Image and Video Super-Resolution in the Wild

[CFAR Outstanding PhD Student Seminar Series 1]
Image and Video Super-Resolution in the Wild by Mr Kelvin Chan
16 Mar 2022 | 02:00pm (Singapore Time)

With the increasing need for high-resolution content, there is an urge to develop super-resolution techniques that improve the resolution of images and videos captured from non-professional imaging devices. Researchers have made incessant efforts to improve the resolution of images and videos to meliorate user experience and enhance performance in downstream tasks. Most existing approaches focus on designing an image-to-image mapping, failing in employing auxiliary information readily available in reality. As a result, such methods often possess suboptimal effectiveness and efficiency owing to inadequate information aggregation and large network complexity. In addition, it remains nontrivial to generalise to uncontrolled scenes, whose degradations could be complex, diverse, and unknown.

In this talk, Mr. Kelvin Chan will first give a brief introduction to the recent developments of super-resolution. He will also present his efforts on effective image and video super-resolution and generalisation to real-world degradations through exploiting generative priors and temporal information.

Kelvin C.K. Chan, NTU
Mr Kelvin C.K. Chan
S-Lab for Advanced Intelligence
Nanyang Technological University

Kelvin C.K. Chan received his BSc degree in Mathematics, BEng degree in Information Engineering and MPhil degree in Mathematics from The Chinese University of Hong Kong in 2015, 2016, 2018, respectively. He is currently a fourth-year PhD student at S-Lab, Nanyang Technological University. His research interest includes various topics in low-level vision, such as super-resolution and deblurring. He has received the Google PhD Fellowship and has won seven champions in the NTIRE video restoration challenge. He is a reviewer for various conferences and journals, and was selected as an outstanding reviewer for ICCV 2021.