Antialiased super-resolution with parallel high-frequency synthesis

Xudong JIANG, Bin SHENG, Weiyao LIN, Ping LI, Lizhuang MA, Ruimin SHEN

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Image super-resolution (SR) increases the resolution of the target image, and has become a fundamental image-editing operation for real-world applications. Traditional methods often cause jaggies and blurring artifacts because natural images generally contain a lot of discrete continuities and edges. This paper proposes a new synthesis-based method for image super-resolution at a pixel level that takes advantages of convolution-based edge anti-aliasing. The target images are divided into two components representing, respectively, the high- and low-frequency contents of the images. We perform bicubic interpolation to reconstruct the missing information in the low-frequency component. A patch-based texture synthesis is subsequently adopted to synthesize the high-frequency patches with the final upscaled images. In particular, we also use the efficient edge-based anti-aliasing for correcting the quantization error, restore the high-frequency details damaged by nonlinear example-based synthesis. Our proposed approach generates super-resolution images dynamically and can be fully implemented in GPU parallelization. Experiments confirm the visual superiority of our proposed approach in comparison with competing state-of-the-art techniques. Copyright © 2015 Springer Science+Business Media New York.
Original languageEnglish
Pages (from-to)543-560
JournalMultimedia Tools and Applications
Volume76
Issue number1
Early online dateNov 2015
DOIs
Publication statusPublished - Jan 2017

Fingerprint

Anti-aliasing
Image resolution
Convolution
Interpolation
Textures
Pixels
Industry
Experiments
Graphics processing unit

Citation

Jiang, X., Sheng, B., Lin, W., Li, P., Ma, L., & Shen, R. (2017). Antialiased super-resolution with parallel high-frequency synthesis. Multimedia Tools and Applications, 76(1), 543-560.

Keywords

  • Super-resolution
  • Convolution
  • Edge anti-aliasing
  • Texture synthesis