论文标题
学习通过障碍物看到
Learning to See Through Obstructions
论文作者
论文摘要
我们提出了一种基于学习的方法，用于消除不必要的障碍物，例如窗户反射，围栏遮挡或雨滴，是从移动摄像机捕获的短序列中。我们的方法利用背景和阻塞元素之间的运动差异来恢复这两个层。具体而言，我们在估计两层的致密光流场和通过深卷积神经网络中重建每一层的密集光流场。基于学习的层重建使我们能够在流量估计和脆弱的假设（例如亮度一致性）中适应潜在的错误。我们表明，综合生成的数据培训很好地传输到真实图像。我们对众多挑战性反射和围栏清除方案的结果证明了该方法的有效性。
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera. Our method leverages the motion differences between the background and the obstructing elements to recover both layers. Specifically, we alternate between estimating dense optical flow fields of the two layers and reconstructing each layer from the flow-warped images via a deep convolutional neural network. The learning-based layer reconstruction allows us to accommodate potential errors in the flow estimation and brittle assumptions such as brightness consistency. We show that training on synthetically generated data transfers well to real images. Our results on numerous challenging scenarios of reflection and fence removal demonstrate the effectiveness of the proposed method.
