EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction
This work addresses the need for consistent comparison in event-based vision research, though it is incremental as it focuses on evaluation rather than new reconstruction methods.
The paper tackles the lack of standardized evaluation for event-based video reconstruction methods by proposing EVREAL, a unified benchmark and analysis suite, which provides detailed performance insights across varying scenarios and downstream tasks.
Event cameras are a new type of vision sensor that incorporates asynchronous and independent pixels, offering advantages over traditional frame-based cameras such as high dynamic range and minimal motion blur. However, their output is not easily understandable by humans, making the reconstruction of intensity images from event streams a fundamental task in event-based vision. While recent deep learning-based methods have shown promise in video reconstruction from events, this problem is not completely solved yet. To facilitate comparison between different approaches, standardized evaluation protocols and diverse test datasets are essential. This paper proposes a unified evaluation methodology and introduces an open-source framework called EVREAL to comprehensively benchmark and analyze various event-based video reconstruction methods from the literature. Using EVREAL, we give a detailed analysis of the state-of-the-art methods for event-based video reconstruction, and provide valuable insights into the performance of these methods under varying settings, challenging scenarios, and downstream tasks.