Comparison of a Transformer-Based Single-Image Super-Resolution Model for the CONNECT Compression Framework

Date of Award

8-1-2024

Degree Name

M.S. in Computer Engineering

Department

Department of Electrical and Computer Engineering

Advisor/Chair

Bradley Ratliff

Abstract

Single-image super-resolution (SISR) is the task of increasing an image’s resolution using one lower resolution image. This task has been used in many areas of life to capture finer details in medical imagery, images with distant objects, and compressed images. Compressing images can save computational resources and bandwidth. Deep Learning (DL) techniques for image compression and SISR have become abundant as such methods have yielded promising results, such as in the Convolutional Neural Network for Enhanced Compression Techniques (CONNECT) compression framework [1] [2] and SwinIR [3], the multi-scale attention network [4], and the Real-ESRGAN [5] super-resolution models. In this thesis, these super-resolution models are to be analyzed and compared with each other using previous work and direct testing on the Set14 dataset with one being selected to be used on the backend of CONNECT as an alternative compression framework. This framework could yield higher compression ratios while maintaining or improving reconstructed image quality. This thesis attempts to improve the existing CONNECT compression framework by analyzing and selecting a DL-based super-resolution model to reconstruct the compressed images after they have been fed through CONNECT. Varying compression methods are then compared using widely used image quality metrics and the compression ratio metric.

Keywords

Image Compression; Super-Resolution; Machine Learning; Transformers; Deep Learning

Rights Statement

Copyright © 2024, author.

Link to Full Text

Share

COinS