LLNet: A deep autoencoder approach to natural low-light image enhancement
详细信息 查看全文
- 作者：Kin Gwn Lore kglore@iastate.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Adedotun Akintayo akintayo@iastate.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Soumik Sarkar ; soumiks@iastate.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Image enhancement ; Natural low-light images ; Deep autoencoders
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：650-662
- 全文大小：5479 K
文摘
- •
Novel application of stacked sparse denoising autoencoder enhances low-light images.
- •
Simultaneous learning of contrast-enhancement and denoising (LLNet).
- •
Sequential learning of contrast-enhancement and denoising (Staged LLNet).
- •
Synthetically trained model evaluated on natural low-light images.
- •
Learned features visualized to gain insights about the model.