Name
Abstract | ||
|---|---|---|
A robust depth of field (DOF) extension algorithm was proposed based on the refocusing property of a light field photograph and the depth-from-defocus approach of multi-focus image fusing. The main techniques of the algorithm are depth estimation and all-in-focus image estimation. By making use of the redundancy of a light field photograph, we leverage both estimations in a noisy environment. For the noise level smaller than 25dB, the proposed algorithm is still robust and the performance is better than other methods both in PSNR and SSIM. We conclude that the algorithm is robust to high noise. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ICAwST.2017.8256430 | 2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) |
Keywords | Field | DocType |
extending depth of field,light field,image fusion,all-in-focus | Computer vision,Noise measurement,Computer science,Noise level,Image estimation,Light field,Robustness (computer science),Redundancy (engineering),Lens (optics),Artificial intelligence,Depth of field | Conference |
ISSN | ISBN | Citations |
2325-5986 | 978-1-5386-2966-6 | 0 |
PageRank | References | Authors |
0.34 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shih-Shuo Tung | 1 | 0 | 0.34 |
| Hao-Chiang Shao | 2 | 9 | 4.97 |
| Wen-Liang Hwang | 3 | 32 | 6.93 |