Date: 30 November 2023
Time: 9:00 AM ET (New York Time)
Speaker(s): Dr. Xin Li
Based on the article: Super-Resolution Image Reconstruction: Selective Milestones and Open Problems
Published: 75th-Anniversary Special Issue of the IEEE Signal Processing Magazine, June 2023
In this talk, I will review the development of image super-resolution technology based on the evolution of key insights associated with the prior knowledge or regularization method from analytical representations to data-driven deep models. The co-evolution of super-resolution with other technical fields, such as autoregressive modeling, sparse coding, and deep learning, will be highlighted in both model-based and learning-based approaches. Model-based super-resolution will include geometry-driven, sparsity-based, and gradient-profile priors; learning-based super-resolution will cover three types of neural network architectures, namely residual networks generative adversarial networks, and pre-trained models. Both model-based and learning-based SR are united by highlighting their limitations from the perspective of model-data mismatch. I will also briefly discuss several open challenges, including arbitrary-ratio, reference-based, and domain-specific super-resolution.
Xin Li (F’17) received the B.S. degree with highest honors in electronic engineering and information science from University of Science and Technology of China, Hefei, in 1996, and the Ph.D. degree in electrical engineering from Princeton University, Princeton, NJ, in 2000. He was a Member of Technical Staff with Sharp Laboratories of America, Camas, WA from Aug. 2000 to Dec. 2002.
He has been a faculty member in Lane Department of Computer Science and Electrical Engineering since Jan. 2003.
Dr. Li was elected a Fellow of IEEE in 2017 for his contributions to image interpolation, restoration and compression.