Abstract

Quality prediction of virtual-views is important for free viewpoint video systems, and can be used as feedback to improve the performance of depth video coding and virtual-view rendering. In this paper, an efficient virtual-view peak signal to noise ratio (PSNR) prediction method is proposed. First, the effect of depth distortion on virtual-view quality is analyzed in detail, and a depth distortion tolerance (DDT) model that determines the DDT range is presented. Next, the DDT model is used to predict the virtual-view quality. Finally, a support vector machine (SVM) is utilized to train and obtain the virtual-view quality prediction model. Experimental results show that the Spearman’s rank correlation coefficient and root mean square error between the actual PSNR and the predicted PSNR by DDT model are 0.8750 and 0.6137 on average, and by the SVM prediction model are 0.9109 and 0.5831. The computational complexity of the SVM method is lower than the DDT model and the state-of-the-art methods.

© 2017 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Support vector machine firefly algorithm based optimization of lens system

Shahaboddin Shamshirband, Dalibor Petković, Nenad T. Pavlović, Sudheer Ch, Torki A. Altameem, and Abdullah Gani
Appl. Opt. 54(1) 37-45 (2015)

Optimizing multiview video plus depth retargeting technique for stereoscopic 3D displays

Feng Shao, Wenchong Lin, Randi Fu, Mei Yu, and Gangyi Jiang
Opt. Express 25(11) 12478-12492 (2017)

Data filtering with support vector machines in geometric camera calibration

B. Ergun, T. Kavzoglu, I Colkesen, and C. Sahin
Opt. Express 18(3) 1927-1936 (2010)

References

  • View by:
  • |
  • |
  • |

  1. A. Smolic, “3D video and free viewpoint video—From capture to display,” Pattern Recogn. 44, 1958–1968 (2011).
    [Crossref]
  2. C. Fehn, “Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3D-TV,” Proc. SPIE 5291, 93–104 (2004).
    [Crossref]
  3. L. Fang, Y. Xiang, and N.-M. Cheung, “Estimation of virtual view synthesis distortion toward virtual view position,” IEEE Trans. Image Process. 25, 1961–1976 (2016).
    [Crossref]
  4. Y. Xiang, N.-M. Cheung, J. Zhang, and L. Fang, “Analytical model for camera distance related 3D virtual view distortion estimation,” in IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October2014, pp. 5442–5446.
  5. Y. Yang and Q. Dai, “Contourlet-based image quality assessment for synthesised virtual image,” Electron. Lett. 46, 492–494 (2010).
    [Crossref]
  6. Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
    [Crossref]
  7. W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.
  8. H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
    [Crossref]
  9. G. Cheung, V. Velisavljevic, and A. Ortega, “On dependent bit allocation for multiview image coding with depth-image-based rendering,” IEEE Trans. Image Process. 20, 3179–3194 (2011).
    [Crossref]
  10. V. Velisavljevic, G. Cheung, and J. Chakareski, “Bit allocation for multiview image compression using cubic synthesized view distortion model,” in IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, 11–15 July2011, pp. 1–6.
  11. Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
    [Crossref]
  12. W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
    [Crossref]
  13. C. Li, X. Jin, and Q. Dai, “A novel distortion model for depth coding in 3D-HEVC,” in IEEE International Conference on Image Processing (ICIP), Paris, France, October2014, pp. 3228–3232.
  14. B. T. Oh and K.-J. Oh, “View synthesis distortion estimation for AVC-and HEVC-compatible 3-D video coding,” IEEE Trans. Circuits Syst. Video Technol. 24, 1006–1015 (2014).
    [Crossref]
  15. M. Yang, C. Zhu, X. Lan, and N. Zheng, “Parameter-free view synthesis distortion model with application to depth video coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, May2015, pp. 2812–2815.
  16. D. Zhang and J. Liang, “View synthesis distortion estimation with a graphical model and recursive calculation of probability distribution,” IEEE Trans. Circuits Syst. Video Technol. 25, 827–840 (2015).
    [Crossref]
  17. Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
    [Crossref]
  18. Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
    [Crossref]
  19. H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
    [Crossref]

2016 (3)

L. Fang, Y. Xiang, and N.-M. Cheung, “Estimation of virtual view synthesis distortion toward virtual view position,” IEEE Trans. Image Process. 25, 1961–1976 (2016).
[Crossref]

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

2015 (3)

D. Zhang and J. Liang, “View synthesis distortion estimation with a graphical model and recursive calculation of probability distribution,” IEEE Trans. Circuits Syst. Video Technol. 25, 827–840 (2015).
[Crossref]

Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

2014 (3)

B. T. Oh and K.-J. Oh, “View synthesis distortion estimation for AVC-and HEVC-compatible 3-D video coding,” IEEE Trans. Circuits Syst. Video Technol. 24, 1006–1015 (2014).
[Crossref]

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
[Crossref]

2011 (3)

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

G. Cheung, V. Velisavljevic, and A. Ortega, “On dependent bit allocation for multiview image coding with depth-image-based rendering,” IEEE Trans. Image Process. 20, 3179–3194 (2011).
[Crossref]

A. Smolic, “3D video and free viewpoint video—From capture to display,” Pattern Recogn. 44, 1958–1968 (2011).
[Crossref]

2010 (1)

Y. Yang and Q. Dai, “Contourlet-based image quality assessment for synthesised virtual image,” Electron. Lett. 46, 492–494 (2010).
[Crossref]

2004 (1)

C. Fehn, “Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3D-TV,” Proc. SPIE 5291, 93–104 (2004).
[Crossref]

Chakareski, J.

V. Velisavljevic, G. Cheung, and J. Chakareski, “Bit allocation for multiview image compression using cubic synthesized view distortion model,” in IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, 11–15 July2011, pp. 1–6.

Chang, Y.

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

Cheung, G.

G. Cheung, V. Velisavljevic, and A. Ortega, “On dependent bit allocation for multiview image coding with depth-image-based rendering,” IEEE Trans. Image Process. 20, 3179–3194 (2011).
[Crossref]

V. Velisavljevic, G. Cheung, and J. Chakareski, “Bit allocation for multiview image compression using cubic synthesized view distortion model,” in IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, 11–15 July2011, pp. 1–6.

Cheung, N.-M.

L. Fang, Y. Xiang, and N.-M. Cheung, “Estimation of virtual view synthesis distortion toward virtual view position,” IEEE Trans. Image Process. 25, 1961–1976 (2016).
[Crossref]

Y. Xiang, N.-M. Cheung, J. Zhang, and L. Fang, “Analytical model for camera distance related 3D virtual view distortion estimation,” in IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October2014, pp. 5442–5446.

Dai, Q.

Y. Yang and Q. Dai, “Contourlet-based image quality assessment for synthesised virtual image,” Electron. Lett. 46, 492–494 (2010).
[Crossref]

C. Li, X. Jin, and Q. Dai, “A novel distortion model for depth coding in 3D-HEVC,” in IEEE International Conference on Image Processing (ICIP), Paris, France, October2014, pp. 3228–3232.

Fang, L.

L. Fang, Y. Xiang, and N.-M. Cheung, “Estimation of virtual view synthesis distortion toward virtual view position,” IEEE Trans. Image Process. 25, 1961–1976 (2016).
[Crossref]

Y. Xiang, N.-M. Cheung, J. Zhang, and L. Fang, “Analytical model for camera distance related 3D virtual view distortion estimation,” in IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October2014, pp. 5442–5446.

Fehn, C.

C. Fehn, “Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3D-TV,” Proc. SPIE 5291, 93–104 (2004).
[Crossref]

Gomila, C.

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.

Guan, T.

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Hu, J. H.

Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
[Crossref]

Hu, R. M.

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Hu, S.

Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
[Crossref]

Huo, J.

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

Jin, X.

C. Li, X. Jin, and Q. Dai, “A novel distortion model for depth coding in 3D-HEVC,” in IEEE International Conference on Image Processing (ICIP), Paris, France, October2014, pp. 3228–3232.

Kim, W.-S.

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.

Kuo, C.-C. J.

Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
[Crossref]

Kwong, S.

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
[Crossref]

Lai, P.

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.

Lan, X.

M. Yang, C. Zhu, X. Lan, and N. Zheng, “Parameter-free view synthesis distortion model with application to depth video coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, May2015, pp. 2812–2815.

Li, C.

C. Li, X. Jin, and Q. Dai, “A novel distortion model for depth coding in 3D-HEVC,” in IEEE International Conference on Image Processing (ICIP), Paris, France, October2014, pp. 3228–3232.

Li, F. R.

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

Liang, J.

D. Zhang and J. Liang, “View synthesis distortion estimation with a graphical model and recursive calculation of probability distribution,” IEEE Trans. Circuits Syst. Video Technol. 25, 827–840 (2015).
[Crossref]

Lu, T.

Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
[Crossref]

Lu, Z.

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

Oh, B. T.

B. T. Oh and K.-J. Oh, “View synthesis distortion estimation for AVC-and HEVC-compatible 3-D video coding,” IEEE Trans. Circuits Syst. Video Technol. 24, 1006–1015 (2014).
[Crossref]

Oh, K.-J.

B. T. Oh and K.-J. Oh, “View synthesis distortion estimation for AVC-and HEVC-compatible 3-D video coding,” IEEE Trans. Circuits Syst. Video Technol. 24, 1006–1015 (2014).
[Crossref]

Ortega, A.

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

G. Cheung, V. Velisavljevic, and A. Ortega, “On dependent bit allocation for multiview image coding with depth-image-based rendering,” IEEE Trans. Image Process. 20, 3179–3194 (2011).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.

Shen, J. L.

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Smolic, A.

A. Smolic, “3D video and free viewpoint video—From capture to display,” Pattern Recogn. 44, 1958–1968 (2011).
[Crossref]

Song, X. W.

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Tian, D.

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.

Velisavljevic, V.

G. Cheung, V. Velisavljevic, and A. Ortega, “On dependent bit allocation for multiview image coding with depth-image-based rendering,” IEEE Trans. Image Process. 20, 3179–3194 (2011).
[Crossref]

V. Velisavljevic, G. Cheung, and J. Chakareski, “Bit allocation for multiview image compression using cubic synthesized view distortion model,” in IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, 11–15 July2011, pp. 1–6.

Wang, S. Z.

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
[Crossref]

Wang, X.

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Wang, Z.

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
[Crossref]

Xiang, Y.

L. Fang, Y. Xiang, and N.-M. Cheung, “Estimation of virtual view synthesis distortion toward virtual view position,” IEEE Trans. Image Process. 25, 1961–1976 (2016).
[Crossref]

Y. Xiang, N.-M. Cheung, J. Zhang, and L. Fang, “Analytical model for camera distance related 3D virtual view distortion estimation,” in IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October2014, pp. 5442–5446.

Xiao, J.

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Yang, F.

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

Yang, M.

M. Yang, C. Zhu, X. Lan, and N. Zheng, “Parameter-free view synthesis distortion model with application to depth video coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, May2015, pp. 2812–2815.

Yang, Y.

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Y. Yang and Q. Dai, “Contourlet-based image quality assessment for synthesised virtual image,” Electron. Lett. 46, 492–494 (2010).
[Crossref]

Yu, L.

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Yuan, H.

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

Zhang, D.

D. Zhang and J. Liang, “View synthesis distortion estimation with a graphical model and recursive calculation of probability distribution,” IEEE Trans. Circuits Syst. Video Technol. 25, 827–840 (2015).
[Crossref]

Zhang, J.

Y. Xiang, N.-M. Cheung, J. Zhang, and L. Fang, “Analytical model for camera distance related 3D virtual view distortion estimation,” in IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October2014, pp. 5442–5446.

Zhang, Y.

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
[Crossref]

Zheng, N.

M. Yang, C. Zhu, X. Lan, and N. Zheng, “Parameter-free view synthesis distortion model with application to depth video coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, May2015, pp. 2812–2815.

Zhong, R.

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Zhu, C.

M. Yang, C. Zhu, X. Lan, and N. Zheng, “Parameter-free view synthesis distortion model with application to depth video coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, May2015, pp. 2812–2815.

Electron. Lett. (1)

Y. Yang and Q. Dai, “Contourlet-based image quality assessment for synthesised virtual image,” Electron. Lett. 46, 492–494 (2010).
[Crossref]

IEEE Trans. Broadcast. (1)

H. Yuan, S. Kwong, X. Wang, Y. Zhang, and F. R. Li, “A virtual view PSNR estimation method for 3-D videos,” IEEE Trans. Broadcast. 62, 134–140 (2016).
[Crossref]

IEEE Trans. Circuits Syst. Video Technol. (3)

D. Zhang and J. Liang, “View synthesis distortion estimation with a graphical model and recursive calculation of probability distribution,” IEEE Trans. Circuits Syst. Video Technol. 25, 827–840 (2015).
[Crossref]

B. T. Oh and K.-J. Oh, “View synthesis distortion estimation for AVC-and HEVC-compatible 3-D video coding,” IEEE Trans. Circuits Syst. Video Technol. 24, 1006–1015 (2014).
[Crossref]

H. Yuan, Y. Chang, J. Huo, F. Yang, and Z. Lu, “Model based joint bit allocation between texture videos and depth maps for 3D video coding,” IEEE Trans. Circuits Syst. Video Technol. 21, 485–497 (2011).
[Crossref]

IEEE Trans. Image Process. (4)

G. Cheung, V. Velisavljevic, and A. Ortega, “On dependent bit allocation for multiview image coding with depth-image-based rendering,” IEEE Trans. Image Process. 20, 3179–3194 (2011).
[Crossref]

L. Fang, Y. Xiang, and N.-M. Cheung, “Estimation of virtual view synthesis distortion toward virtual view position,” IEEE Trans. Image Process. 25, 1961–1976 (2016).
[Crossref]

Y. Zhang, S. Kwong, S. Hu, and C.-C. J. Kuo, “Efficient multiview depth coding optimization based on allowable depth distortion in view synthesis,” IEEE Trans. Image Process. 23, 4879–4892 (2014).
[Crossref]

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map coding optimization using rendered view distortion for 3D video coding,” IEEE Trans. Image Process. 24, 3534–3545 (2015).
[Crossref]

Inf. Sci. (1)

Y. Yang, X. Wang, T. Guan, J. L. Shen, and L. Yu, “A multi-dimensional image quality prediction model for user-generated images in social networks,” Inf. Sci. 281, 601–610 (2014).
[Crossref]

Neurocomputing (1)

Z. Wang, X. W. Song, S. Z. Wang, J. Xiao, R. Zhong, and R. M. Hu, “Filling Kinect depth holes via position-guided matrix completion,” Neurocomputing 215, 48–52 (2016).
[Crossref]

Pattern Recogn. (1)

A. Smolic, “3D video and free viewpoint video—From capture to display,” Pattern Recogn. 44, 1958–1968 (2011).
[Crossref]

Pattern Recogn. Lett. (1)

Z. Wang, J. H. Hu, S. Z. Wang, and T. Lu, “Trilateral constrained sparse representation for Kinect depth hole filling,” Pattern Recogn. Lett. 65, 95–102 (2015).
[Crossref]

Proc. SPIE (1)

C. Fehn, “Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3D-TV,” Proc. SPIE 5291, 93–104 (2004).
[Crossref]

Other (5)

Y. Xiang, N.-M. Cheung, J. Zhang, and L. Fang, “Analytical model for camera distance related 3D virtual view distortion estimation,” in IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October2014, pp. 5442–5446.

W.-S. Kim, A. Ortega, P. Lai, D. Tian, and C. Gomila, “Depth map distortion analysis for view rendering and depth coding,” in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7–10 November2009, pp. 721–724.

V. Velisavljevic, G. Cheung, and J. Chakareski, “Bit allocation for multiview image compression using cubic synthesized view distortion model,” in IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, 11–15 July2011, pp. 1–6.

C. Li, X. Jin, and Q. Dai, “A novel distortion model for depth coding in 3D-HEVC,” in IEEE International Conference on Image Processing (ICIP), Paris, France, October2014, pp. 3228–3232.

M. Yang, C. Zhu, X. Lan, and N. Zheng, “Parameter-free view synthesis distortion model with application to depth video coding,” in IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, May2015, pp. 2812–2815.

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (6)

Fig. 1.
Fig. 1.

Relationship between distortion in the depth map and geometry errors in virtual-view.

Fig. 2.
Fig. 2.

Depth distortion and virtual-view rendering distortion. (a) Uncompressed depth map; (b) compressed depth map; (c) depth difference map; (d) synthesized image with uncompressed depth map; (e) synthesized image with compressed depth map; (f) rendering distortion.

Fig. 3.
Fig. 3.

Illustration of tolerable depth distortion.

Fig. 4.
Fig. 4.

Intolerable depth distortion mask.

Fig. 5.
Fig. 5.

Pixel projection with and without depth error using 3D warping.

Fig. 6.
Fig. 6.

Actual PSNRs and estimated PSNRs comparison, successive 30 frames with QP=35. (a) Book Arrival; (b) Door Flowers; (c) Leave Laptop; (d) Alt Moabit; (e) Newspaper; (f) Lovebird1; (g) Kendo; (h) Balloons.

Tables (4)

Tables Icon

Table 1. Test Sequences

Tables Icon

Table 2. Actual PSNR and the Estimated PSNRs of Various Methods

Tables Icon

Table 3. RMSE, SRCC, and PLCC among the Actual PSNRs and the Estimated PSNRs of Various Methods

Tables Icon

Table 4. Computational Complexity Comparison of Various Methods

Equations (16)

Equations on this page are rendered with MathJax. Learn more.

dp=b·f255[(1znear1zfar)·d+1zfar],
dp=α·d+β,
d=d+Δd.
Δdp=α·Δd.
ex1=(ey1+ey2)/2=(|Sw(y1)S¯w(y1)|+|Sw(y2)S¯w(y2)|)/2,
ex1=(|C(x1)C¯(x0)|+|C(x2)C¯(x1)|)/2,
ex1=(|C(x1)C(x0)|+|C(x2)C(x1)|)/2,
E=i=1nei2,
YPSNR=10·log10(2552·NE),
Cgra1=|C(x2)C(x1)|,
Cgra2=|C(x1)C(x0)|,
gra1=x2x1=(y2(α·D(x2)+β))(y2(α·D¯(x1)+β))=(y2(α·(D(x1)+dgra1))(y2α·D¯(x1))=α·(δD(x1)dgra1),
gra2=x1x0=(y1α·(D(x1)+β))(y1α·(D¯(x0)+β))=(y1α·D(x1))(y1α·(D¯(x1)+dgra2))=α·(δD(x1)+dgra2),
ex1=(|C(x1)C(x1+gra1)|+|C(x1)C(x1gra2)|)/2.
MSE=1nk=1n[C(k)Cave]2,
f(Ch)=WT·ϕ(Ch)+b,

Metrics