*This is a HYBRID Event with in-person attendance in Levine 307 and virtual attendance via Zoom.

ABSTRACT

Event cameras are novel vision sensors that mimic functions from the human retina and offer potential advantages over traditional cameras (low latency, high speed, high dynamic range, etc.). They acquire visual information in the form of pixel-wise brightness changes, called events. This talk presents event processing approaches for motion estimation in computer vision and robotics applications. In particular, we will discuss recent advances by the Robotic Interactive Perception Lab at TU Berlin in extending the contrast maximization framework to stereo depth and optical flow estimation while avoiding its Achilles’ heel: event collapse.