Fast Search of a Similar Patch for Self-Similarity Based Image Super Resolution

Jun-Sang YOO
Ji-Hoon CHOI
Kang-Sun CHOI
Dae-Yeol LEE
Hui-Yong KIM
Jong-Ok KIM

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D    No.8    pp.2194-2198
Publication Date: 2016/08/01
Publicized: 2016/05/16
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDL8049
Type of Manuscript: LETTER
Category: Image Processing and Video Processing
Keyword: 
super-resolution,  self-similarity,  kick-out condition,  fast search,  

Full Text: PDF(994.6KB)>>
Buy this Article


Summary: 
In the self-similarity super resolution (SR) approach, similar examples are searched across down-scales in the image pyramid, and the computations of searching similar examples are very heavy. This makes it difficult to work in a real-time way under common software implementation. Therefore, the search process should be further accelerated at an algorithm level. Cauchy-Schwarz inequality has been used previously for fast vector quantization (VQ) encoding. The candidate patches in the search region of SR are analogous to the code-words in the VQ, and Cauchy-Schwarz inequality is exploited to exclude implausible candidate patches early. Consequently, significant acceleration of the similar patch search process is achieved. The proposed method can easily make an optimal trade-off between running speed and visual quality by appropriately configuring the bypass-threshold.

open access publishing via