Optoelectronics Letters

, Volume 14, Issue 5, pp 391–395 | Cite as

Depth image super-resolution algorithm based on structural features and non-local means

  • Wang Jing (王靖)
  • Wei-Zhong Zhang (张维忠)Email author
  • Bao-Xiang Huang (黄宝香)
  • Huan Yang (杨环)


The resolution and quality of the depth map captured by depth cameras are limited due to sensor hardware limitations, which becomes a roadblock for further computer vision applications. In order to solve this problem, we propose a new method to enhance low-resolution depth maps using high-resolution color images. The structural-aware term is introduced because of the availability of structural information in color images and the assumption of identical structural features within local neighborhoods of color images and depth images captured from the same scene. We integrate the structural-aware term with color similarity and depth similarity within local neighborhoods to design a local weighting filter based on structural features. To use non-local self-similarity of images, the local weighting filter is combined with the concept of non-local means, and then a non-local weighting filter based on structural features is designed. Some experimental results show that super-resolution depth image can be reconstructed well by the process of the non-local filter and the local filter based on structural features. The proposed method can reconstruct much better high-resolution depth images compared with previously reported methods.

Document code


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Yanjie Li, Tianfan Xue, Lifeng Sun and Jianzhuang Liu, IEEE International Conference on Multimedia and Expo, IEEE Computer Society, 152 (2012).Google Scholar
  2. [2]
    K. R. Lee, R. Khoshabeh and T. Nguyen, Signal Processing Conference IEEE, 1124 (2012).Google Scholar
  3. [3]
    Weiwei Di, Xudong Zhang, Liangmei Hu and Linlin Duan, Journal of Image and Graphics 19, 1162 (2014). (in Chinese)Google Scholar
  4. [4]
    J. Xie, R. S. Feris and M. T. Sun, IEEE International Conference on Image Processing 25, 3773 (2015).Google Scholar
  5. [5]
    Jaesik Park, Hyeongwoo Kim, Yu-Wing Tai, Michael S. Brown and Inso Kweon, IEEE International Conference on Computer Vision 24, 1623 (2011).Google Scholar
  6. [6]
    Qingxiong Yang, Ruigang Yang, James Davis and David Nister, IEEE Conference on Computer Vision and Pattern Recognition, 1 (2007).Google Scholar
  7. [7]
    J. Kopf, M. F. Cohen, D. Lischinski and M. Uyttendaele, ACM Transactions on Graphics (TOG) 26, 96 (2007).CrossRefGoogle Scholar
  8. [8]
    K. He, J. Sun and X. Tang, IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 1397 (2013).CrossRefGoogle Scholar
  9. [9]
    Y. F. Tu, X. D. Zhang, J. Zhang and L. M. Hu, Computer Applications and Software 34, 220 (2017). (in Chinese)Google Scholar
  10. [10]
    Y. X. Yang and Z. F. Wang, Pattern Recognition and Artificial Intelligence 26, 454 (2013). (in Chinese)Google Scholar
  11. [11]
    J. Zhang, Dissertation for Doctor’s Degree, University of Science and Technology of China, 2015. (in Chinese)Google Scholar
  12. [12]
    H. X. Yuan, P. An, S. Q. Wu, Y. Zheng and C. Y. Tong, Journal of Computer-Aided Design and Computer Graphics 28, 2195 (2016). (in Chinese)Google Scholar
  13. [13]
    C. Tomasi and R. Manduchi, International Conference on Computer Vision, 839 (1998).Google Scholar
  14. [14]
    F. L. Liu, M. R. Sun and W. N. Cai, Optoelectronics Letters 13, 237 (2017).ADSCrossRefGoogle Scholar
  15. [15]
    A. Buades, B. Coll and J. M. Morel, Siam Journal on Multiscale Modeling and Simulation 4, 490 (2005).CrossRefGoogle Scholar
  16. [16]
    J. Chen, C. K. Tang and J. Wang, ACM Transaction on Graphics 28, 1 (2009).Google Scholar
  17. [17]
    D. Scharstein and C. Pal, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1 (2007).Google Scholar

Copyright information

© Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Wang Jing (王靖)
    • 1
  • Wei-Zhong Zhang (张维忠)
    • 1
    Email author
  • Bao-Xiang Huang (黄宝香)
    • 1
  • Huan Yang (杨环)
    • 1
  1. 1.College of Computer Science and TechnologyQingdao UniversityQingdaoChina

Personalised recommendations