TR2012-070

A Local Depth Image Enhancement Scheme for View Synthesis


    •  Wang, Y., Tian, D., Vetro, A., "A Local Depth Image Enhancement Scheme for View Synthesis", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109.ICIP.2012.6467562, September 2012, pp. 2725-2728.
      BibTeX TR2012-070 PDF
      • @inproceedings{Wang2012sep,
      • author = {Wang, Y. and Tian, D. and Vetro, A.},
      • title = {A Local Depth Image Enhancement Scheme for View Synthesis},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2012,
      • pages = {2725--2728},
      • month = sep,
      • doi = {10.1109.ICIP.2012.6467562},
      • issn = {1522-4880},
      • isbn = {978-1-4673-2534-9},
      • url = {https://www.merl.com/publications/TR2012-070}
      • }
  • MERL Contact:
  • Research Area:

    Digital Video

Abstract:

The quality of the depth map is crucial for depth image based rendering (DIBR) which enables a variety of advanced 3D video related applications such as perceived depth adjustment for stereoscopic video and intermediate view generation for multiview auto-stereoscopic displays. However, the input depth map for DIBR may suffer from errors and noise, which could seriously impact the rendered view quality. In order to reduce the errors and suppress the noise in the depth map, a local depth image enhancement technique is proposed that leverages trellis-based optimization techniques. A cost function is used to evaluate candidate depth values based on the stereo cost as well as color and depth consistency. Sparse depth features are also used in the enhancement process. The experimental results show notable subjective improvements in terms of rendering quality.

 

  • Related News & Events

    •  NEWS    ICIP 2012: 4 publications by Anthony Vetro, Shantanu D. Rane, Huifang Sun and Dong Tian
      Date: September 30, 2012
      Where: IEEE International Conference on Image Processing (ICIP)
      MERL Contacts: Anthony Vetro; Huifang Sun
      Brief
      • The papers "An Attribute-Based Framework for Privacy Preserving Image Querying" by Rane, S. and Sun, W., "Emerging Cryptographic Challenges in Image and Video Processing" by Puech, W., Erkin, Z., Barni, M., Rane, S. and Lagendijk, R.L., "A Local Depth Image Enhancement Scheme for View Synthesis" by Wang, Y., Tian, D. and Vetro, A. and "On Modeling the Rendering Error in 3D Video" by Cheung, N.-M., Tian, D., Vetro, A. and Sun, H. were presented at the IEEE International Conference on Image Processing (ICIP).
    •