Gyroscope-Aided Motion Deblurring with Deep Networks
This addresses motion blur issues in photography and computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of removing strong, spatially-variant motion blur in images by integrating gyroscope measurements into a convolutional neural network, resulting in improved visual quality and real-time performance.
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.