© The Institution of Engineering and Technology
Most of depth up-sampling algorithms are based on the consistent hypothesis, i.e. the object boundaries in the colour image are consistent with depth discontinuity regions in the depth map. However, the hypothesis is not always correct. Under the combined guidance of high-resolution (HR) depth edge map and HR colour image gradient map, a simple and efficient depth up-sampler is presented. Firstly, the consistent regions are distinguished from the other regions and more accurate depth edge points are found. Then, the initial up-sampled depth map from traditional bilinear interpolation is refined by an effective depth-assignment scheme. Extensive experiments demonstrate that the proposed method outperforms conventional interpolation algorithms and some other edge-based depth up-sampling methods.
References
-
-
1)
-
5. Kang, Y.S., Lee, S.B., Ho, Y.S.: ‘Depth map up-sampling using depth local features’, Electron. Lett., 2014, 50, pp. 170–171 (doi: 10.1049/el.2013.3956).
-
2)
-
3. Chanho, J., Sanghyun, J., Su, M.J.: ‘Depth map upsampling with image decomposition’, Electron. Lett., 2015, 52, pp. 1782–1784.
-
3)
-
23. Scharstein, D., Szeliski, R.: ‘A taxonomy and evaluation of dense two-frame stereo correspondence algorithms’, Int. J. Comput. Vis., 2002, 47, (1–3), pp. 7–42 (doi: 10.1023/A:1014573219977).
-
4)
-
19. Yuan, L., Sun, J., Quan, L., Shum, H.Y.: ‘Image deblurring with blurred/noisy image pairs’, ACM Trans. Graphics, 2007, 26, (3), p. 1 (doi: 10.1145/1276377.1276379).
-
5)
-
6. Jingyu, Y., Xinchen, Y., Kun, L., et al: ‘Color-guided depth recovery from RGB-D data using an adaptive autogressive model’, Trans. Image Process., 2014, 8, pp. 3443–3458.
-
6)
-
4. Diebel, J., Thrun, S.: ‘An application of Markov random fields to range sensing’, Adv. Neural Inf. Process. Syst., 2006, 18, pp. 291–298.
-
7)
-
2. Lee, S.B., Kwon, S., Ho, Y.S.: ‘Discontinuity adaptive depth upsampling for 3D video acquisition’, Electron. Lett., 2013, 49, pp. 612–1614 (doi: 10.1049/el.2013.0693).
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.2297
Related content
content/journals/10.1049/el.2017.2297
pub_keyword,iet_inspecKeyword,pub_concept
6
6