Talk Abstract: Event-based vision Sensors (EVS) generate events by detecting relative illumination changes that exceed a predefined temporal contrast threshold at the pixel level. This behavior conserves bandwidth and power when portions of the scene remain static. As EVS asynchronously read these events, they provide high-temporal resolution data suitable for complementing conventional frame-based CMOS Image Sensors (CIS). Emerging hybrid CIS+EVS sensors leverage the high spatial resolution of CIS intensity frames and the high temporal resolution of event data to enhance applications such as motion blur reduction or video-frame interpolation (VFI) for slow-motion video capture. In this presentation, we will showcase our use case study of hybrid EVS+CIS sensors, focusing on the fusion of CIS images with EVS data in the domain of photography.

Speaker Biography: Bo Mu is a Director of Algorithm Development at Omnivision Technologies, where he leads the development of advanced imaging technology. Before joining Omnivision, he served as a Senior System Engineer at KLA+ from 2007 to 2011, a Senior Principal Engineer at Fairchild Imaging and BAE Systems Imaging Solutions from 2011 to 2017, and the Manager of Sensor Integration at Quanergy from 2017 to 2019. He earned his Ph.D. in Imaging Science from the Rochester Institute of Technology in 2007. He has authored or co-authored numerous papers and patents. His current research interests include emerging imaging technologies, video and image processing, camera ISPs, imaging system simulation, machine learning, and computer vision.