Events-to-Video: Bringing Modern Computer Vision to Event Cameras
This work enables the use of event cameras' high temporal resolution and dynamic range for a broader range of computer vision tasks, representing a significant shift rather than an incremental improvement.
The paper tackles the challenge of applying standard computer vision techniques to event cameras by reconstructing videos from event data, achieving over 20% improvement in image quality compared to state-of-the-art methods and outperforming specialized event-based algorithms on tasks like object classification and visual-inertial odometry.
Event cameras are novel sensors that report brightness changes in the form of asynchronous "events" instead of intensity frames. They have significant advantages over conventional cameras: high temporal resolution, high dynamic range, and no motion blur. Since the output of event cameras is fundamentally different from conventional cameras, it is commonly accepted that they require the development of specialized algorithms to accommodate the particular nature of events. In this work, we take a different view and propose to apply existing, mature computer vision techniques to videos reconstructed from event data. We propose a novel recurrent network to reconstruct videos from a stream of events, and train it on a large amount of simulated event data. Our experiments show that our approach surpasses state-of-the-art reconstruction methods by a large margin (> 20%) in terms of image quality. We further apply off-the-shelf computer vision algorithms to videos reconstructed from event data on tasks such as object classification and visual-inertial odometry, and show that this strategy consistently outperforms algorithms that were specifically designed for event data. We believe that our approach opens the door to bringing the outstanding properties of event cameras to an entirely new range of tasks. A video of the experiments is available at https://youtu.be/IdYrC4cUO0I