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

TL;DR

This paper introduces EVREAL, a comprehensive benchmark and analysis suite for evaluating event-based video reconstruction methods, providing standardized protocols, diverse datasets, and detailed performance insights.

Contribution

The paper presents EVREAL, an open-source framework that standardizes evaluation and enables detailed comparison of state-of-the-art event-based video reconstruction techniques.

Findings

EVREAL facilitates fair comparison of methods.

Analysis reveals strengths and weaknesses of current approaches.

Performance varies significantly across different scenarios.

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.