Name
Abstract | ||
|---|---|---|
Image demosaicing and denoising are import steps of image signal processing. Sequential executions of demosaicing and denoising have essential drawbacks that they degrade the results of each other. Joint demosaicing and denoising overcomes the difficulties by solving the two problems in one model. This paper introduces a unified object function with hidden priors and a variant of ADMM to recover a full-resolution color image with a noisy Bayer input. Experimental results demonstrate that our method performs better than state-of-the-art methods in both PSNR comparison and human vision. In addition, our method is much more robust to variations of noise level. |
Year | Venue | Keywords |
|---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Demosaicing, Denoising, Bayer image, ADMM |
Field | DocType | ISSN |
Noise reduction,Computer vision,Pattern recognition,Noise measurement,Computer science,Noise level,Robustness (computer science),Demosaicing,Minification,Artificial intelligence,Prior probability,Color image | Conference | 1522-4880 |
Citations | PageRank | References |
2 | 0.37 | 3 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hanlin Tan | 1 | 15 | 3.00 |
| Xiangrong Zeng | 2 | 10 | 5.20 |
| Shiming Lai | 3 | 2 | 0.70 |
| Yu Liu | 4 | 198 | 25.45 |
| Maojun Zhang | 5 | 314 | 48.74 |