Abstract

In this paper, we propose a scheme based on sparse camera array and convolution neural network super-resolution for super-multiview integral imaging. In particular, the proposed scheme is adequate to not only the virtual-world three-dimensional scene with high performance and efficiency, but also the real-world 3D scene with higher availability than the traditional methods. In the proposed scheme, we first adopt the sparse camera array strategy to capture the sparse viewpoint images and use these images to synthesize the low-resolution elemental image array, then the convolution neural network super-resolution scheme is used to restore the high-resolution elemental image array from the low-resolution elemental image array for super-multiview integral image display. Experimental results verify the feasibility of the proposed scheme.

© 2019 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Multiple ray cluster rendering for interactive integral imaging system

Shaohui Jiao, Xiaoguang Wang, Mingcai Zhou, Weiming Li, Tao Hong, Dongkyung Nam, Jin-Ho Lee, Enhua Wu, Haitao Wang, and Ji-Yeun Kim
Opt. Express 21(8) 10070-10086 (2013)

Homogeneous light field model for interactive control of viewing parameters of integral imaging displays

Yin Xu, XiaoRui Wang, Yan Sun, and JianQi Zhang
Opt. Express 20(13) 14137-14151 (2012)

Nonlinear mapping method for the generation of an elemental image array in a photorealistic pseudoscopic free 3D display

Jun Wen, Xingpeng Yan, Xiaoyu Jiang, Zhiqiang Yan, Yifei Wang, and Junfu Wang
Appl. Opt. 57(22) 6375-6382 (2018)

References

  • View by:
  • |
  • |
  • |

  1. Y. Kim, K. Hong, and B. Lee, “Recent researches based on integral imaging display method,” 3D Res. 1, 17–27 (2010).
    [Crossref]
  2. Z. Yan, X. Yan, X. Jiang, and L. Ai, “Computational integral imaging reconstruction of perspective and orthographic view images by common patches analysis,” Opt. Express 25, 21887–21900 (2017).
    [Crossref]
  3. M. Guo, Y. Si, Y. Lyu, S. Wang, and F. Jin, “Elemental image array generation based on discrete viewpoint pickup and window interception in integral imaging,” Appl. Opt. 54, 876–884 (2015).
    [Crossref]
  4. C. C. Ji, C. G. Luo, H. Deng, D. H. Li, and Q. H. Wang, “Tilted elemental image array generation method for moiré-reduced computer generated integral imaging display,” Opt. Express 21, 19816–19824 (2013).
    [Crossref]
  5. Z. L. Xiong, S. L. Li, J. Chen, H. Deng, and Q. H. Wang, “Nonunified integral imaging elemental image array generation method based on selective pixel sampling algorithm,” Appl. Opt. 54, 2532–2536 (2015).
    [Crossref]
  6. S. W. Min, S. Choi, and Y. Takashima, “Improvement of fill factor in pinhole-type integral imaging display using a retroreflector,” Opt. Express 25, 33078–33087 (2017).
    [Crossref]
  7. X. W. Li, L. Li, and Q. H. Wang, “Wavelet-based iterative perfect reconstruction in computational integral imaging,” J. Opt. Soc. Am. A 35, 1212–1220 (2018).
    [Crossref]
  8. X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
    [Crossref]
  9. H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.
  10. K. Yanaka, “Integral photography using hexagonal fly’s eye lens and fractional view,” in Stereoscopic Displays and Applications XIX (International Society for Optics and Photonics, 2008), pp. 68031K.
  11. M. Suk, “Enhanced image mapping algorithm for 3D integral imaging display system,” in Information and Communications University (2005).
  12. M. Halle, “Multiple viewpoint rendering,” in Conference on Computer Graphics and Interactive Techniques (2010), pp. 243–254.
  13. K. S. Park, S. W. Min, and Y. Cho, “Viewpoint vector rendering for efficient elemental image generation,” IEICE Trans. Inf. Syst. 90, 233–241 (2007).
    [Crossref]
  14. Y. Cho, K. S. Park, and S. W. Min, “Design and implementation of a fast integral image rendering method,” in International Conference on Entertainment Computing (Springer, 2006), pp. 135–140.
  15. R. Yang, X. Huang, and S. Chen, “Efficient rendering of integral images,” in ACM SIGGRAPH 2005 Posters (ACM, 2005), pp. 44.
  16. S. Xing, X. Sang, X. Yu, C. Duo, B. Pang, X. Gao, and K. Wang, “High-efficient computer-generated integral imaging based on the backward ray-tracing technique and optical reconstruction,” Opt. Express 25, 330–338 (2017).
    [Crossref]
  17. K. C. Kwon, C. Park, M. U. Erdenebat, J. S. Jeong, J. H. Choi, N. Kim, and K. H. Yoo, “High speed image space parallel processing for computer-generated integral imaging system,” Opt. Express 20, 732–740 (2012).
    [Crossref]
  18. S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
    [Crossref]
  19. M. U. Erdenebat, B. J. Kim, Y. L. Piao, S. Y. Park, K. C. Kwon, M. L. Piao, K. H. Yoo, and N. Kim, “Three-dimensional image acquisition and reconstruction system on a mobile device based on computer-generated integral imaging,” Appl. Opt. 56, 7796–7802 (2017).
    [Crossref]
  20. C. Dong, C. C. Loy, and X. Tang, “Accelerating the super-resolution convolutional neural network,” in European Conference on Computer Vision (Springer, 2016), pp. 391–407.
  21. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
    [Crossref]
  22. L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
    [Crossref]
  23. https://github.com/Kohit/waifu2x-caffe-matlab .

2019 (1)

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

2018 (2)

X. W. Li, L. Li, and Q. H. Wang, “Wavelet-based iterative perfect reconstruction in computational integral imaging,” J. Opt. Soc. Am. A 35, 1212–1220 (2018).
[Crossref]

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

2017 (5)

2016 (1)

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

2015 (2)

2013 (1)

2012 (1)

2010 (1)

Y. Kim, K. Hong, and B. Lee, “Recent researches based on integral imaging display method,” 3D Res. 1, 17–27 (2010).
[Crossref]

2007 (1)

K. S. Park, S. W. Min, and Y. Cho, “Viewpoint vector rendering for efficient elemental image generation,” IEICE Trans. Inf. Syst. 90, 233–241 (2007).
[Crossref]

Ai, L.

Barreiro, J. C.

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

Chen, J.

Chen, N.

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Chen, S.

R. Yang, X. Huang, and S. Chen, “Efficient rendering of integral images,” in ACM SIGGRAPH 2005 Posters (ACM, 2005), pp. 44.

Chen, Y.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
[Crossref]

Cho, S. H.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Cho, Y.

K. S. Park, S. W. Min, and Y. Cho, “Viewpoint vector rendering for efficient elemental image generation,” IEICE Trans. Inf. Syst. 90, 233–241 (2007).
[Crossref]

Y. Cho, K. S. Park, and S. W. Min, “Design and implementation of a fast integral image rendering method,” in International Conference on Entertainment Computing (Springer, 2006), pp. 135–140.

Choi, B. S.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Choi, J. H.

Choi, S.

Deng, H.

Dong, C.

C. Dong, C. C. Loy, and X. Tang, “Accelerating the super-resolution convolutional neural network,” in European Conference on Computer Vision (Springer, 2016), pp. 391–407.

Dorado, A.

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

Duo, C.

Erdenebat, M. U.

Gao, X.

Guo, M.

Halle, M.

M. Halle, “Multiple viewpoint rendering,” in Conference on Computer Graphics and Interactive Techniques (2010), pp. 243–254.

Hong, K.

Y. Kim, K. Hong, and B. Lee, “Recent researches based on integral imaging display method,” 3D Res. 1, 17–27 (2010).
[Crossref]

Hong, S.

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

Huang, X.

R. Yang, X. Huang, and S. Chen, “Efficient rendering of integral images,” in ACM SIGGRAPH 2005 Posters (ACM, 2005), pp. 44.

Jang, S.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Jeon, H.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Jeong, J. S.

Ji, C. C.

Jiang, X.

Jin, F.

Kim, B. J.

Kim, N.

Kim, W. T.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Kim, Y.

Y. Kim, K. Hong, and B. Lee, “Recent researches based on integral imaging display method,” 3D Res. 1, 17–27 (2010).
[Crossref]

Kwag, J.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Kwon, K. C.

Lee, B.

Y. Kim, K. Hong, and B. Lee, “Recent researches based on integral imaging display method,” 3D Res. 1, 17–27 (2010).
[Crossref]

Lee, H. S.

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

Li, D. H.

Li, G.

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Li, L.

Li, S. L.

Li, X.

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

Li, X. W.

Liu, Y.

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

Loy, C. C.

C. Dong, C. C. Loy, and X. Tang, “Accelerating the super-resolution convolutional neural network,” in European Conference on Computer Vision (Springer, 2016), pp. 391–407.

Luo, C. G.

Lyu, Y.

Martinez-Corral, M.

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

Meng, D.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
[Crossref]

Meng, L.

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Min, S. W.

S. W. Min, S. Choi, and Y. Takashima, “Improvement of fill factor in pinhole-type integral imaging display using a retroreflector,” Opt. Express 25, 33078–33087 (2017).
[Crossref]

K. S. Park, S. W. Min, and Y. Cho, “Viewpoint vector rendering for efficient elemental image generation,” IEICE Trans. Inf. Syst. 90, 233–241 (2007).
[Crossref]

Y. Cho, K. S. Park, and S. W. Min, “Design and implementation of a fast integral image rendering method,” in International Conference on Entertainment Computing (Springer, 2006), pp. 135–140.

Pang, B.

Park, C.

Park, K. S.

K. S. Park, S. W. Min, and Y. Cho, “Viewpoint vector rendering for efficient elemental image generation,” IEICE Trans. Inf. Syst. 90, 233–241 (2007).
[Crossref]

Y. Cho, K. S. Park, and S. W. Min, “Design and implementation of a fast integral image rendering method,” in International Conference on Entertainment Computing (Springer, 2006), pp. 135–140.

Park, S. Y.

Piao, M. L.

Piao, Y. L.

Saavedra, G.

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

Sang, X.

Si, Y.

Situ, G.

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Suk, M.

M. Suk, “Enhanced image mapping algorithm for 3D integral imaging display system,” in Information and Communications University (2005).

Takashima, Y.

Tang, X.

C. Dong, C. C. Loy, and X. Tang, “Accelerating the super-resolution convolutional neural network,” in European Conference on Computer Vision (Springer, 2016), pp. 391–407.

Wang, H.

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Wang, K.

Wang, Q.

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

Wang, Q. H.

Wang, S.

Wang, W.

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Wang, Y.

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

Xing, S.

Xiong, Z. L.

Yan, X.

Yan, Z.

Yanaka, K.

K. Yanaka, “Integral photography using hexagonal fly’s eye lens and fractional view,” in Stereoscopic Displays and Applications XIX (International Society for Optics and Photonics, 2008), pp. 68031K.

Yang, R.

R. Yang, X. Huang, and S. Chen, “Efficient rendering of integral images,” in ACM SIGGRAPH 2005 Posters (ACM, 2005), pp. 44.

Yoo, K. H.

Yu, X.

Zhang, K.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
[Crossref]

Zhang, L.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
[Crossref]

Zhou, X.

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

Zuo, W.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
[Crossref]

3D Res. (1)

Y. Kim, K. Hong, and B. Lee, “Recent researches based on integral imaging display method,” 3D Res. 1, 17–27 (2010).
[Crossref]

Appl. Opt. (3)

IEEE Trans. Image Process. (1)

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).
[Crossref]

IEICE Trans. Inf. Syst. (1)

K. S. Park, S. W. Min, and Y. Cho, “Viewpoint vector rendering for efficient elemental image generation,” IEICE Trans. Inf. Syst. 90, 233–241 (2007).
[Crossref]

J. Disp. Technol. (1)

S. Hong, A. Dorado, G. Saavedra, J. C. Barreiro, and M. Martinez-Corral, “Three-dimensional integral-imaging display from calibrated and depth-hole filtered Kinect information,” J. Disp. Technol. 12, 1301–1308 (2016).
[Crossref]

J. Opt. Soc. Am. A (1)

Opt. Express (5)

Opt. Laser. Eng. (1)

X. Li, Y. Wang, Q. Wang, Y. Liu, and X. Zhou, “Modified integral imaging reconstruction and encryption using an improved SR reconstruction algorithm,” Opt. Laser. Eng. 112, 162–169 (2019).
[Crossref]

Sci. Rep. (1)

L. Meng, W. Wang, H. Wang, H. Wang, G. Li, N. Chen, and G. Situ, “Author correction: deep-learning-based ghost imaging,” Sci. Rep. 8, 6315 (2018).
[Crossref]

Other (8)

https://github.com/Kohit/waifu2x-caffe-matlab .

H. S. Lee, S. Jang, H. Jeon, B. S. Choi, S. H. Cho, W. T. Kim, and J. Kwag, “Large‐area ultra‐high density 5.36” 10  K × 6  K 2250 ppi display,” in SID Symposium Digest of Technical Papers (2018), pp. 607–609.

K. Yanaka, “Integral photography using hexagonal fly’s eye lens and fractional view,” in Stereoscopic Displays and Applications XIX (International Society for Optics and Photonics, 2008), pp. 68031K.

M. Suk, “Enhanced image mapping algorithm for 3D integral imaging display system,” in Information and Communications University (2005).

M. Halle, “Multiple viewpoint rendering,” in Conference on Computer Graphics and Interactive Techniques (2010), pp. 243–254.

C. Dong, C. C. Loy, and X. Tang, “Accelerating the super-resolution convolutional neural network,” in European Conference on Computer Vision (Springer, 2016), pp. 391–407.

Y. Cho, K. S. Park, and S. W. Min, “Design and implementation of a fast integral image rendering method,” in International Conference on Entertainment Computing (Springer, 2006), pp. 135–140.

R. Yang, X. Huang, and S. Chen, “Efficient rendering of integral images,” in ACM SIGGRAPH 2005 Posters (ACM, 2005), pp. 44.

Supplementary Material (1)

NameDescription
» Visualization 1       Diverse perspectives of the reconstructed 3D images for virtual 3D scene.

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 (10)

Fig. 1.
Fig. 1. Schematic diagram of the proposed super-multiview integral imaging scheme.
Fig. 2.
Fig. 2. Strategy of the sparse camera array pickup.
Fig. 3.
Fig. 3. Process of the high-resolution EIA restoration.
Fig. 4.
Fig. 4. Experimental setup for super-multiview integral imaging display for the virtual 3D scene.
Fig. 5.
Fig. 5. Local cropping images from (a) the restored high-resolution EIA with α = 4 and (b) the low-resolution EIA.
Fig. 6.
Fig. 6. Diverse perspectives of the reconstructed 3D images for the virtual 3D scene (see Visualization 1).
Fig. 7.
Fig. 7. Comparison between the traditional and our scheme in high-resolution EIAs and its reconstructed 3D images. (a) ECVIR method, (b) proposed scheme with α = 2 , and (c) proposed scheme with α = 4 .
Fig. 8.
Fig. 8. Viewpoint images generated by the center virtual camera, high-resolution EIAs with α = 4 , and reconstructed 3D images, including (a) “fish,” (b) “mushroom.” and (c) “head.”
Fig. 9.
Fig. 9. Elemental images with noise and the denoising results. (a),(c) Elemental images cropped from low-resolution EIAs with localvar noise; (b),(d) elemental images cropped from denoising high-resolution EIAs with α = 4 .
Fig. 10.
Fig. 10. Diverse perspectives of the reconstructed 3D images for a real-world 3D scene.

Tables (1)

Tables Icon

Table 1. Rendering Time of the Proposed and the Traditional Methods

Equations (2)

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

RT ECVIR = M × N × T VP ( R VP , C scene ) ,
R T SCA = ( 1 α · M ) × ( 1 α · N ) × T VP ( R VP , C scene ) = 1 α 2 RT ECVIR .

Metrics