Filtered Mapping-Based Method for Compressed Web Image Super-Resolution

IEEE Access

Lin Li¹  Xiaoping Liu¹  Wei Jia²  Li Cao²  Yang Zhao³ 

[1] Inf., Hefei Univ. of Technol., Hefei, China;;Sch. of Comput. &School of Computer and Information, Hefei University of Technology, Hefei, China;

关键词: Super-resolution;    upsampling;    deblocking;   

DOI  :  10.1109/ACCESS.2017.2721458

来源: DOAJ

【 摘 要 】

The Web images and videos are often downsampled and compressed to save the bandwidth and storage. Hence, the low-quality and low-resolution Web images/videos cannot match the high-definition display devices nowadays. Unfortunately, traditional image super-resolution (SR) methods are not very robust to compression artifacts. In this paper, we propose an efficient joint SR and deblocking method based on simple three-step-process, which consists of a block-matching and 3D filtering process, a local binary encoding process, and a mapping reconstruction process. Furthermore, the cascade framework and an extra post-processing are also presented for large magnification factors. Experimental results on real-world Web images with obvious compression artifacts demonstrate that the proposed method can reproduce clear and sharp SR results, and effectively remove the unnatural artifacts at the same time.

【 授权许可】

Unknown