| Autor: |
Xiaodong Kuang, Xiubao Sui, Yuan Liu, Qian Chen, Guohua GU |
| Jazyk: |
angličtina |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
IEEE Photonics Journal, Vol 10, Iss 2, Pp 1-15 (2018) |
| Druh dokumentu: |
article |
| ISSN: |
1943-0655 |
| DOI: |
10.1109/JPHOT.2017.2779149 |
| Popis: |
In this paper, we propose a deep learning method for single infrared image optical noise removal. With a fully convolutional neural network, it is able to eliminate the optical noise in single infrared image. Our architecture consists of two networks: a denoising network and a conditional discriminator. The denoising network takes a noise image as input and outputs a denoising result, while the discriminator tries to make the output look more like the target. Actually, only in the testing phase, this method is feed-forward. Significant image quality in experiments is achieved compared with the existing method. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
