The topic of this talk is “Deep prior guided networks for High Dynamic-Range (HDR) image generation.” In the talk, I will start with an introduction to HDR imaging and how we generate HDR images using conventional image processing techniques. Next, I will present how to deal with this through our proposed deep prior guided networks. In the end, I will conclude the talk by comparing our proposed methods with others and presenting possible future directions.

Yan-Tsung Peng is an assistant professor of Computer Science at the National Chengchi University (NCCU), Taipei, Taiwan. He joined NCCU in Feb. of 2019. Prior to that, He was once an assistant patent examiner with the Intellectual Property Office, Taiwan and a Senior Engineer with Qualcomm Technologies, Inc., San Diego. He received the Ph.D. degree in electrical and computer engineering from the University of California, San Diego in 2017. His research interests include image processing, video compression, and machine learning and its applications.