Date: 10 November 2023, Friday
Time: 4:30 PM
Venue: CD634, The Hong Kong Polytechnic University
Zoom Meeting ID: 270 294 7238
Password: 123456
Speaker: Dr Yi Wang, The Hong Kong Polytechnic University
Image and Video Restoration and Benchmarking in Bitstream Corruptions
Dr Yi Wang, The Hong Kong Polytechnic University
Abstract: Image and video restoration is a long-standing problem in computer vision, which aims to recover or improve the image/video quality that has been degraded by various corruptions such as noise, blur, and compression artifacts. The restoration methods can also be used to recover crucial visual information for digital forensics and make AI-based vision robust to common corruptions. In this talk, we investigate a real-world image and video restoration problem with bit errors on the encoded bitstream due to unreliable communication channels or physical damage of storage medium. The bitstream corruptions cause complicated and unpredictable error patterns in the pixel domain, such as image block misalignment, blocking artifacts, color artifacts, ghosting effect, content loss, and novel combinations of those, which cannot be addressed by existing techniques trivially. We will present our recent studies on bitstream-corrupted image/video restoration and benchmarking.
Speaker’s Bio: Dr. Yi Wang received the BEng in Electronic and Information Engineering and MEng in Signal and Information Processing from Northwestern Polytechnical University, China, and earned PhD in the School of Electrical and Electronic Engineering from Nanyang Technological University, Singapore, in 2021. He is currently a Research Assistant Professor in the Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong. He has published more than 20 papers in journals and international conferences, including IEEE Transactions (e.g., IEEE TIP, TCSVT, TNNLS, and TMM), CVPR, and NeurIPS. He worked as a Research Fellow in Nanyang Technological University, Singapore, from 2021 to 2023. His research interest includes Image/Video Processing, Computer Vision, Machine Learning, and Digital Forensics. He is IEEE Member. He served as Associate Editor of The Visual Computer.
