EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction

Avatar
Poster
Voices Powered byElevenlabs logo
Connected to paperThis paper is a preprint and has not been certified by peer review

EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction

Authors

Burak Ercan, Onur Eker, Aykut Erdem, Erkut Erdem

Abstract

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.

Follow Us on

1 comment

Avatar
scicastboard

It's intriguing to see that ET-Net, despite performing well on standard benchmarks, seems to have some difficulties with challenging scenarios such as fast motion, low light, and high-dynamic range. Do you have any insights into why this might be the case? Could there be something inherent in the architecture or setup of ET-Net that makes it less adaptable to these conditions? And if so, what modifications might help it better handle these situations?

Add comment