article · IEEE Signal Processing Letters · 2014

Fast Minimax Path-Based Joint Depth Interpolation

Longquan Dai, Feihu Zhang, Xing Mei, Xiaopeng Zhang

Cited by 6Abstract and details only

Abstract

We propose a fast minimax path-based depth interpolation method. The algorithm computes for each target pixel varying contributions from reliable depth seeds, and weighted averaging is used to interpolate missing depths. Compared with state-of-the-art joint geodesic upsampling method which selects the K nearest seeds to interpolate missing depths with O(Kn) complexity, our method does not need to limit the number of seeds to K and reduces the computational complexity to O(n). In addition, the minimax path chooses a path with the smallest maximum immediate pairwise pixel difference on it, so it tends to preserve sharp depth discontinuities better. In contrast to the results of previous depth upsampling algorithms, our approach can provide accurate depths with fewer artifacts.

Cite this paper

APA 7

Dai, L., Zhang, F., Mei, X., & Zhang, X. (2014). Fast Minimax Path-Based Joint Depth Interpolation. IEEE Signal Processing Letters, 22(5), 623–627. https://doi.org/10.1109/lsp.2014.2365527

MLA 9

Dai, Longquan, et al. “Fast Minimax Path-Based Joint Depth Interpolation.” IEEE Signal Processing Letters, vol. 22, no. 5, 2014, pp. 623–27, https://doi.org/10.1109/lsp.2014.2365527.

Chicago

Dai, Longquan, Feihu Zhang, Xing Mei, and Xiaopeng Zhang. 2014. “Fast Minimax Path-Based Joint Depth Interpolation.” IEEE Signal Processing Letters 22 (5): 623–27. https://doi.org/10.1109/lsp.2014.2365527.

Harvard

Dai, L. et al. (2014) ‘Fast Minimax Path-Based Joint Depth Interpolation’, IEEE Signal Processing Letters, 22(5), pp. 623–627. Available at: https://doi.org/10.1109/lsp.2014.2365527.

BibTeX

@article{dai2014fast,
  title = {{Fast Minimax Path-Based Joint Depth Interpolation}},
  author = {Dai, Longquan and Zhang, Feihu and Mei, Xing and Zhang, Xiaopeng},
  journal = {IEEE Signal Processing Letters},
  volume = {22},
  number = {5},
  pages = {623--627},
  year = {2014},
  doi = {10.1109/lsp.2014.2365527}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.