (IGL) at ETH Zurich.

Dr. Emre Aksan

Dr. Thabo Beeler

Thabo Beeler is currently a Research Director at Google, where he is heading the Syntec team within AR Perception. They work on digital humans in the context of virtual and augmented reality, focusing on capture, reconstruction, appearance acquisition, generative modeling, and synthesis. Prior to that, Thabo Beeler was a research scientist at Disney Research | Studios where he built up the Capture and Effects group, focusing on digital humans for film.

Peizhuo Li

Publications

Categorical Codebook Matching for Embodied Character Controllers

Authors:
Sebastian Starke
Paul Starke
Nicky He
Taku Komura
Yuting Ye

TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis

Authors:
Zihan Zhang
Richard Liu
Kfir Aberman
Rana Hanocka