Advertisement

Multimedia Tools and Applications

, Volume 76, Issue 8, pp 11143–11155 | Cite as

Edge-directed single image super-resolution via cross-resolution sharpening function learning

  • Wei Han
  • Jun Chu
  • Lingfeng Wang
  • Chunhong Pan
Article

Abstract

Edge-directed single image super-resolution methods have been paid more attentions due to their sharp edge preserving in the recovered high-resolution image. Their core is the high-resolution gradient estimation. In this paper, we propose a novel cross-resolution gradient sharpening function learning to obtain the high-resolution gradient. The main idea of cross-resolution learning is to learn a sharpening function from low-resolution, and use it in high-resolution. Specifically, a blurred low-resolution image is first constructed by performing bicubic down-sampling and up-sampling operations sequentially. The gradient sharpening function considered as a linear transform is learned from blurred low-resolution gradient to the input low-resolution image gradient. After that, the high-resolution gradient is estimated by applying the learned gradient sharpening function to the initial blurred gradient obtained from the bicubic up-sampled of the low-resolution image. Finally, edge-directed single image super-resolution reconstruction is performed to obtain the sharpened high-resolution image. Extensive experiments demonstrate the effectiveness of our method in comparison with the state-of-the-art approaches.

Keywords

Super-resolution Gradient magnitude transformation Linear transformation function 

References

  1. 1.
    Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans Pattern Anal Mach Intell 24(9):1167–1183CrossRefGoogle Scholar
  2. 2.
    Chang H, Yeung D-Y, Xiong Y (2004) Super-resolution through neighbor embedding. In: Proceedings IEEE conference computer vision pattern recognition, pp 275–282Google Scholar
  3. 3.
    Dai S, Han M, Xu W, Wu Y, Gong Y (2007) Soft edge smoothness prior for alpha channel super resolution. In: Proceedings IEEE conference computer vision pattern recognition, pp 1–8Google Scholar
  4. 4.
    Fattal R (2007) Image upsampling via imposed edge statistics. ACM Trans Graph 26(13):95:1–95:5Google Scholar
  5. 5.
    Fattal R (2007) Image upsampling via imposed edge statistics. ACM Trans Graph (Proceedings of SIGGRAPH 2007) 26(13):95:1–95:8Google Scholar
  6. 6.
    Freedman G, Fattal R (2010) Image and video upscaling from local self-examples. ACM Trans Graph 28(3):1–10Google Scholar
  7. 7.
    Freeman WT, Jones TR, Pasztor EC (2002) Example-based superresolution. IEEE Comput Graph Appl 22(2):56–65CrossRefGoogle Scholar
  8. 8.
    Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. In: International conference on computer vision, pp 349–356Google Scholar
  9. 9.
    Irani M, Peleg S (1993) Motion analysis for image enhancement: Resolution, occlusion and transparency. J Vis Commun Image Represent 4(4):324–335CrossRefGoogle Scholar
  10. 10.
    Kim K, Kwon Y (2008) Example-based learning for singleimage SR and JPEG artifact removal, Max Planck’Insitut fur biologische Kybernetik, Tbingen, Germany Tech, RepGoogle Scholar
  11. 11.
    Lin Z, Shum H-Y (2004) Fundamental limits of reconstruction-based superresolution algorithms under local translation. IEEE Trans Pattern Anal Mach Intell 26(1):83–97CrossRefGoogle Scholar
  12. 12.
    Morse BS, Schwartzwald D (2001) Image magnification using level set reconstruction. In: Proceedings IEEE conference computer vision pattern recognition, pp 333–340Google Scholar
  13. 13.
    Shan Q, Li Z, Jia J, Tang C-K (2008) Fast image/video upsampling. ACM Transactions on Graphics (SIGGRAPH ASIA) 127(17):153:1–153:7Google Scholar
  14. 14.
    Sun J, Xu Z, Shum H-Y (2008) Image super-resolution using gradient profile prior. In: Proceedings IEEE conference computer vision pattern recognition, pp 1–8Google Scholar
  15. 15.
    Sun J, Xu Z, Shum H-Y (2011) Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Trans Image Process 20(6):1529–1542MathSciNetCrossRefGoogle Scholar
  16. 16.
    Tai Y-W, Liu S, Brown MS, Lin S (2010) Super resolution using edge prior and single image detail synthesis. In: Proceedings IEEE conference computer vision pattern recognition, pp 2400–2407Google Scholar
  17. 17.
    Wang LF, Xiang SM, Meng GF, Wu HY, Pan CH (2013) Edge-Directed Single-Image Super-Resolution Via Adaptive Gradient Magnitude Self-Interpolation. IEEE Trans Circuits Syst Video Technol 23(8):1289–1299CrossRefGoogle Scholar
  18. 18.
    Yang J, Lin Z, Cohen S (2013) Fast image super-resolution based on in-place example regression. In: IEEE conference on computer vision and pattern recognition, pp 1059–1066Google Scholar
  19. 19.
    Yang J, Wright J, Ma Y, Huang T (2008) Image super-resolution as sparse representation of raw image patches. In: Proceedings IEEE conference computer vision pattern recognition, pp 1–8Google Scholar
  20. 20.
    Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Wei Han
    • 1
    • 2
  • Jun Chu
    • 1
    • 2
  • Lingfeng Wang
    • 3
  • Chunhong Pan
    • 3
  1. 1.Institute of Computer VisionNanchang Hangkong UniversityNanchangChina
  2. 2.Nanchang Hangkong UniversityNanchangChina
  3. 3.NLPR, Institute of AutomationChinese Academy of SciencesBeijingChina

Personalised recommendations