Chang Yakun, Jung Cheolkon
IEEE Trans Image Process. 2018 Nov 9. doi: 10.1109/TIP.2018.2880088.
When people take a picture through glass, the scene behind the glass is often interfered by specular reflection. Due to relatively easy implementation, most studies have tried to recover the transmitted scene from multiple images rather than single image. However, the use of multiple images is not practical for common users in real situations due to the critical shooting conditions. In this paper, we propose single image reflection removal using convolutional neural networks. We provide a ghosting model that causes reflection effects in captured images. First, we synthesize multiple reflection images from the input single one based on ghosting model and relative intensity. Then, we construct an end-to-end network that consists of encoder and decoder. To optimize the network parameters, we use a joint training strategy to learn the layer separation knowledge from the synthesized reflection images. For the loss function, we utilize both internal and external losses in optimization. Finally, we apply the proposed network to single image reflection removal. Compared with the previous work, the proposed method does not need handcrafted features and specular filters for reflection removal. Experimental results show that the proposed method successfully removes reflection from both synthetic and real images as well as achieves the highest scores in PSNR, SSIM and FSIM.
当人们透过玻璃拍照时，玻璃后的场景常常会受到镜面反射的干扰。由于实现起来相对容易，大多数研究都试图从多幅图像而非单幅图像中恢复透射场景。然而，在实际情况下，由于拍摄条件苛刻，使用多幅图像对普通用户来说并不实用。在本文中，我们提出了使用卷积神经网络去除单幅图像中的反射。我们提供了一个在捕获图像中产生反射效果的重影模型。首先，我们基于重影模型和相对强度从输入的单幅图像合成多幅反射图像。然后，我们构建一个由编码器和解码器组成的端到端网络。为了优化网络参数，我们使用联合训练策略从合成的反射图像中学习层分离知识。对于损失函数，我们在优化中同时使用内部损失和外部损失。最后，我们将所提出的网络应用于单幅图像反射去除。与之前的工作相比，所提出的方法在去除反射时不需要手工特征和镜面滤波器。实验结果表明，所提出的方法成功地从合成图像和真实图像中去除了反射，并且在PSNR、SSIM和FSIM方面取得了最高分。
