抄録
When we take a picture through glass windows, the photographs are often degraded by undesired reflections. To separate reflection layer and background layer is an important problem for enhancing image quality. However, single-image reflection removal is a challenging process because of the ill-posed nature of the problem. In this paper, we propose a single-image reflection removal method based on generative adversarial networks. Our network is an end-To-end trained network with four types of losses. It includes pixel loss, feature loss, adversarial loss, and gradient constraint loss. We propose a novel gradient constraint loss in order to separate the background layer and the reflection layer clearly. Gradient constraint loss is applied in a gradient domain and it minimizes the correlation between the background and reflection layer. Owing to the novel loss and our new synthetic dataset, our reflection removal method outperforms state-of-The-Art methods in PSNR and SSIM, especially in real world images.
本文言語 | English |
---|---|
論文番号 | 8868089 |
ページ(範囲) | 148790-148799 |
ページ数 | 10 |
ジャーナル | IEEE Access |
巻 | 7 |
DOI | |
出版ステータス | Published - 2019 |
ASJC Scopus subject areas
- コンピュータ サイエンス(全般)
- 材料科学(全般)
- 工学(全般)
- 電子工学および電気工学