Learning to Deblur and Generate High Frame Rate Video with an Event Camera
This addresses the issue of motion blur in high-speed video recording for applications like robotics or sports analysis, representing an incremental improvement by combining event data with existing network architectures.
The paper tackles the problem of motion blur in traditional cameras by using event camera data to deblur images and generate high-frame-rate videos, achieving results that outperform state-of-the-art methods in producing sharper outputs.
Event cameras are bio-inspired cameras which can measure the change of intensity asynchronously with high temporal resolution. One of the event cameras' advantages is that they do not suffer from motion blur when recording high-speed scenes. In this paper, we formulate the deblurring task on traditional cameras directed by events to be a residual learning one, and we propose corresponding network architectures for effective learning of deblurring and high frame rate video generation tasks. We first train a modified U-Net network to restore a sharp image from a blurry image using corresponding events. Then we train another similar network with different downsampling blocks to generate high frame rate video using the restored sharp image and events. Experiment results show that our method can restore sharper images and videos than state-of-the-art methods.