Self-learning-based single image super-resolution of a highly compressed image

Li Wei Kang, Bo Chi Chuang, Chih Chung Hsu, Chia Wen Lin, Chia Hung Yeh

研究成果: 書貢獻/報告類型會議論文篇章

19 引文 斯高帕斯(Scopus)

摘要

Low-quality images are usually not only with low-resolution, but also suffer from compression artifacts (blocking artifact is treated as an example in this paper). Directly performing image super-resolution (SR) to a highly compressed (low-quality) image would also simultaneously magnify the blocking artifacts, resulting in unpleasing visual quality. In this paper, we propose a self-learning-based SR framework to simultaneously achieve single-image SR and compression artifact removal for a highly-compressed image. We argue that individually performing deblocking first, followed by SR to an image, would usually inevitably lose some image details induced by deblocking, which may be useful for SR, resulting in worse SR result. In our method, we propose to self-learn image sparse representation for modeling the relationship between low and high-resolution image patches in terms of the learned dictionaries, respectively, for image patches with and without blocking artifacts. As a result, image SR and deblocking can be simultaneously achieved via sparse representation and MCA (morphological component analysis)-based image decomposition. Experimental results demonstrate the efficacy of the proposed algorithm.

原文英語
主出版物標題2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013
頁面224-229
頁數6
DOIs
出版狀態已發佈 - 2013
對外發佈
事件2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013 - Pula, Sardinia, 意大利
持續時間: 2013 9月 302013 10月 2

出版系列

名字2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013

會議

會議2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013
國家/地區意大利
城市Pula, Sardinia
期間2013/09/302013/10/02

ASJC Scopus subject areas

  • 訊號處理

指紋

深入研究「Self-learning-based single image super-resolution of a highly compressed image」主題。共同形成了獨特的指紋。

引用此