EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset

TL;DR

This paper introduces EventAid, a comprehensive benchmark dataset and evaluation framework for event-aided image and video enhancement tasks, enabling fair comparison and analysis of state-of-the-art methods using real-captured data.

Contribution

It provides the first real-captured hybrid dataset for multiple event-aided enhancement tasks and offers a unified benchmarking platform for evaluating existing algorithms.

Findings

Quantitative and visual comparison of state-of-the-art methods

Analysis of event property effects on enhancement performance

Performance limits of event-aided image deblurring methods

Abstract

Event cameras are emerging imaging technology that offers advantages over conventional frame-based imaging sensors in dynamic range and sensing speed. Complementing the rich texture and color perception of traditional image frames, the hybrid camera system of event and frame-based cameras enables high-performance imaging. With the assistance of event cameras, high-quality image/video enhancement methods make it possible to break the limits of traditional frame-based cameras, especially exposure time, resolution, dynamic range, and frame rate limits. This paper focuses on five event-aided image and video enhancement tasks (i.e., event-based video reconstruction, event-aided high frame rate video reconstruction, image deblurring, image super-resolution, and high dynamic range image reconstruction), provides an analysis of the effects of different event properties, a real-captured and ground truth labeled benchmark dataset, a unified benchmarking of state-of-the-art methods, and an evaluation for two mainstream event simulators. In detail, this paper collects a real-captured evaluation dataset EventAid for five event-aided image/video enhancement tasks, by using "Event-RGB" multi-camera hybrid system, taking into account scene diversity and spatiotemporal synchronization. We further perform quantitative and visual comparisons for state-of-the-art algorithms, provide a controlled experiment to analyze the performance limit of event-aided image deblurring methods, and discuss open problems to inspire future research.