Acta Physica Sinica, Volume. 69, Issue 6, 064201-1(2020)
Figures & Tables(8)
Fig. 3. Performance of reconstructed image: (a) Performance in sparsity, pixels = 256 × 256; (b) performance in sparsity, pixels = 512 × 512; (c) PSNR in different resolution; (d) performance in redundancy, pixels = 256 × 256.
Fig. 4. Image reconstruction in different sparsity and redundancy: (a)
Fig. 5. Dense reconstruction of light field with occluded targets: (a) Dense light field; (b), (e) reference images; (c), (d) reconstructed virtual images of view 2 and view 5; (g), (h) target images; (f), (i) residual images.
Fig. 6. Dense reconstruction of light field: (a) Reconstructed image for proposed algorithm; (b) reconstructed image for DIBR; (c) target image; (d) residual image; (e) dense light field.
Table 1. Performance of image reconstruction in different sparsity and redundancy
View tableView in ArticleTable 1. Performance of image reconstruction in different sparsity and redundancy
Sparse parameter (K), Redundancy parameter (N) MSE PSNR/dB SSIM Time/s K = 16, N = 256 54.4215 30.7731 0.8860 1266.08 K = 34, N = 1024 49.0044 31.2285 0.8865 14306.55
Table 2. Dense reconstruction of light field in different scenes.
View tableView in ArticleTable 2. Dense reconstruction of light field in different scenes.
Sense Table Bicycle town Boardgames rosemary Vinyl bicycle* * 稀疏度K = 34, 冗余度N = 1024. MSE 21.2124 54.4215 25.8005 53.9244 18.8950 22.4756 49.0044 PSNR/dB 34.8649 30.7731 34.0145 30.8129 35.3673 34.6137 31.2285 SSIM 0.9323 0.8860 0.9474 0.9341 0.9699 0.9421 0.8865
Tools
Get Citation
Copy Citation Text
Zheng-De Xia, Na Song, Bin Liu, Jin-Xiao Pan, Wen-Min Yan, Zi-Hui Shao.
Paper Information
Category:
Received: Oct. 23, 2019
Accepted: --
Published Online: Nov. 19, 2020
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20