GERD: Geometric event response data generation
This work addresses a gap for researchers in event-based vision by providing a tool for generating synthetic data, though it is incremental as it focuses on data generation rather than new algorithms.
The authors tackled the lack of foundational geometric models for event-based vision sensors by introducing GERD, a method to generate controlled event-based data through time-varying transformations of prototypical objects, resulting in curated event videos to facilitate geometric studies.
Event-based vision sensors are appealing because of their time resolution, higher dynamic range, and low-power consumption. They also provide data that is fundamentally different from conventional frame-based cameras: events are sparse, discrete, and require integration in time. Unlike conventional models grounded in established geometric and physical principles, event-based models lack comparable foundations. We introduce a method to generate event-based data under controlled transformations. Specifically, we subject a prototypical object to transformations that change over time to produce carefully curated event videos. We hope this work simplifies studies for geometric approaches in event-based vision. GERD is available at https://github.com/ncskth/gerd