Soren Pirk

Soren’s research interests are in Machine Learning and Visual Computing with a focus on time-variant phenomena and multi-modal data streams. He is interested in developing efficient geometric representations to enable solving complex tasks like interactively simulating natural phenomena, encoding interactions and behavior, or for 4D computer vision. In the past he has worked on topics such as simulating natural phenomena, understanding physical interactions, robotic manipulation and social navigation, learning from demonstration, style transfer, and video prediction.

His personal website with a complete publication list is available here: link.