Color-Guided Restoration and Local Adjustment of Multi-resolution Depth Map

  • Xingrui ZhangEmail author
  • Qian Guo
  • Yudong Guan
  • Jianying Feng
  • Chunli Ti
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 670)


The depth map obtained by Microsoft Kinect is often accompanied with a large area information loss called black hole. In this paper, an optimal algorithm for image restoration with multi-resolution anisotropic diffusion is proposed to fill the black areas. At the same times, the restriction of anisotropic diffusion algorithm can be broken through by using multi-resolution. Using the color map as a guidance to refine the details of the image. Then according to local adjustment, the error rate can be effectively reduced. At the end of this paper, the joint bilateral filter (JBF) is introduced as a contrast, and the PCL open source point cloud database is used for 3D reconstruction. Compared with competing methods, the proposed algorithm can fill the larger black holes significantly. The experiments show that it also has good performance on reducing the error rate and preserving the edge details.


Computer vision Depth map enhancement Anisotropic diffusion 3D reconstruction 


  1. 1.
    Buades, A, B., Coll, and J. M. Morel.: A non-local algorithm for image denoising. IEEE Computer Society Conference on Computer Vision and Pattern Recognition IEEE Computer Society, 60–65, (2005).Google Scholar
  2. 2.
    Min, D., Lu, J., Do, M.N.: Depth video enhancement based on weighted mode filtering. IEEE Trans. Image Process. 21, 1176–1190 (2012).Google Scholar
  3. 3.
    He, K., Sun, J., Tang, X.: Guided Image Filtering. In: Daniilidis K., Maragos P., Paragios N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6311. Springer, Berlin, Heidelberg (2010).Google Scholar
  4. 4.
    Camplani, M., Salgado, L.: Efficient spatio-temporal hole filling strategy for Kinect depth maps. Proceedings of SPIE, 8290, 13 (2012).Google Scholar
  5. 5.
    Jin-yi, Liu., Xiao-jin, Gong., Ji-lin, Liu.: Guided in painting and filtering for Kinect depth maps // international Conference on Pattern Recognition, Tsukuba, IEEE, 2055–2058, (2012).Google Scholar
  6. 6.
    S, Liu., Y, Wang., et al.: Kinect depth restoration via energy minimization with TV21 regularization // International Conference on Image Processing, Melbouene, IEEE, 724–727 (2013).Google Scholar
  7. 7.
    NE, Yang., YG, Kim., RH, Park.: Depth hole filling using the depth distribution of neighboring regions of depth holes in the Kinect sensor // Signal Processing, Communication and Computing, Hong Kong, IEEE, 658–661 (2010).Google Scholar
  8. 8.
    Jia-lun, Kang., Xiang-hong, Tang.: A direction image in painting algorithm based on fast marching method. Journal of Hangzhou Dianzi University, 32, 147–150 (2012).Google Scholar
  9. 9.
    Janoch, A., Karayev, S., Jia, Y., et al.: A category-level 3-D object dataset: putting the Kinect to work // international Conference on Computer Vision Workshops, Barcelona, IEEE, 1168–1174 (2011).Google Scholar
  10. 10.
    Wang, Z., Song, X., Wang, S, Z., et al.: Filling Kinect depth holes via position-guided matrix completion. Neurocomputing, 215, 48–52 (2016).Google Scholar
  11. 11.
    Scharstein, D., Pal. C.: Learning conditional random fields for stereo. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, June (2007).Google Scholar
  12. 12.
    Jingyu, Yang. et al.: Color-Guided Depth Recovery From RGB-D Data Using an Adaptive Autoregressive Model. IEEE Transactions on Image Processing 23, 3443–3458 (2014).Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Xingrui Zhang
    • 1
    Email author
  • Qian Guo
    • 2
  • Yudong Guan
    • 1
  • Jianying Feng
    • 1
  • Chunli Ti
    • 1
  1. 1.School of Electronics and Information EngineeringHarbin Institute of TechnologyHarbinChina
  2. 2.Beijing Automation Control Equipment Research InstituteBeijingChina

Personalised recommendations