Super-resolution imaging (SR) is a class of techniques that improve the resolution of an imaging system. A highly compressed image is typically not only of lowresolution, but also undergoes from compression artifacts. In this paper, we suggest a learning-based framework to accomplish joint single-image SR and deblocking for a highly-compressed image. We say that individually performing deblocking and SR (i.e., deblocking followed by SR, or SR followed by deblocking) on a highly compressed image usually cannot achieve a satisfactory visual quality. In our method, we suggest to learn image sparse representations for modeling the relationship between low and high-resolution image patches in terms of the learned dictionaries for image patches with and without blocking artifacts, respectively.
Article Details
Unique Paper ID: 143621
Publication Volume & Issue: Volume 2, Issue 12
Page(s): 453 - 456
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024