On the exploration of referenced-based super resolution for face images

• Main Author: Ong, Ming Yang
• Other Authors: Chen Change Loy
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• Online Access: https://hdl.handle.net/10356/144598
• Institution: Nanyang Technological University

Over the years, many people have been trying various methods to recover high-frequency image details from lower resolution images. This is mostly due to the rising demands for high-resolution images can be observed for the following fields: Medical, Astronomy and Social Media today. In this report, I will be presenting the different methods I have tested to improve Image Super-Resolution. Specialized area like Face Super-Resolution and Reference Image Super-Resolution will also be introduced and explored in this project. Extensive experiments have been performed to discover underlying reasons for the results achieved.