Towards Closing the Domain Gap with Event Cameras
This addresses the domain gap issue for autonomous driving systems, but it is incremental as it focuses on a specific lighting condition gap.
The paper tackles the domain gap problem in end-to-end driving by proposing event cameras as an alternative to traditional cameras, showing they maintain consistent performance across day-night lighting differences with domain-shift penalties comparable to or smaller than grayscale frames.
Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of traditional cameras we propose event cameras as a potential alternative which can maintain performance across lighting condition domain gaps without requiring additional adjustments. Our results show that event cameras maintain more consistent performance across lighting conditions, exhibiting domain-shift penalties that are generally comparable to or smaller than grayscale frames and provide superior baseline performance in cross-domain scenarios.