Abstract

Due to the shortage of paired images, the training of reflection removal networks relies heavily on synthesized samples, for which the ground truths of transmission and reflection are both known. But most existing CNN-based models cannot fully utilize the reflection information, which may cause performance limitations. In this paper, our goal is to design a novel, to the best of our knowledge, network that can take the reflection layer to refine the transmission layer. To this end, we propose a two-stage generative-adversarial-network-based network, where the first stage is used to obtain the coarse estimation of transmission and reflection, and the second stage is used to achieve the refinement. In addition, instead of just applying two penalty terms on the two coarse predictions in previous works, we consider the coarse reflection as a soft mask overlapped on the transmission and apply the recently proposed gated convolution into the second stage for further refinement. The network is trained with an adversarial frame using WGAN. The experimental results with benchmark datasets indicate that our method outperforms several state-of-the-art networks.

© 2021 Optical Society of America

Full Article  |  PDF Article
More Like This
Weakly supervised serous retinal detachment segmentation in SD-OCT images by two-stage learning

Ruiwen Xing, Sijie Niu, Xizhan Gao, Tingting Liu, Wen Fan, and Yuehui Chen
Biomed. Opt. Express 12(4) 2312-2327 (2021)

Quantitative phase imaging in digital holographic microscopy based on image inpainting using a two-stage generative adversarial network

Shujun Ma, Qi Liu, Yantao Yu, Yu Luo, and Shiliang Wang
Opt. Express 29(16) 24928-24946 (2021)

Artifact removal in photoacoustic tomography with an unsupervised method

Mengyang Lu, Xin Liu, Chengcheng Liu, Boyi Li, Wenting Gu, Jiehui Jiang, and Dean Ta
Biomed. Opt. Express 12(10) 6284-6299 (2021)

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Data Availability

Data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (7)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (3)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (11)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Metrics

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription