We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN). With the help of such measurements, it can handle extremely strong and spatially-variant motion blur. At the same time, the image data is used to overcome the limitations of gyro-based blur estimation. To train our network, we also introduce a novel way of generating realistic training data using the gyroscope. The evaluation shows a clear improvement in visual quality over the state-of-the-art while achieving real-time performance. Furthermore, the method is shown to improve the performance of existing feature detectors and descriptors against the motion blur.
翻译:我们建议一种分流方法,将陀螺仪测量纳入进化神经网络(CNN)。在这种测量的帮助下,它可以处理极其强大和空间变异的运动。与此同时,图像数据被用来克服基于陀螺仪的模糊估计的局限性。为了培训我们的网络,我们还采用了一种新的方法,利用陀螺仪生成现实的培训数据。评估显示,在取得实时性能的同时,相对于最新技术而言,视觉质量有了明显改善。此外,还展示了改进现有地物探测器和描述器在移动模糊性方面的性能的方法。