Abstract
Eliminating reflections on a single-image has been a challenging issue in image processing and computer vision, because defining an elaborate physical model to separate irregular reflections is almost impossible. In fact, while human vision can automatically focus on the transmitted object, basic deep neural networks even have a limitation to learn the attentive mechanism. In this paper, to solve this problem, a Generative Adversarial Networks guided by using Depth of Field (DoF) is proposed. The DoF is formulated by using image statistics and indicates the focused region of image. Thus, by adding this information to both generative and discriminative networks, the generator focuses on the transmitted layer and the discriminator will be able to estimate the local consistency of the restored areas. Since it is intractable to obtain the ground-truth transmitted layer in real images, a dataset with synthetic reflection is considered for quantitative evaluation. The experimental results demonstrate that the proposed method outperforms the existing approaches in both PSNR and SSIM. The visual outputs indicate that the proposed network convincingly eliminates the reflection and produce sufficient transmitted layers as compared to the previous methods.
Original language | English |
---|---|
Title of host publication | International Workshop on Advanced Imaging Technology, IWAIT 2020 |
Editors | Phooi Yee Lau, Mohammad Shobri |
Publisher | SPIE |
ISBN (Electronic) | 9781510638358 |
DOIs | |
Publication status | Published - 2020 |
Event | International Workshop on Advanced Imaging Technology, IWAIT 2020 - Yogyakarta, Indonesia Duration: 2020 Jan 5 → 2020 Jan 7 |
Publication series
Name | Proceedings of SPIE - The International Society for Optical Engineering |
---|---|
Volume | 11515 |
ISSN (Print) | 0277-786X |
ISSN (Electronic) | 1996-756X |
Conference
Conference | International Workshop on Advanced Imaging Technology, IWAIT 2020 |
---|---|
Country/Territory | Indonesia |
City | Yogyakarta |
Period | 20/1/5 → 20/1/7 |
Bibliographical note
Publisher Copyright:© 2020 SPIE.
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering